In this notebook, we'll build a neural network that can learn to play games through reinforcement learning. More specifically, we'll use Q-learning to train an agent to play a game called Cart-Pole. In this game, a freely swinging pole is attached to a cart. The cart can move to the left and right, and the goal is to keep the pole upright as long as possible.
We can simulate this game using OpenAI Gym. First, let's check out how OpenAI Gym works. Then, we'll get into training an agent to play the Cart-Pole game.
In [1]:
import gym
import tensorflow as tf
import numpy as np
Note: Make sure you have OpenAI Gym cloned into the same directory with this notebook. I've included
gymas a submodule, so you can rungit submodule --init --recursiveto pull the contents into thegymrepo.
In [2]:
# Create the Cart-Pole game environment
env = gym.make('CartPole-v1')
[2017-07-21 16:40:06,542] Making new env: CartPole-v1
In [4]:
dir(env.action_space)
Out[4]:
['__class__',
'__delattr__',
'__dict__',
'__dir__',
'__doc__',
'__eq__',
'__format__',
'__ge__',
'__getattribute__',
'__gt__',
'__hash__',
'__init__',
'__init_subclass__',
'__le__',
'__lt__',
'__module__',
'__ne__',
'__new__',
'__reduce__',
'__reduce_ex__',
'__repr__',
'__setattr__',
'__sizeof__',
'__str__',
'__subclasshook__',
'__weakref__',
'contains',
'from_jsonable',
'n',
'sample',
'to_jsonable']
We interact with the simulation through env. To show the simulation running, you can use env.render() to render one frame. Passing in an action as an integer to env.step will generate the next step in the simulation. You can see how many actions are possible from env.action_space and to get a random action you can use env.action_space.sample(). This is general to all Gym games. In the Cart-Pole game, there are two possible actions, moving the cart left or right. So there are two actions we can take, encoded as 0 and 1.
Run the code below to watch the simulation run.
In [3]:
env.reset()
rewards = []
for _ in range(100):
#env.render()
state, reward, done, info = env.step(env.action_space.sample()) # take a random action
rewards.append(reward)
if done:
rewards = []
env.reset()
In [4]:
#env.close()
To shut the window showing the simulation, use env.close().
If you ran the simulation above, we can look at the rewards:
In [5]:
print(rewards[-20:])
[1.0, 1.0, 1.0, 1.0]
The game resets after the pole has fallen past a certain angle. For each frame while the simulation is running, it returns a reward of 1.0. The longer the game runs, the more reward we get. Then, our network's goal is to maximize the reward by keeping the pole vertical. It will do this by moving the cart to the left and the right.
We train our Q-learning agent using the Bellman Equation:
$$ Q(s, a) = r + \gamma \max{Q(s', a')} $$where $s$ is a state, $a$ is an action, and $s'$ is the next state from state $s$ and action $a$.
Before we used this equation to learn values for a Q-table. However, for this game there are a huge number of states available. The state has four values: the position and velocity of the cart, and the position and velocity of the pole. These are all real-valued numbers, so ignoring floating point precisions, you practically have infinite states. Instead of using a table then, we'll replace it with a neural network that will approximate the Q-table lookup function.
Now, our Q value, $Q(s, a)$ is calculated by passing in a state to the network. The output will be Q-values for each available action, with fully connected hidden layers.
As I showed before, we can define our targets for training as $\hat{Q}(s,a) = r + \gamma \max{Q(s', a')}$. Then we update the weights by minimizing $(\hat{Q}(s,a) - Q(s,a))^2$.
For this Cart-Pole game, we have four inputs, one for each value in the state, and two outputs, one for each action. To get $\hat{Q}$, we'll first choose an action, then simulate the game using that action. This will get us the next state, $s'$, and the reward. With that, we can calculate $\hat{Q}$ then pass it back into the $Q$ network to run the optimizer and update the weights.
Below is my implementation of the Q-network. I used two fully connected layers with ReLU activations. Two seems to be good enough, three might be better. Feel free to try it out.
In [6]:
class QNetwork:
def __init__(self, learning_rate=0.01, state_size=4,
action_size=2, hidden_size=10,
name='QNetwork'):
# state inputs to the Q-network
with tf.variable_scope(name):
self.inputs_ = tf.placeholder(tf.float32, [None, state_size], name='inputs')
# One hot encode the actions to later choose the Q-value for the action
self.actions_ = tf.placeholder(tf.int32, [None], name='actions')
one_hot_actions = tf.one_hot(self.actions_, action_size)
# Target Q values for training
self.targetQs_ = tf.placeholder(tf.float32, [None], name='target')
# ReLU hidden layers
self.fc1 = tf.contrib.layers.fully_connected(self.inputs_, 256)
self.fc2 = tf.contrib.layers.fully_connected(self.fc1, 128)
self.fc3 = tf.contrib.layers.fully_connected(self.fc1, 64)
# Linear output layer
self.output = tf.contrib.layers.fully_connected(self.fc3, action_size,
activation_fn=None)
### Train with loss (targetQ - Q)^2
# output has length 2, for two actions. This next line chooses
# one value from output (per row) according to the one-hot encoded actions.
self.Q = tf.reduce_sum(tf.multiply(self.output, one_hot_actions), axis=1)
self.loss = tf.reduce_mean(tf.square(self.targetQs_ - self.Q))
self.opt = tf.train.AdamOptimizer(learning_rate).minimize(self.loss)
Reinforcement learning algorithms can have stability issues due to correlations between states. To reduce correlations when training, we can store the agent's experiences and later draw a random mini-batch of those experiences to train on.
Here, we'll create a Memory object that will store our experiences, our transitions $<s, a, r, s'>$. This memory will have a maxmium capacity, so we can keep newer experiences in memory while getting rid of older experiences. Then, we'll sample a random mini-batch of transitions $<s, a, r, s'>$ and train on those.
Below, I've implemented a Memory object. If you're unfamiliar with deque, this is a double-ended queue. You can think of it like a tube open on both sides. You can put objects in either side of the tube. But if it's full, adding anything more will push an object out the other side. This is a great data structure to use for the memory buffer.
In [7]:
from collections import deque
class Memory():
def __init__(self, max_size = 1000):
self.buffer = deque(maxlen=max_size)
def add(self, experience):
self.buffer.append(experience)
def sample(self, batch_size):
idx = np.random.choice(np.arange(len(self.buffer)),
size=batch_size,
replace=False)
return [self.buffer[ii] for ii in idx]
To learn about the environment and rules of the game, the agent needs to explore by taking random actions. We'll do this by choosing a random action with some probability $\epsilon$ (epsilon). That is, with some probability $\epsilon$ the agent will make a random action and with probability $1 - \epsilon$, the agent will choose an action from $Q(s,a)$. This is called an $\epsilon$-greedy policy.
At first, the agent needs to do a lot of exploring. Later when it has learned more, the agent can favor choosing actions based on what it has learned. This is called exploitation. We'll set it up so the agent is more likely to explore early in training, then more likely to exploit later in training.
Putting all this together, we can list out the algorithm we'll use to train the network. We'll train the network in episodes. One episode is one simulation of the game. For this game, the goal is to keep the pole upright for 195 frames. So we can start a new episode once meeting that goal. The game ends if the pole tilts over too far, or if the cart moves too far the left or right. When a game ends, we'll start a new episode. Now, to train the agent:
In [25]:
train_episodes = 10000 # max number of episodes to learn from
max_steps = 600 # max steps in an episode
gamma = 0.999 # future reward discount
# Exploration parameters
explore_start = 0.9 # exploration probability at start
explore_stop = 0.01 # minimum exploration probability
decay_rate = 0.000002 # exponential decay rate for exploration prob
# Network parameters
hidden_size = 64 # number of units in each Q-network hidden layer
learning_rate = 0.00001 # Q-network learning rate
# Memory parameters
memory_size = 100000 # memory capacity
batch_size = 32 # experience mini-batch size
pretrain_length = batch_size*2 # number experiences to pretrain the memory
previous_steps = 10
state_size = 4
batches_per_step = 20
In [26]:
tf.reset_default_graph()
mainQN = QNetwork(name='main', state_size=state_size*previous_steps, hidden_size=hidden_size, learning_rate=learning_rate)
In [27]:
def get_state(all_states, num_steps):
good_states = all_states[-num_steps:]
num_repeats = max(0, num_steps-len(good_states))
return np.concatenate(([np.zeros_like(good_states[0])] * num_repeats) + good_states)
In [28]:
# Initialize the simulation
env.reset()
# Take one random step to get the pole and cart moving
all_states = []
state, reward, done, _ = env.step(env.action_space.sample())
all_states = [state]
In [29]:
get_state(all_states,3)
Out[29]:
array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , -0.04515355, 0.24250584,
-0.00331733, -0.32490421])
In [30]:
memory = Memory(max_size=memory_size)
# Make a bunch of random actions and store the experiences
for ii in range(pretrain_length):
# Uncomment the line below to watch the simulation
# env.render()
# Make a random action
action = env.action_space.sample()
next_state, reward, done, _ = env.step(action)
if done:
# The simulation fails so no next state
next_state = np.zeros(state.shape)
# Add experience to memory
memory.add((get_state(all_states, previous_steps), action, reward, next_state))
# Start new episode
env.reset()
# Take one random step to get the pole and cart moving
state, reward, done, _ = env.step(env.action_space.sample())
all_states = [state]
else:
# Add experience to memory
memory.add((get_state(all_states, previous_steps), action, reward, next_state))
all_states.append(next_state)
In [31]:
memory.buffer
Out[31]:
deque([(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , -0.04515355, 0.24250584, -0.00331733, -0.32490421]),
0,
1.0,
array([-0.04030343, 0.04743128, -0.00981541, -0.03326928])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , -0.04515355, 0.24250584, -0.00331733,
-0.32490421, -0.04030343, 0.04743128, -0.00981541, -0.03326928]),
1,
1.0,
array([-0.03935481, 0.2426926 , -0.0104808 , -0.32903284])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , -0.04515355, 0.24250584,
-0.00331733, -0.32490421, -0.04030343, 0.04743128, -0.00981541,
-0.03326928, -0.03935481, 0.2426926 , -0.0104808 , -0.32903284]),
1,
1.0,
array([-0.03450095, 0.43796218, -0.01706145, -0.62500241])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , -0.04515355,
0.24250584, -0.00331733, -0.32490421, -0.04030343, 0.04743128,
-0.00981541, -0.03326928, -0.03935481, 0.2426926 , -0.0104808 ,
-0.32903284, -0.03450095, 0.43796218, -0.01706145, -0.62500241]),
0,
1.0,
array([-0.02574171, 0.24308251, -0.0295615 , -0.33774128])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
-0.04515355, 0.24250584, -0.00331733, -0.32490421, -0.04030343,
0.04743128, -0.00981541, -0.03326928, -0.03935481, 0.2426926 ,
-0.0104808 , -0.32903284, -0.03450095, 0.43796218, -0.01706145,
-0.62500241, -0.02574171, 0.24308251, -0.0295615 , -0.33774128]),
0,
1.0,
array([-0.02088006, 0.04839343, -0.03631633, -0.05452506])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , -0.04515355, 0.24250584, -0.00331733, -0.32490421,
-0.04030343, 0.04743128, -0.00981541, -0.03326928, -0.03935481,
0.2426926 , -0.0104808 , -0.32903284, -0.03450095, 0.43796218,
-0.01706145, -0.62500241, -0.02574171, 0.24308251, -0.0295615 ,
-0.33774128, -0.02088006, 0.04839343, -0.03631633, -0.05452506]),
1,
1.0,
array([-0.01991219, 0.24401677, -0.03740683, -0.35844125])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , -0.04515355, 0.24250584, -0.00331733,
-0.32490421, -0.04030343, 0.04743128, -0.00981541, -0.03326928,
-0.03935481, 0.2426926 , -0.0104808 , -0.32903284, -0.03450095,
0.43796218, -0.01706145, -0.62500241, -0.02574171, 0.24308251,
-0.0295615 , -0.33774128, -0.02088006, 0.04839343, -0.03631633,
-0.05452506, -0.01991219, 0.24401677, -0.03740683, -0.35844125]),
0,
1.0,
array([-0.01503186, 0.04944601, -0.04457565, -0.07778433])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , -0.04515355, 0.24250584,
-0.00331733, -0.32490421, -0.04030343, 0.04743128, -0.00981541,
-0.03326928, -0.03935481, 0.2426926 , -0.0104808 , -0.32903284,
-0.03450095, 0.43796218, -0.01706145, -0.62500241, -0.02574171,
0.24308251, -0.0295615 , -0.33774128, -0.02088006, 0.04839343,
-0.03631633, -0.05452506, -0.01991219, 0.24401677, -0.03740683,
-0.35844125, -0.01503186, 0.04944601, -0.04457565, -0.07778433]),
0,
1.0,
array([-0.01404294, -0.14500951, -0.04613134, 0.20050832])),
(array([ 0. , 0. , 0. , 0. , -0.04515355,
0.24250584, -0.00331733, -0.32490421, -0.04030343, 0.04743128,
-0.00981541, -0.03326928, -0.03935481, 0.2426926 , -0.0104808 ,
-0.32903284, -0.03450095, 0.43796218, -0.01706145, -0.62500241,
-0.02574171, 0.24308251, -0.0295615 , -0.33774128, -0.02088006,
0.04839343, -0.03631633, -0.05452506, -0.01991219, 0.24401677,
-0.03740683, -0.35844125, -0.01503186, 0.04944601, -0.04457565,
-0.07778433, -0.01404294, -0.14500951, -0.04613134, 0.20050832]),
1,
1.0,
array([-0.01694313, 0.05074082, -0.04212117, -0.10636261])),
(array([-0.04515355, 0.24250584, -0.00331733, -0.32490421, -0.04030343,
0.04743128, -0.00981541, -0.03326928, -0.03935481, 0.2426926 ,
-0.0104808 , -0.32903284, -0.03450095, 0.43796218, -0.01706145,
-0.62500241, -0.02574171, 0.24308251, -0.0295615 , -0.33774128,
-0.02088006, 0.04839343, -0.03631633, -0.05452506, -0.01991219,
0.24401677, -0.03740683, -0.35844125, -0.01503186, 0.04944601,
-0.04457565, -0.07778433, -0.01404294, -0.14500951, -0.04613134,
0.20050832, -0.01694313, 0.05074082, -0.04212117, -0.10636261]),
1,
1.0,
array([-0.01592831, 0.24644028, -0.04424843, -0.41203139])),
(array([-0.04030343, 0.04743128, -0.00981541, -0.03326928, -0.03935481,
0.2426926 , -0.0104808 , -0.32903284, -0.03450095, 0.43796218,
-0.01706145, -0.62500241, -0.02574171, 0.24308251, -0.0295615 ,
-0.33774128, -0.02088006, 0.04839343, -0.03631633, -0.05452506,
-0.01991219, 0.24401677, -0.03740683, -0.35844125, -0.01503186,
0.04944601, -0.04457565, -0.07778433, -0.01404294, -0.14500951,
-0.04613134, 0.20050832, -0.01694313, 0.05074082, -0.04212117,
-0.10636261, -0.01592831, 0.24644028, -0.04424843, -0.41203139]),
1,
1.0,
array([-0.0109995 , 0.44216065, -0.05248905, -0.71832937])),
(array([-0.03935481, 0.2426926 , -0.0104808 , -0.32903284, -0.03450095,
0.43796218, -0.01706145, -0.62500241, -0.02574171, 0.24308251,
-0.0295615 , -0.33774128, -0.02088006, 0.04839343, -0.03631633,
-0.05452506, -0.01991219, 0.24401677, -0.03740683, -0.35844125,
-0.01503186, 0.04944601, -0.04457565, -0.07778433, -0.01404294,
-0.14500951, -0.04613134, 0.20050832, -0.01694313, 0.05074082,
-0.04212117, -0.10636261, -0.01592831, 0.24644028, -0.04424843,
-0.41203139, -0.0109995 , 0.44216065, -0.05248905, -0.71832937]),
1,
1.0,
array([-0.00215629, 0.63796814, -0.06685564, -1.0270608 ])),
(array([-0.03450095, 0.43796218, -0.01706145, -0.62500241, -0.02574171,
0.24308251, -0.0295615 , -0.33774128, -0.02088006, 0.04839343,
-0.03631633, -0.05452506, -0.01991219, 0.24401677, -0.03740683,
-0.35844125, -0.01503186, 0.04944601, -0.04457565, -0.07778433,
-0.01404294, -0.14500951, -0.04613134, 0.20050832, -0.01694313,
0.05074082, -0.04212117, -0.10636261, -0.01592831, 0.24644028,
-0.04424843, -0.41203139, -0.0109995 , 0.44216065, -0.05248905,
-0.71832937, -0.00215629, 0.63796814, -0.06685564, -1.0270608 ]),
0,
1.0,
array([ 0.01060307, 0.4437968 , -0.08739686, -0.75609538])),
(array([-0.02574171, 0.24308251, -0.0295615 , -0.33774128, -0.02088006,
0.04839343, -0.03631633, -0.05452506, -0.01991219, 0.24401677,
-0.03740683, -0.35844125, -0.01503186, 0.04944601, -0.04457565,
-0.07778433, -0.01404294, -0.14500951, -0.04613134, 0.20050832,
-0.01694313, 0.05074082, -0.04212117, -0.10636261, -0.01592831,
0.24644028, -0.04424843, -0.41203139, -0.0109995 , 0.44216065,
-0.05248905, -0.71832937, -0.00215629, 0.63796814, -0.06685564,
-1.0270608 , 0.01060307, 0.4437968 , -0.08739686, -0.75609538]),
1,
1.0,
array([ 0.01947901, 0.64000771, -0.10251877, -1.07495041])),
(array([-0.02088006, 0.04839343, -0.03631633, -0.05452506, -0.01991219,
0.24401677, -0.03740683, -0.35844125, -0.01503186, 0.04944601,
-0.04457565, -0.07778433, -0.01404294, -0.14500951, -0.04613134,
0.20050832, -0.01694313, 0.05074082, -0.04212117, -0.10636261,
-0.01592831, 0.24644028, -0.04424843, -0.41203139, -0.0109995 ,
0.44216065, -0.05248905, -0.71832937, -0.00215629, 0.63796814,
-0.06685564, -1.0270608 , 0.01060307, 0.4437968 , -0.08739686,
-0.75609538, 0.01947901, 0.64000771, -0.10251877, -1.07495041]),
0,
1.0,
array([ 0.03227916, 0.44637876, -0.12401777, -0.8161197 ])),
(array([-0.01991219, 0.24401677, -0.03740683, -0.35844125, -0.01503186,
0.04944601, -0.04457565, -0.07778433, -0.01404294, -0.14500951,
-0.04613134, 0.20050832, -0.01694313, 0.05074082, -0.04212117,
-0.10636261, -0.01592831, 0.24644028, -0.04424843, -0.41203139,
-0.0109995 , 0.44216065, -0.05248905, -0.71832937, -0.00215629,
0.63796814, -0.06685564, -1.0270608 , 0.01060307, 0.4437968 ,
-0.08739686, -0.75609538, 0.01947901, 0.64000771, -0.10251877,
-1.07495041, 0.03227916, 0.44637876, -0.12401777, -0.8161197 ]),
0,
1.0,
array([ 0.04120674, 0.25315319, -0.14034017, -0.56487523])),
(array([-0.01503186, 0.04944601, -0.04457565, -0.07778433, -0.01404294,
-0.14500951, -0.04613134, 0.20050832, -0.01694313, 0.05074082,
-0.04212117, -0.10636261, -0.01592831, 0.24644028, -0.04424843,
-0.41203139, -0.0109995 , 0.44216065, -0.05248905, -0.71832937,
-0.00215629, 0.63796814, -0.06685564, -1.0270608 , 0.01060307,
0.4437968 , -0.08739686, -0.75609538, 0.01947901, 0.64000771,
-0.10251877, -1.07495041, 0.03227916, 0.44637876, -0.12401777,
-0.8161197 , 0.04120674, 0.25315319, -0.14034017, -0.56487523]),
1,
1.0,
array([ 0.0462698 , 0.44993622, -0.15163767, -0.89827247])),
(array([-0.01404294, -0.14500951, -0.04613134, 0.20050832, -0.01694313,
0.05074082, -0.04212117, -0.10636261, -0.01592831, 0.24644028,
-0.04424843, -0.41203139, -0.0109995 , 0.44216065, -0.05248905,
-0.71832937, -0.00215629, 0.63796814, -0.06685564, -1.0270608 ,
0.01060307, 0.4437968 , -0.08739686, -0.75609538, 0.01947901,
0.64000771, -0.10251877, -1.07495041, 0.03227916, 0.44637876,
-0.12401777, -0.8161197 , 0.04120674, 0.25315319, -0.14034017,
-0.56487523, 0.0462698 , 0.44993622, -0.15163767, -0.89827247]),
0,
1.0,
array([ 0.05526853, 0.25715875, -0.16960312, -0.65683525])),
(array([-0.01694313, 0.05074082, -0.04212117, -0.10636261, -0.01592831,
0.24644028, -0.04424843, -0.41203139, -0.0109995 , 0.44216065,
-0.05248905, -0.71832937, -0.00215629, 0.63796814, -0.06685564,
-1.0270608 , 0.01060307, 0.4437968 , -0.08739686, -0.75609538,
0.01947901, 0.64000771, -0.10251877, -1.07495041, 0.03227916,
0.44637876, -0.12401777, -0.8161197 , 0.04120674, 0.25315319,
-0.14034017, -0.56487523, 0.0462698 , 0.44993622, -0.15163767,
-0.89827247, 0.05526853, 0.25715875, -0.16960312, -0.65683525]),
1,
1.0,
array([ 0.0604117 , 0.4541849 , -0.18273983, -0.99775864])),
(array([-0.01592831, 0.24644028, -0.04424843, -0.41203139, -0.0109995 ,
0.44216065, -0.05248905, -0.71832937, -0.00215629, 0.63796814,
-0.06685564, -1.0270608 , 0.01060307, 0.4437968 , -0.08739686,
-0.75609538, 0.01947901, 0.64000771, -0.10251877, -1.07495041,
0.03227916, 0.44637876, -0.12401777, -0.8161197 , 0.04120674,
0.25315319, -0.14034017, -0.56487523, 0.0462698 , 0.44993622,
-0.15163767, -0.89827247, 0.05526853, 0.25715875, -0.16960312,
-0.65683525, 0.0604117 , 0.4541849 , -0.18273983, -0.99775864]),
0,
1.0,
array([ 0.0694954 , 0.26191385, -0.202695 , -0.76758117])),
(array([-0.0109995 , 0.44216065, -0.05248905, -0.71832937, -0.00215629,
0.63796814, -0.06685564, -1.0270608 , 0.01060307, 0.4437968 ,
-0.08739686, -0.75609538, 0.01947901, 0.64000771, -0.10251877,
-1.07495041, 0.03227916, 0.44637876, -0.12401777, -0.8161197 ,
0.04120674, 0.25315319, -0.14034017, -0.56487523, 0.0462698 ,
0.44993622, -0.15163767, -0.89827247, 0.05526853, 0.25715875,
-0.16960312, -0.65683525, 0.0604117 , 0.4541849 , -0.18273983,
-0.99775864, 0.0694954 , 0.26191385, -0.202695 , -0.76758117]),
1,
1.0,
array([ 0., 0., 0., 0.])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0.04085823, -0.14784811, -0.02989411, 0.23912504]),
1,
1.0,
array([ 0.03790127, 0.04768786, -0.02511161, -0.06283543])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0.04085823, -0.14784811, -0.02989411,
0.23912504, 0.03790127, 0.04768786, -0.02511161, -0.06283543]),
1,
1.0,
array([ 0.03885502, 0.24316068, -0.02636832, -0.36333426])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0.04085823, -0.14784811,
-0.02989411, 0.23912504, 0.03790127, 0.04768786, -0.02511161,
-0.06283543, 0.03885502, 0.24316068, -0.02636832, -0.36333426]),
0,
1.0,
array([ 0.04371824, 0.04842323, -0.033635 , -0.079081 ])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0.04085823,
-0.14784811, -0.02989411, 0.23912504, 0.03790127, 0.04768786,
-0.02511161, -0.06283543, 0.03885502, 0.24316068, -0.02636832,
-0.36333426, 0.04371824, 0.04842323, -0.033635 , -0.079081 ]),
1,
1.0,
array([ 0.0446867 , 0.2440108 , -0.03521662, -0.38218325])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0.04085823, -0.14784811, -0.02989411, 0.23912504, 0.03790127,
0.04768786, -0.02511161, -0.06283543, 0.03885502, 0.24316068,
-0.02636832, -0.36333426, 0.04371824, 0.04842323, -0.033635 ,
-0.079081 , 0.0446867 , 0.2440108 , -0.03521662, -0.38218325]),
1,
1.0,
array([ 0.04956692, 0.43961463, -0.04286029, -0.68575862])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0.04085823, -0.14784811, -0.02989411, 0.23912504,
0.03790127, 0.04768786, -0.02511161, -0.06283543, 0.03885502,
0.24316068, -0.02636832, -0.36333426, 0.04371824, 0.04842323,
-0.033635 , -0.079081 , 0.0446867 , 0.2440108 , -0.03521662,
-0.38218325, 0.04956692, 0.43961463, -0.04286029, -0.68575862]),
0,
1.0,
array([ 0.05835921, 0.24511308, -0.05657546, -0.40687129])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0.04085823, -0.14784811, -0.02989411,
0.23912504, 0.03790127, 0.04768786, -0.02511161, -0.06283543,
0.03885502, 0.24316068, -0.02636832, -0.36333426, 0.04371824,
0.04842323, -0.033635 , -0.079081 , 0.0446867 , 0.2440108 ,
-0.03521662, -0.38218325, 0.04956692, 0.43961463, -0.04286029,
-0.68575862, 0.05835921, 0.24511308, -0.05657546, -0.40687129]),
0,
1.0,
array([ 0.06326147, 0.05083709, -0.06471288, -0.13254787])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0.04085823, -0.14784811,
-0.02989411, 0.23912504, 0.03790127, 0.04768786, -0.02511161,
-0.06283543, 0.03885502, 0.24316068, -0.02636832, -0.36333426,
0.04371824, 0.04842323, -0.033635 , -0.079081 , 0.0446867 ,
0.2440108 , -0.03521662, -0.38218325, 0.04956692, 0.43961463,
-0.04286029, -0.68575862, 0.05835921, 0.24511308, -0.05657546,
-0.40687129, 0.06326147, 0.05083709, -0.06471288, -0.13254787]),
0,
1.0,
array([ 0.06427821, -0.14330108, -0.06736384, 0.13903753])),
(array([ 0. , 0. , 0. , 0. , 0.04085823,
-0.14784811, -0.02989411, 0.23912504, 0.03790127, 0.04768786,
-0.02511161, -0.06283543, 0.03885502, 0.24316068, -0.02636832,
-0.36333426, 0.04371824, 0.04842323, -0.033635 , -0.079081 ,
0.0446867 , 0.2440108 , -0.03521662, -0.38218325, 0.04956692,
0.43961463, -0.04286029, -0.68575862, 0.05835921, 0.24511308,
-0.05657546, -0.40687129, 0.06326147, 0.05083709, -0.06471288,
-0.13254787, 0.06427821, -0.14330108, -0.06736384, 0.13903753]),
0,
1.0,
array([ 0.06141219, -0.33739677, -0.06458309, 0.40973074])),
(array([ 0.04085823, -0.14784811, -0.02989411, 0.23912504, 0.03790127,
0.04768786, -0.02511161, -0.06283543, 0.03885502, 0.24316068,
-0.02636832, -0.36333426, 0.04371824, 0.04842323, -0.033635 ,
-0.079081 , 0.0446867 , 0.2440108 , -0.03521662, -0.38218325,
0.04956692, 0.43961463, -0.04286029, -0.68575862, 0.05835921,
0.24511308, -0.05657546, -0.40687129, 0.06326147, 0.05083709,
-0.06471288, -0.13254787, 0.06427821, -0.14330108, -0.06736384,
0.13903753, 0.06141219, -0.33739677, -0.06458309, 0.40973074]),
0,
1.0,
array([ 0.05466426, -0.53154648, -0.05638848, 0.68137393])),
(array([ 0.03790127, 0.04768786, -0.02511161, -0.06283543, 0.03885502,
0.24316068, -0.02636832, -0.36333426, 0.04371824, 0.04842323,
-0.033635 , -0.079081 , 0.0446867 , 0.2440108 , -0.03521662,
-0.38218325, 0.04956692, 0.43961463, -0.04286029, -0.68575862,
0.05835921, 0.24511308, -0.05657546, -0.40687129, 0.06326147,
0.05083709, -0.06471288, -0.13254787, 0.06427821, -0.14330108,
-0.06736384, 0.13903753, 0.06141219, -0.33739677, -0.06458309,
0.40973074, 0.05466426, -0.53154648, -0.05638848, 0.68137393]),
1,
1.0,
array([ 0.04403333, -0.3356886 , -0.042761 , 0.37148463])),
(array([ 0.03885502, 0.24316068, -0.02636832, -0.36333426, 0.04371824,
0.04842323, -0.033635 , -0.079081 , 0.0446867 , 0.2440108 ,
-0.03521662, -0.38218325, 0.04956692, 0.43961463, -0.04286029,
-0.68575862, 0.05835921, 0.24511308, -0.05657546, -0.40687129,
0.06326147, 0.05083709, -0.06471288, -0.13254787, 0.06427821,
-0.14330108, -0.06736384, 0.13903753, 0.06141219, -0.33739677,
-0.06458309, 0.40973074, 0.05466426, -0.53154648, -0.05638848,
0.68137393, 0.04403333, -0.3356886 , -0.042761 , 0.37148463]),
0,
1.0,
array([ 0.03731956, -0.53017779, -0.03533131, 0.65038384])),
(array([ 0.04371824, 0.04842323, -0.033635 , -0.079081 , 0.0446867 ,
0.2440108 , -0.03521662, -0.38218325, 0.04956692, 0.43961463,
-0.04286029, -0.68575862, 0.05835921, 0.24511308, -0.05657546,
-0.40687129, 0.06326147, 0.05083709, -0.06471288, -0.13254787,
0.06427821, -0.14330108, -0.06736384, 0.13903753, 0.06141219,
-0.33739677, -0.06458309, 0.40973074, 0.05466426, -0.53154648,
-0.05638848, 0.68137393, 0.04403333, -0.3356886 , -0.042761 ,
0.37148463, 0.03731956, -0.53017779, -0.03533131, 0.65038384]),
1,
1.0,
array([ 0.026716 , -0.33458199, -0.02232363, 0.346788 ])),
(array([ 0.0446867 , 0.2440108 , -0.03521662, -0.38218325, 0.04956692,
0.43961463, -0.04286029, -0.68575862, 0.05835921, 0.24511308,
-0.05657546, -0.40687129, 0.06326147, 0.05083709, -0.06471288,
-0.13254787, 0.06427821, -0.14330108, -0.06736384, 0.13903753,
0.06141219, -0.33739677, -0.06458309, 0.40973074, 0.05466426,
-0.53154648, -0.05638848, 0.68137393, 0.04403333, -0.3356886 ,
-0.042761 , 0.37148463, 0.03731956, -0.53017779, -0.03533131,
0.65038384, 0.026716 , -0.33458199, -0.02232363, 0.346788 ]),
1,
1.0,
array([ 0.02002436, -0.13914974, -0.01538787, 0.04715006])),
(array([ 0.04956692, 0.43961463, -0.04286029, -0.68575862, 0.05835921,
0.24511308, -0.05657546, -0.40687129, 0.06326147, 0.05083709,
-0.06471288, -0.13254787, 0.06427821, -0.14330108, -0.06736384,
0.13903753, 0.06141219, -0.33739677, -0.06458309, 0.40973074,
0.05466426, -0.53154648, -0.05638848, 0.68137393, 0.04403333,
-0.3356886 , -0.042761 , 0.37148463, 0.03731956, -0.53017779,
-0.03533131, 0.65038384, 0.026716 , -0.33458199, -0.02232363,
0.346788 , 0.02002436, -0.13914974, -0.01538787, 0.04715006]),
0,
1.0,
array([ 0.01724136, -0.3340477 , -0.01444487, 0.33493853])),
(array([ 0.05835921, 0.24511308, -0.05657546, -0.40687129, 0.06326147,
0.05083709, -0.06471288, -0.13254787, 0.06427821, -0.14330108,
-0.06736384, 0.13903753, 0.06141219, -0.33739677, -0.06458309,
0.40973074, 0.05466426, -0.53154648, -0.05638848, 0.68137393,
0.04403333, -0.3356886 , -0.042761 , 0.37148463, 0.03731956,
-0.53017779, -0.03533131, 0.65038384, 0.026716 , -0.33458199,
-0.02232363, 0.346788 , 0.02002436, -0.13914974, -0.01538787,
0.04715006, 0.01724136, -0.3340477 , -0.01444487, 0.33493853]),
1,
1.0,
array([ 0.01056041, -0.13872318, -0.0077461 , 0.03773567])),
(array([ 0.06326147, 0.05083709, -0.06471288, -0.13254787, 0.06427821,
-0.14330108, -0.06736384, 0.13903753, 0.06141219, -0.33739677,
-0.06458309, 0.40973074, 0.05466426, -0.53154648, -0.05638848,
0.68137393, 0.04403333, -0.3356886 , -0.042761 , 0.37148463,
0.03731956, -0.53017779, -0.03533131, 0.65038384, 0.026716 ,
-0.33458199, -0.02232363, 0.346788 , 0.02002436, -0.13914974,
-0.01538787, 0.04715006, 0.01724136, -0.3340477 , -0.01444487,
0.33493853, 0.01056041, -0.13872318, -0.0077461 , 0.03773567]),
1,
1.0,
array([ 0.00778595, 0.05650899, -0.00699138, -0.25738113])),
(array([ 0.06427821, -0.14330108, -0.06736384, 0.13903753, 0.06141219,
-0.33739677, -0.06458309, 0.40973074, 0.05466426, -0.53154648,
-0.05638848, 0.68137393, 0.04403333, -0.3356886 , -0.042761 ,
0.37148463, 0.03731956, -0.53017779, -0.03533131, 0.65038384,
0.026716 , -0.33458199, -0.02232363, 0.346788 , 0.02002436,
-0.13914974, -0.01538787, 0.04715006, 0.01724136, -0.3340477 ,
-0.01444487, 0.33493853, 0.01056041, -0.13872318, -0.0077461 ,
0.03773567, 0.00778595, 0.05650899, -0.00699138, -0.25738113]),
1,
1.0,
array([ 0.00891613, 0.25173006, -0.01213901, -0.55226102])),
(array([ 0.06141219, -0.33739677, -0.06458309, 0.40973074, 0.05466426,
-0.53154648, -0.05638848, 0.68137393, 0.04403333, -0.3356886 ,
-0.042761 , 0.37148463, 0.03731956, -0.53017779, -0.03533131,
0.65038384, 0.026716 , -0.33458199, -0.02232363, 0.346788 ,
0.02002436, -0.13914974, -0.01538787, 0.04715006, 0.01724136,
-0.3340477 , -0.01444487, 0.33493853, 0.01056041, -0.13872318,
-0.0077461 , 0.03773567, 0.00778595, 0.05650899, -0.00699138,
-0.25738113, 0.00891613, 0.25173006, -0.01213901, -0.55226102]),
1,
1.0,
array([ 0.01395073, 0.44702036, -0.02318423, -0.84874367])),
(array([ 0.05466426, -0.53154648, -0.05638848, 0.68137393, 0.04403333,
-0.3356886 , -0.042761 , 0.37148463, 0.03731956, -0.53017779,
-0.03533131, 0.65038384, 0.026716 , -0.33458199, -0.02232363,
0.346788 , 0.02002436, -0.13914974, -0.01538787, 0.04715006,
0.01724136, -0.3340477 , -0.01444487, 0.33493853, 0.01056041,
-0.13872318, -0.0077461 , 0.03773567, 0.00778595, 0.05650899,
-0.00699138, -0.25738113, 0.00891613, 0.25173006, -0.01213901,
-0.55226102, 0.01395073, 0.44702036, -0.02318423, -0.84874367]),
1,
1.0,
array([ 0.02289114, 0.64245072, -0.0401591 , -1.14862597])),
(array([ 0.04403333, -0.3356886 , -0.042761 , 0.37148463, 0.03731956,
-0.53017779, -0.03533131, 0.65038384, 0.026716 , -0.33458199,
-0.02232363, 0.346788 , 0.02002436, -0.13914974, -0.01538787,
0.04715006, 0.01724136, -0.3340477 , -0.01444487, 0.33493853,
0.01056041, -0.13872318, -0.0077461 , 0.03773567, 0.00778595,
0.05650899, -0.00699138, -0.25738113, 0.00891613, 0.25173006,
-0.01213901, -0.55226102, 0.01395073, 0.44702036, -0.02318423,
-0.84874367, 0.02289114, 0.64245072, -0.0401591 , -1.14862597]),
0,
1.0,
array([ 0.03574015, 0.44787536, -0.06313162, -0.86880186])),
(array([ 0.03731956, -0.53017779, -0.03533131, 0.65038384, 0.026716 ,
-0.33458199, -0.02232363, 0.346788 , 0.02002436, -0.13914974,
-0.01538787, 0.04715006, 0.01724136, -0.3340477 , -0.01444487,
0.33493853, 0.01056041, -0.13872318, -0.0077461 , 0.03773567,
0.00778595, 0.05650899, -0.00699138, -0.25738113, 0.00891613,
0.25173006, -0.01213901, -0.55226102, 0.01395073, 0.44702036,
-0.02318423, -0.84874367, 0.02289114, 0.64245072, -0.0401591 ,
-1.14862597, 0.03574015, 0.44787536, -0.06313162, -0.86880186]),
1,
1.0,
array([ 0.04469766, 0.64379678, -0.08050766, -1.18064691])),
(array([ 0.026716 , -0.33458199, -0.02232363, 0.346788 , 0.02002436,
-0.13914974, -0.01538787, 0.04715006, 0.01724136, -0.3340477 ,
-0.01444487, 0.33493853, 0.01056041, -0.13872318, -0.0077461 ,
0.03773567, 0.00778595, 0.05650899, -0.00699138, -0.25738113,
0.00891613, 0.25173006, -0.01213901, -0.55226102, 0.01395073,
0.44702036, -0.02318423, -0.84874367, 0.02289114, 0.64245072,
-0.0401591 , -1.14862597, 0.03574015, 0.44787536, -0.06313162,
-0.86880186, 0.04469766, 0.64379678, -0.08050766, -1.18064691]),
1,
1.0,
array([ 0.05757359, 0.8398662 , -0.10412059, -1.49744212])),
(array([ 0.02002436, -0.13914974, -0.01538787, 0.04715006, 0.01724136,
-0.3340477 , -0.01444487, 0.33493853, 0.01056041, -0.13872318,
-0.0077461 , 0.03773567, 0.00778595, 0.05650899, -0.00699138,
-0.25738113, 0.00891613, 0.25173006, -0.01213901, -0.55226102,
0.01395073, 0.44702036, -0.02318423, -0.84874367, 0.02289114,
0.64245072, -0.0401591 , -1.14862597, 0.03574015, 0.44787536,
-0.06313162, -0.86880186, 0.04469766, 0.64379678, -0.08050766,
-1.18064691, 0.05757359, 0.8398662 , -0.10412059, -1.49744212]),
0,
1.0,
array([ 0.07437092, 0.64615246, -0.13406944, -1.23900132])),
(array([ 0.01724136, -0.3340477 , -0.01444487, 0.33493853, 0.01056041,
-0.13872318, -0.0077461 , 0.03773567, 0.00778595, 0.05650899,
-0.00699138, -0.25738113, 0.00891613, 0.25173006, -0.01213901,
-0.55226102, 0.01395073, 0.44702036, -0.02318423, -0.84874367,
0.02289114, 0.64245072, -0.0401591 , -1.14862597, 0.03574015,
0.44787536, -0.06313162, -0.86880186, 0.04469766, 0.64379678,
-0.08050766, -1.18064691, 0.05757359, 0.8398662 , -0.10412059,
-1.49744212, 0.07437092, 0.64615246, -0.13406944, -1.23900132]),
1,
1.0,
array([ 0.08729397, 0.84271703, -0.15884946, -1.57050071])),
(array([ 0.01056041, -0.13872318, -0.0077461 , 0.03773567, 0.00778595,
0.05650899, -0.00699138, -0.25738113, 0.00891613, 0.25173006,
-0.01213901, -0.55226102, 0.01395073, 0.44702036, -0.02318423,
-0.84874367, 0.02289114, 0.64245072, -0.0401591 , -1.14862597,
0.03574015, 0.44787536, -0.06313162, -0.86880186, 0.04469766,
0.64379678, -0.08050766, -1.18064691, 0.05757359, 0.8398662 ,
-0.10412059, -1.49744212, 0.07437092, 0.64615246, -0.13406944,
-1.23900132, 0.08729397, 0.84271703, -0.15884946, -1.57050071]),
1,
1.0,
array([ 0.10414831, 1.03933837, -0.19025948, -1.90822508])),
(array([ 0.00778595, 0.05650899, -0.00699138, -0.25738113, 0.00891613,
0.25173006, -0.01213901, -0.55226102, 0.01395073, 0.44702036,
-0.02318423, -0.84874367, 0.02289114, 0.64245072, -0.0401591 ,
-1.14862597, 0.03574015, 0.44787536, -0.06313162, -0.86880186,
0.04469766, 0.64379678, -0.08050766, -1.18064691, 0.05757359,
0.8398662 , -0.10412059, -1.49744212, 0.07437092, 0.64615246,
-0.13406944, -1.23900132, 0.08729397, 0.84271703, -0.15884946,
-1.57050071, 0.10414831, 1.03933837, -0.19025948, -1.90822508]),
1,
1.0,
array([ 0., 0., 0., 0.])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , -0.01887329, -0.22918876, 0.00817488, 0.30130059]),
0,
1.0,
array([-0.02345706, -0.42442627, 0.01420089, 0.59655045])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , -0.01887329, -0.22918876, 0.00817488,
0.30130059, -0.02345706, -0.42442627, 0.01420089, 0.59655045]),
0,
1.0,
array([-0.03194559, -0.61974404, 0.0261319 , 0.89367249])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , -0.01887329, -0.22918876,
0.00817488, 0.30130059, -0.02345706, -0.42442627, 0.01420089,
0.59655045, -0.03194559, -0.61974404, 0.0261319 , 0.89367249]),
1,
1.0,
array([-0.04434047, -0.42498606, 0.04400535, 0.60931717])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , -0.01887329,
-0.22918876, 0.00817488, 0.30130059, -0.02345706, -0.42442627,
0.01420089, 0.59655045, -0.03194559, -0.61974404, 0.0261319 ,
0.89367249, -0.04434047, -0.42498606, 0.04400535, 0.60931717]),
1,
1.0,
array([-0.05284019, -0.230506 , 0.0561917 , 0.33081288])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
-0.01887329, -0.22918876, 0.00817488, 0.30130059, -0.02345706,
-0.42442627, 0.01420089, 0.59655045, -0.03194559, -0.61974404,
0.0261319 , 0.89367249, -0.04434047, -0.42498606, 0.04400535,
0.60931717, -0.05284019, -0.230506 , 0.0561917 , 0.33081288]),
0,
1.0,
array([-0.05745031, -0.42638093, 0.06280795, 0.6406732 ])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , -0.01887329, -0.22918876, 0.00817488, 0.30130059,
-0.02345706, -0.42442627, 0.01420089, 0.59655045, -0.03194559,
-0.61974404, 0.0261319 , 0.89367249, -0.04434047, -0.42498606,
0.04400535, 0.60931717, -0.05284019, -0.230506 , 0.0561917 ,
0.33081288, -0.05745031, -0.42638093, 0.06280795, 0.6406732 ]),
0,
1.0,
array([-0.06597793, -0.62231965, 0.07562142, 0.95245517])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , -0.01887329, -0.22918876, 0.00817488,
0.30130059, -0.02345706, -0.42442627, 0.01420089, 0.59655045,
-0.03194559, -0.61974404, 0.0261319 , 0.89367249, -0.04434047,
-0.42498606, 0.04400535, 0.60931717, -0.05284019, -0.230506 ,
0.0561917 , 0.33081288, -0.05745031, -0.42638093, 0.06280795,
0.6406732 , -0.06597793, -0.62231965, 0.07562142, 0.95245517]),
1,
1.0,
array([-0.07842432, -0.42829226, 0.09467052, 0.68445737])),
(array([ 0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , -0.01887329, -0.22918876,
0.00817488, 0.30130059, -0.02345706, -0.42442627, 0.01420089,
0.59655045, -0.03194559, -0.61974404, 0.0261319 , 0.89367249,
-0.04434047, -0.42498606, 0.04400535, 0.60931717, -0.05284019,
-0.230506 , 0.0561917 , 0.33081288, -0.05745031, -0.42638093,
0.06280795, 0.6406732 , -0.06597793, -0.62231965, 0.07562142,
0.95245517, -0.07842432, -0.42829226, 0.09467052, 0.68445737]),
1,
1.0,
array([-0.08699017, -0.23460336, 0.10835967, 0.42301658])),
(array([ 0. , 0. , 0. , 0. , -0.01887329,
-0.22918876, 0.00817488, 0.30130059, -0.02345706, -0.42442627,
0.01420089, 0.59655045, -0.03194559, -0.61974404, 0.0261319 ,
0.89367249, -0.04434047, -0.42498606, 0.04400535, 0.60931717,
-0.05284019, -0.230506 , 0.0561917 , 0.33081288, -0.05745031,
-0.42638093, 0.06280795, 0.6406732 , -0.06597793, -0.62231965,
0.07562142, 0.95245517, -0.07842432, -0.42829226, 0.09467052,
0.68445737, -0.08699017, -0.23460336, 0.10835967, 0.42301658]),
1,
1.0,
array([-0.09168223, -0.04116997, 0.11682 , 0.16636371])),
(array([-0.01887329, -0.22918876, 0.00817488, 0.30130059, -0.02345706,
-0.42442627, 0.01420089, 0.59655045, -0.03194559, -0.61974404,
0.0261319 , 0.89367249, -0.04434047, -0.42498606, 0.04400535,
0.60931717, -0.05284019, -0.230506 , 0.0561917 , 0.33081288,
-0.05745031, -0.42638093, 0.06280795, 0.6406732 , -0.06597793,
-0.62231965, 0.07562142, 0.95245517, -0.07842432, -0.42829226,
0.09467052, 0.68445737, -0.08699017, -0.23460336, 0.10835967,
0.42301658, -0.09168223, -0.04116997, 0.11682 , 0.16636371]),
1,
1.0,
array([-0.09250563, 0.15210284, 0.12014728, -0.08730256])),
(array([-0.02345706, -0.42442627, 0.01420089, 0.59655045, -0.03194559,
-0.61974404, 0.0261319 , 0.89367249, -0.04434047, -0.42498606,
0.04400535, 0.60931717, -0.05284019, -0.230506 , 0.0561917 ,
0.33081288, -0.05745031, -0.42638093, 0.06280795, 0.6406732 ,
-0.06597793, -0.62231965, 0.07562142, 0.95245517, -0.07842432,
-0.42829226, 0.09467052, 0.68445737, -0.08699017, -0.23460336,
0.10835967, 0.42301658, -0.09168223, -0.04116997, 0.11682 ,
0.16636371, -0.09250563, 0.15210284, 0.12014728, -0.08730256]),
1,
1.0,
array([-0.08946358, 0.34531603, 0.11840122, -0.33979466])),
(array([-0.03194559, -0.61974404, 0.0261319 , 0.89367249, -0.04434047,
-0.42498606, 0.04400535, 0.60931717, -0.05284019, -0.230506 ,
0.0561917 , 0.33081288, -0.05745031, -0.42638093, 0.06280795,
0.6406732 , -0.06597793, -0.62231965, 0.07562142, 0.95245517,
-0.07842432, -0.42829226, 0.09467052, 0.68445737, -0.08699017,
-0.23460336, 0.10835967, 0.42301658, -0.09168223, -0.04116997,
0.11682 , 0.16636371, -0.09250563, 0.15210284, 0.12014728,
-0.08730256, -0.08946358, 0.34531603, 0.11840122, -0.33979466]),
1,
1.0,
array([-0.08255726, 0.53857176, 0.11160533, -0.59292001])),
(array([-0.04434047, -0.42498606, 0.04400535, 0.60931717, -0.05284019,
-0.230506 , 0.0561917 , 0.33081288, -0.05745031, -0.42638093,
0.06280795, 0.6406732 , -0.06597793, -0.62231965, 0.07562142,
0.95245517, -0.07842432, -0.42829226, 0.09467052, 0.68445737,
-0.08699017, -0.23460336, 0.10835967, 0.42301658, -0.09168223,
-0.04116997, 0.11682 , 0.16636371, -0.09250563, 0.15210284,
0.12014728, -0.08730256, -0.08946358, 0.34531603, 0.11840122,
-0.33979466, -0.08255726, 0.53857176, 0.11160533, -0.59292001]),
0,
1.0,
array([-0.07178582, 0.34207902, 0.09974693, -0.26727071])),
(array([-0.05284019, -0.230506 , 0.0561917 , 0.33081288, -0.05745031,
-0.42638093, 0.06280795, 0.6406732 , -0.06597793, -0.62231965,
0.07562142, 0.95245517, -0.07842432, -0.42829226, 0.09467052,
0.68445737, -0.08699017, -0.23460336, 0.10835967, 0.42301658,
-0.09168223, -0.04116997, 0.11682 , 0.16636371, -0.09250563,
0.15210284, 0.12014728, -0.08730256, -0.08946358, 0.34531603,
0.11840122, -0.33979466, -0.08255726, 0.53857176, 0.11160533,
-0.59292001, -0.07178582, 0.34207902, 0.09974693, -0.26727071]),
0,
1.0,
array([-0.06494424, 0.14568546, 0.09440152, 0.05513233])),
(array([-0.05745031, -0.42638093, 0.06280795, 0.6406732 , -0.06597793,
-0.62231965, 0.07562142, 0.95245517, -0.07842432, -0.42829226,
0.09467052, 0.68445737, -0.08699017, -0.23460336, 0.10835967,
0.42301658, -0.09168223, -0.04116997, 0.11682 , 0.16636371,
-0.09250563, 0.15210284, 0.12014728, -0.08730256, -0.08946358,
0.34531603, 0.11840122, -0.33979466, -0.08255726, 0.53857176,
0.11160533, -0.59292001, -0.07178582, 0.34207902, 0.09974693,
-0.26727071, -0.06494424, 0.14568546, 0.09440152, 0.05513233]),
1,
1.0,
array([-0.06203053, 0.33933597, 0.09550416, -0.20633724])),
(array([-0.06597793, -0.62231965, 0.07562142, 0.95245517, -0.07842432,
-0.42829226, 0.09467052, 0.68445737, -0.08699017, -0.23460336,
0.10835967, 0.42301658, -0.09168223, -0.04116997, 0.11682 ,
0.16636371, -0.09250563, 0.15210284, 0.12014728, -0.08730256,
-0.08946358, 0.34531603, 0.11840122, -0.33979466, -0.08255726,
0.53857176, 0.11160533, -0.59292001, -0.07178582, 0.34207902,
0.09974693, -0.26727071, -0.06494424, 0.14568546, 0.09440152,
0.05513233, -0.06203053, 0.33933597, 0.09550416, -0.20633724]),
0,
1.0,
array([-0.05524381, 0.14298726, 0.09137742, 0.11487921]))])
In [32]:
%matplotlib inline
import matplotlib.pyplot as plt
def running_mean(x, N):
cumsum = np.cumsum(np.insert(x, 0, 0))
return (cumsum[N:] - cumsum[:-N]) / N
saver = tf.train.Saver()
In [ ]:
# Now train with experiences
rewards_list = []
with tf.Session() as sess:
# Initialize variables
sess.run(tf.global_variables_initializer())
step = 0
for ep in range(1, train_episodes):
total_reward = 0
t = 0
while t < max_steps:
step += 1
# Uncomment this next line to watch the training
# env.render()
# Explore or Exploit
explore_p = explore_stop + (explore_start - explore_stop)*np.exp(-decay_rate*step)
if explore_p > np.random.rand():
# Make a random action
action = env.action_space.sample()
else:
# Get action from Q-network
mystate = get_state(all_states, previous_steps)
feed = {mainQN.inputs_: mystate.reshape((1, *mystate.shape))}
Qs = sess.run(mainQN.output, feed_dict=feed)
action = np.argmax(Qs)
# Take action, get new state and reward
next_state, reward, done, _ = env.step(action)
total_reward += reward
if done:
# the episode ends so no next state
next_state = np.zeros(state.shape)
t = max_steps
print('Episode: {}'.format(ep),
'Total reward: {}'.format(total_reward),
'Training loss: {:.4f}'.format(loss),
'Explore P: {:.4f}'.format(explore_p))
rewards_list.append((ep, total_reward))
if ep % 100 == 0:
eps, rews = np.array(rewards_list).T
smoothed_rews = running_mean(rews, 10)
smoothed_rews2 = running_mean(rews, 20)
fig, axes = plt.subplots(1,1, figsize=(13,13))
axes.plot(eps[-len(smoothed_rews):], smoothed_rews)
axes.plot(eps[-len(smoothed_rews2):], smoothed_rews2)
axes.plot(eps, rews, color='grey', alpha=0.3)
axes.set_xlabel('Episode')
axes.set_ylabel('Total Reward')
plt.show()
# Add experience to memory
memory.add((get_state(all_states, previous_steps), action, reward, next_state))
# Start new episode
env.reset()
# Take one random step to get the pole and cart moving
state, reward, done, _ = env.step(env.action_space.sample())
all_states = [state]
else:
# Add experience to memory
memory.add((get_state(all_states, previous_steps), action, reward, next_state))
all_states.append(next_state)
t += 1
# Sample mini-batch from memory
num_batches_available = max(len(memory.buffer)//batch_size, 1)
num_training_batches = min(batches_per_step, num_batches_available)
for i in range(num_training_batches):
batch = memory.sample(batch_size)
states = np.array([each[0] for each in batch])
actions = np.array([each[1] for each in batch])
rewards = np.array([each[2] for each in batch])
next_states = np.array([each[3] for each in batch])
# Train network
target_Qs = sess.run(mainQN.output, feed_dict={mainQN.inputs_: states})
# Set target_Qs to 0 for states where episode ends
episode_ends = (next_states == np.zeros(next_states[0].shape)).all(axis=1)
target_Qs[episode_ends] = (0, 0)
targets = rewards + gamma * np.max(target_Qs, axis=1)
loss, _ = sess.run([mainQN.loss, mainQN.opt],
feed_dict={mainQN.inputs_: states,
mainQN.targetQs_: targets,
mainQN.actions_: actions})
saver.save(sess, "checkpoints/cartpole.ckpt")
Episode: 1 Total reward: 19.0 Training loss: 1.0756 Explore P: 0.9000
Episode: 2 Total reward: 22.0 Training loss: 1.0773 Explore P: 0.8999
Episode: 3 Total reward: 15.0 Training loss: 1.0624 Explore P: 0.8999
Episode: 4 Total reward: 9.0 Training loss: 1.0634 Explore P: 0.8999
Episode: 5 Total reward: 50.0 Training loss: 1.0692 Explore P: 0.8998
Episode: 6 Total reward: 46.0 Training loss: 1.0166 Explore P: 0.8997
Episode: 7 Total reward: 20.0 Training loss: 1.2025 Explore P: 0.8997
Episode: 8 Total reward: 45.0 Training loss: 1.7654 Explore P: 0.8996
Episode: 9 Total reward: 31.0 Training loss: 1.1243 Explore P: 0.8995
Episode: 10 Total reward: 8.0 Training loss: 1.3370 Explore P: 0.8995
Episode: 11 Total reward: 11.0 Training loss: 1.7546 Explore P: 0.8995
Episode: 12 Total reward: 17.0 Training loss: 1.6703 Explore P: 0.8995
Episode: 13 Total reward: 18.0 Training loss: 1.4960 Explore P: 0.8994
Episode: 14 Total reward: 10.0 Training loss: 1.5226 Explore P: 0.8994
Episode: 15 Total reward: 9.0 Training loss: 2.7580 Explore P: 0.8994
Episode: 16 Total reward: 17.0 Training loss: 2.7906 Explore P: 0.8994
Episode: 17 Total reward: 13.0 Training loss: 4.1562 Explore P: 0.8994
Episode: 18 Total reward: 40.0 Training loss: 2.8295 Explore P: 0.8993
Episode: 19 Total reward: 18.0 Training loss: 1.3450 Explore P: 0.8993
Episode: 20 Total reward: 75.0 Training loss: 6.0538 Explore P: 0.8991
Episode: 21 Total reward: 18.0 Training loss: 6.5073 Explore P: 0.8991
Episode: 22 Total reward: 10.0 Training loss: 1.1403 Explore P: 0.8991
Episode: 23 Total reward: 9.0 Training loss: 4.6586 Explore P: 0.8991
Episode: 24 Total reward: 26.0 Training loss: 2.0849 Explore P: 0.8990
Episode: 25 Total reward: 13.0 Training loss: 12.8755 Explore P: 0.8990
Episode: 26 Total reward: 17.0 Training loss: 1.4082 Explore P: 0.8990
Episode: 27 Total reward: 24.0 Training loss: 1.3508 Explore P: 0.8989
Episode: 28 Total reward: 34.0 Training loss: 10.2938 Explore P: 0.8989
Episode: 29 Total reward: 9.0 Training loss: 1.3750 Explore P: 0.8988
Episode: 30 Total reward: 43.0 Training loss: 4.5151 Explore P: 0.8988
Episode: 31 Total reward: 22.0 Training loss: 10.1672 Explore P: 0.8987
Episode: 32 Total reward: 14.0 Training loss: 2.1120 Explore P: 0.8987
Episode: 33 Total reward: 21.0 Training loss: 1.5378 Explore P: 0.8987
Episode: 34 Total reward: 35.0 Training loss: 2.1460 Explore P: 0.8986
Episode: 35 Total reward: 11.0 Training loss: 1.7509 Explore P: 0.8986
Episode: 36 Total reward: 13.0 Training loss: 1.4837 Explore P: 0.8986
Episode: 37 Total reward: 10.0 Training loss: 1.6359 Explore P: 0.8985
Episode: 38 Total reward: 25.0 Training loss: 11.6598 Explore P: 0.8985
Episode: 39 Total reward: 17.0 Training loss: 3.4774 Explore P: 0.8985
Episode: 40 Total reward: 11.0 Training loss: 19.3423 Explore P: 0.8984
Episode: 41 Total reward: 41.0 Training loss: 3.5039 Explore P: 0.8984
Episode: 42 Total reward: 8.0 Training loss: 23.5127 Explore P: 0.8984
Episode: 43 Total reward: 33.0 Training loss: 1.3274 Explore P: 0.8983
Episode: 44 Total reward: 20.0 Training loss: 16.9893 Explore P: 0.8983
Episode: 45 Total reward: 16.0 Training loss: 9.2844 Explore P: 0.8982
Episode: 46 Total reward: 10.0 Training loss: 11.0951 Explore P: 0.8982
Episode: 47 Total reward: 40.0 Training loss: 1.7341 Explore P: 0.8981
Episode: 48 Total reward: 19.0 Training loss: 16.5308 Explore P: 0.8981
Episode: 49 Total reward: 11.0 Training loss: 13.8048 Explore P: 0.8981
Episode: 50 Total reward: 13.0 Training loss: 38.9402 Explore P: 0.8981
Episode: 51 Total reward: 10.0 Training loss: 12.5303 Explore P: 0.8981
Episode: 52 Total reward: 15.0 Training loss: 7.3815 Explore P: 0.8980
Episode: 53 Total reward: 19.0 Training loss: 1.6220 Explore P: 0.8980
Episode: 54 Total reward: 30.0 Training loss: 17.2222 Explore P: 0.8979
Episode: 55 Total reward: 17.0 Training loss: 16.8474 Explore P: 0.8979
Episode: 56 Total reward: 10.0 Training loss: 31.9063 Explore P: 0.8979
Episode: 57 Total reward: 18.0 Training loss: 6.1431 Explore P: 0.8979
Episode: 58 Total reward: 15.0 Training loss: 12.6749 Explore P: 0.8978
Episode: 59 Total reward: 33.0 Training loss: 20.2360 Explore P: 0.8978
Episode: 60 Total reward: 23.0 Training loss: 30.1034 Explore P: 0.8977
Episode: 61 Total reward: 7.0 Training loss: 1.3911 Explore P: 0.8977
Episode: 62 Total reward: 29.0 Training loss: 5.5073 Explore P: 0.8977
Episode: 63 Total reward: 14.0 Training loss: 98.5832 Explore P: 0.8976
Episode: 64 Total reward: 14.0 Training loss: 64.8776 Explore P: 0.8976
Episode: 65 Total reward: 16.0 Training loss: 37.5220 Explore P: 0.8976
Episode: 66 Total reward: 21.0 Training loss: 91.4176 Explore P: 0.8976
Episode: 67 Total reward: 19.0 Training loss: 2.2973 Explore P: 0.8975
Episode: 68 Total reward: 23.0 Training loss: 37.4426 Explore P: 0.8975
Episode: 69 Total reward: 47.0 Training loss: 11.1340 Explore P: 0.8974
Episode: 70 Total reward: 17.0 Training loss: 2.6303 Explore P: 0.8974
Episode: 71 Total reward: 12.0 Training loss: 17.8281 Explore P: 0.8973
Episode: 72 Total reward: 13.0 Training loss: 31.6798 Explore P: 0.8973
Episode: 73 Total reward: 19.0 Training loss: 26.0199 Explore P: 0.8973
Episode: 74 Total reward: 53.0 Training loss: 33.7357 Explore P: 0.8972
Episode: 75 Total reward: 24.0 Training loss: 56.7551 Explore P: 0.8971
Episode: 76 Total reward: 53.0 Training loss: 5.5294 Explore P: 0.8971
Episode: 77 Total reward: 16.0 Training loss: 2.0611 Explore P: 0.8970
Episode: 78 Total reward: 36.0 Training loss: 3.4190 Explore P: 0.8970
Episode: 79 Total reward: 12.0 Training loss: 3.4789 Explore P: 0.8969
Episode: 80 Total reward: 11.0 Training loss: 2.2657 Explore P: 0.8969
Episode: 81 Total reward: 28.0 Training loss: 3.0912 Explore P: 0.8969
Episode: 82 Total reward: 55.0 Training loss: 65.4264 Explore P: 0.8968
Episode: 83 Total reward: 17.0 Training loss: 5.6256 Explore P: 0.8967
Episode: 84 Total reward: 10.0 Training loss: 2.3138 Explore P: 0.8967
Episode: 85 Total reward: 11.0 Training loss: 4.2621 Explore P: 0.8967
Episode: 86 Total reward: 32.0 Training loss: 1.9653 Explore P: 0.8967
Episode: 87 Total reward: 46.0 Training loss: 2.9482 Explore P: 0.8966
Episode: 88 Total reward: 12.0 Training loss: 35.1520 Explore P: 0.8965
Episode: 89 Total reward: 19.0 Training loss: 112.0224 Explore P: 0.8965
Episode: 90 Total reward: 12.0 Training loss: 3.6854 Explore P: 0.8965
Episode: 91 Total reward: 75.0 Training loss: 260.7110 Explore P: 0.8964
Episode: 92 Total reward: 13.0 Training loss: 14.6303 Explore P: 0.8963
Episode: 93 Total reward: 30.0 Training loss: 32.9123 Explore P: 0.8963
Episode: 94 Total reward: 57.0 Training loss: 23.2599 Explore P: 0.8962
Episode: 95 Total reward: 44.0 Training loss: 126.1553 Explore P: 0.8961
Episode: 96 Total reward: 23.0 Training loss: 29.6969 Explore P: 0.8961
Episode: 97 Total reward: 24.0 Training loss: 4.7177 Explore P: 0.8960
Episode: 98 Total reward: 48.0 Training loss: 3.3245 Explore P: 0.8959
Episode: 99 Total reward: 18.0 Training loss: 4.4743 Explore P: 0.8959
Episode: 100 Total reward: 10.0 Training loss: 74.2390 Explore P: 0.8959
Episode: 101 Total reward: 27.0 Training loss: 6.0122 Explore P: 0.8958
Episode: 102 Total reward: 9.0 Training loss: 334.4926 Explore P: 0.8958
Episode: 103 Total reward: 21.0 Training loss: 369.8010 Explore P: 0.8958
Episode: 104 Total reward: 49.0 Training loss: 246.0619 Explore P: 0.8957
Episode: 105 Total reward: 10.0 Training loss: 31.3543 Explore P: 0.8957
Episode: 106 Total reward: 10.0 Training loss: 123.2971 Explore P: 0.8957
Episode: 107 Total reward: 13.0 Training loss: 91.6034 Explore P: 0.8956
Episode: 108 Total reward: 20.0 Training loss: 32.3731 Explore P: 0.8956
Episode: 109 Total reward: 14.0 Training loss: 3.0777 Explore P: 0.8956
Episode: 110 Total reward: 15.0 Training loss: 115.2231 Explore P: 0.8956
Episode: 111 Total reward: 12.0 Training loss: 20.1594 Explore P: 0.8955
Episode: 112 Total reward: 13.0 Training loss: 75.2785 Explore P: 0.8955
Episode: 113 Total reward: 13.0 Training loss: 7.1727 Explore P: 0.8955
Episode: 114 Total reward: 51.0 Training loss: 52.0600 Explore P: 0.8954
Episode: 115 Total reward: 20.0 Training loss: 153.9050 Explore P: 0.8954
Episode: 116 Total reward: 12.0 Training loss: 105.9201 Explore P: 0.8953
Episode: 117 Total reward: 16.0 Training loss: 2.8293 Explore P: 0.8953
Episode: 118 Total reward: 36.0 Training loss: 3.2671 Explore P: 0.8952
Episode: 119 Total reward: 33.0 Training loss: 2.7800 Explore P: 0.8952
Episode: 120 Total reward: 16.0 Training loss: 34.8405 Explore P: 0.8952
Episode: 121 Total reward: 11.0 Training loss: 30.9788 Explore P: 0.8951
Episode: 122 Total reward: 42.0 Training loss: 103.8291 Explore P: 0.8951
Episode: 123 Total reward: 37.0 Training loss: 58.9573 Explore P: 0.8950
Episode: 124 Total reward: 49.0 Training loss: 41.8547 Explore P: 0.8949
Episode: 125 Total reward: 19.0 Training loss: 18.5323 Explore P: 0.8949
Episode: 126 Total reward: 26.0 Training loss: 61.0427 Explore P: 0.8948
Episode: 127 Total reward: 22.0 Training loss: 29.2004 Explore P: 0.8948
Episode: 128 Total reward: 25.0 Training loss: 17.4225 Explore P: 0.8948
Episode: 129 Total reward: 20.0 Training loss: 4.1081 Explore P: 0.8947
Episode: 130 Total reward: 11.0 Training loss: 11.6343 Explore P: 0.8947
Episode: 131 Total reward: 12.0 Training loss: 2.6282 Explore P: 0.8947
Episode: 132 Total reward: 39.0 Training loss: 68.9728 Explore P: 0.8946
Episode: 133 Total reward: 16.0 Training loss: 18.4531 Explore P: 0.8946
Episode: 134 Total reward: 17.0 Training loss: 4.2487 Explore P: 0.8945
Episode: 135 Total reward: 24.0 Training loss: 1.9065 Explore P: 0.8945
Episode: 136 Total reward: 24.0 Training loss: 223.2294 Explore P: 0.8945
Episode: 137 Total reward: 10.0 Training loss: 16.3388 Explore P: 0.8944
Episode: 138 Total reward: 30.0 Training loss: 49.6885 Explore P: 0.8944
Episode: 139 Total reward: 10.0 Training loss: 2.3654 Explore P: 0.8944
Episode: 140 Total reward: 34.0 Training loss: 7.7723 Explore P: 0.8943
Episode: 141 Total reward: 26.0 Training loss: 13.0212 Explore P: 0.8943
Episode: 142 Total reward: 22.0 Training loss: 29.2322 Explore P: 0.8942
Episode: 143 Total reward: 16.0 Training loss: 6.7076 Explore P: 0.8942
Episode: 144 Total reward: 23.0 Training loss: 7.2684 Explore P: 0.8942
Episode: 145 Total reward: 12.0 Training loss: 64.1339 Explore P: 0.8941
Episode: 146 Total reward: 38.0 Training loss: 10.4543 Explore P: 0.8941
Episode: 147 Total reward: 30.0 Training loss: 20.9739 Explore P: 0.8940
Episode: 148 Total reward: 17.0 Training loss: 100.4025 Explore P: 0.8940
Episode: 149 Total reward: 11.0 Training loss: 33.9364 Explore P: 0.8940
Episode: 150 Total reward: 24.0 Training loss: 1.8198 Explore P: 0.8939
Episode: 151 Total reward: 14.0 Training loss: 2.2650 Explore P: 0.8939
Episode: 152 Total reward: 66.0 Training loss: 66.1082 Explore P: 0.8938
Episode: 153 Total reward: 9.0 Training loss: 44.4945 Explore P: 0.8938
Episode: 154 Total reward: 14.0 Training loss: 64.3925 Explore P: 0.8937
Episode: 155 Total reward: 16.0 Training loss: 1.8536 Explore P: 0.8937
Episode: 156 Total reward: 10.0 Training loss: 1.5884 Explore P: 0.8937
Episode: 157 Total reward: 30.0 Training loss: 15.0648 Explore P: 0.8936
Episode: 158 Total reward: 31.0 Training loss: 9.1736 Explore P: 0.8936
Episode: 159 Total reward: 22.0 Training loss: 93.8976 Explore P: 0.8936
Episode: 160 Total reward: 27.0 Training loss: 1.7169 Explore P: 0.8935
Episode: 161 Total reward: 12.0 Training loss: 1.4579 Explore P: 0.8935
Episode: 162 Total reward: 20.0 Training loss: 113.5390 Explore P: 0.8934
Episode: 163 Total reward: 13.0 Training loss: 4.5285 Explore P: 0.8934
Episode: 164 Total reward: 16.0 Training loss: 69.1436 Explore P: 0.8934
Episode: 165 Total reward: 33.0 Training loss: 10.8600 Explore P: 0.8933
Episode: 166 Total reward: 12.0 Training loss: 18.1755 Explore P: 0.8933
Episode: 167 Total reward: 7.0 Training loss: 2.0019 Explore P: 0.8933
Episode: 168 Total reward: 20.0 Training loss: 1.3080 Explore P: 0.8933
Episode: 169 Total reward: 18.0 Training loss: 1.5355 Explore P: 0.8932
Episode: 170 Total reward: 11.0 Training loss: 44.1698 Explore P: 0.8932
Episode: 171 Total reward: 15.0 Training loss: 347.8667 Explore P: 0.8932
Episode: 172 Total reward: 8.0 Training loss: 18.7084 Explore P: 0.8932
Episode: 173 Total reward: 25.0 Training loss: 1.4459 Explore P: 0.8931
Episode: 174 Total reward: 32.0 Training loss: 6.9366 Explore P: 0.8931
Episode: 175 Total reward: 10.0 Training loss: 6.1790 Explore P: 0.8931
Episode: 176 Total reward: 30.0 Training loss: 6.5466 Explore P: 0.8930
Episode: 177 Total reward: 35.0 Training loss: 22.5247 Explore P: 0.8929
Episode: 178 Total reward: 17.0 Training loss: 8.2320 Explore P: 0.8929
Episode: 179 Total reward: 28.0 Training loss: 30.6504 Explore P: 0.8929
Episode: 180 Total reward: 12.0 Training loss: 1.6479 Explore P: 0.8928
Episode: 181 Total reward: 14.0 Training loss: 6.2710 Explore P: 0.8928
Episode: 182 Total reward: 19.0 Training loss: 1.4089 Explore P: 0.8928
Episode: 183 Total reward: 10.0 Training loss: 1.5333 Explore P: 0.8928
Episode: 184 Total reward: 11.0 Training loss: 1.5760 Explore P: 0.8927
Episode: 185 Total reward: 14.0 Training loss: 388.7765 Explore P: 0.8927
Episode: 186 Total reward: 11.0 Training loss: 15.7610 Explore P: 0.8927
Episode: 187 Total reward: 10.0 Training loss: 76.5291 Explore P: 0.8927
Episode: 188 Total reward: 14.0 Training loss: 114.3525 Explore P: 0.8927
Episode: 189 Total reward: 18.0 Training loss: 94.4720 Explore P: 0.8926
Episode: 190 Total reward: 14.0 Training loss: 119.1218 Explore P: 0.8926
Episode: 191 Total reward: 35.0 Training loss: 4.7949 Explore P: 0.8925
Episode: 192 Total reward: 11.0 Training loss: 193.2796 Explore P: 0.8925
Episode: 193 Total reward: 14.0 Training loss: 2.1572 Explore P: 0.8925
Episode: 194 Total reward: 15.0 Training loss: 8.9596 Explore P: 0.8925
Episode: 195 Total reward: 13.0 Training loss: 1.6370 Explore P: 0.8925
Episode: 196 Total reward: 27.0 Training loss: 13.5442 Explore P: 0.8924
Episode: 197 Total reward: 26.0 Training loss: 11.0637 Explore P: 0.8924
Episode: 198 Total reward: 21.0 Training loss: 8.5068 Explore P: 0.8923
Episode: 199 Total reward: 26.0 Training loss: 1.3453 Explore P: 0.8923
Episode: 200 Total reward: 22.0 Training loss: 1.3528 Explore P: 0.8922
Episode: 201 Total reward: 24.0 Training loss: 16.4743 Explore P: 0.8922
Episode: 202 Total reward: 28.0 Training loss: 2.4176 Explore P: 0.8921
Episode: 203 Total reward: 11.0 Training loss: 1.5720 Explore P: 0.8921
Episode: 204 Total reward: 9.0 Training loss: 81.9544 Explore P: 0.8921
Episode: 205 Total reward: 16.0 Training loss: 188.8078 Explore P: 0.8921
Episode: 206 Total reward: 43.0 Training loss: 82.9268 Explore P: 0.8920
Episode: 207 Total reward: 10.0 Training loss: 16.7030 Explore P: 0.8920
Episode: 208 Total reward: 19.0 Training loss: 216.2025 Explore P: 0.8920
Episode: 209 Total reward: 15.0 Training loss: 35.0983 Explore P: 0.8919
Episode: 210 Total reward: 19.0 Training loss: 1.6764 Explore P: 0.8919
Episode: 211 Total reward: 22.0 Training loss: 3.3312 Explore P: 0.8919
Episode: 212 Total reward: 16.0 Training loss: 32.5085 Explore P: 0.8918
Episode: 213 Total reward: 42.0 Training loss: 1.4383 Explore P: 0.8918
Episode: 214 Total reward: 16.0 Training loss: 123.3836 Explore P: 0.8917
Episode: 215 Total reward: 13.0 Training loss: 78.9887 Explore P: 0.8917
Episode: 216 Total reward: 12.0 Training loss: 64.0919 Explore P: 0.8917
Episode: 217 Total reward: 12.0 Training loss: 2.4499 Explore P: 0.8917
Episode: 218 Total reward: 20.0 Training loss: 85.7267 Explore P: 0.8916
Episode: 219 Total reward: 16.0 Training loss: 1.7061 Explore P: 0.8916
Episode: 220 Total reward: 14.0 Training loss: 19.5751 Explore P: 0.8916
Episode: 221 Total reward: 19.0 Training loss: 56.8594 Explore P: 0.8915
Episode: 222 Total reward: 14.0 Training loss: 27.2567 Explore P: 0.8915
Episode: 223 Total reward: 10.0 Training loss: 13.3189 Explore P: 0.8915
Episode: 224 Total reward: 25.0 Training loss: 25.1525 Explore P: 0.8915
Episode: 225 Total reward: 9.0 Training loss: 14.3440 Explore P: 0.8914
Episode: 226 Total reward: 14.0 Training loss: 2.0311 Explore P: 0.8914
Episode: 227 Total reward: 33.0 Training loss: 25.5130 Explore P: 0.8914
Episode: 228 Total reward: 21.0 Training loss: 302.9150 Explore P: 0.8913
Episode: 229 Total reward: 16.0 Training loss: 2.0273 Explore P: 0.8913
Episode: 230 Total reward: 20.0 Training loss: 184.4123 Explore P: 0.8913
Episode: 231 Total reward: 18.0 Training loss: 2.3417 Explore P: 0.8912
Episode: 232 Total reward: 25.0 Training loss: 2.1640 Explore P: 0.8912
Episode: 233 Total reward: 19.0 Training loss: 60.9048 Explore P: 0.8911
Episode: 234 Total reward: 21.0 Training loss: 1.5934 Explore P: 0.8911
Episode: 235 Total reward: 15.0 Training loss: 1.2309 Explore P: 0.8911
Episode: 236 Total reward: 36.0 Training loss: 4.4995 Explore P: 0.8910
Episode: 237 Total reward: 13.0 Training loss: 48.8871 Explore P: 0.8910
Episode: 238 Total reward: 12.0 Training loss: 1.3261 Explore P: 0.8910
Episode: 239 Total reward: 49.0 Training loss: 2.5646 Explore P: 0.8909
Episode: 240 Total reward: 14.0 Training loss: 84.4066 Explore P: 0.8909
Episode: 241 Total reward: 14.0 Training loss: 12.5401 Explore P: 0.8908
Episode: 242 Total reward: 16.0 Training loss: 72.0868 Explore P: 0.8908
Episode: 243 Total reward: 42.0 Training loss: 110.8959 Explore P: 0.8907
Episode: 244 Total reward: 16.0 Training loss: 30.7302 Explore P: 0.8907
Episode: 245 Total reward: 23.0 Training loss: 19.9573 Explore P: 0.8907
Episode: 246 Total reward: 16.0 Training loss: 36.1510 Explore P: 0.8906
Episode: 247 Total reward: 47.0 Training loss: 1.3628 Explore P: 0.8906
Episode: 248 Total reward: 26.0 Training loss: 27.4820 Explore P: 0.8905
Episode: 249 Total reward: 23.0 Training loss: 1.8580 Explore P: 0.8905
Episode: 250 Total reward: 13.0 Training loss: 88.3976 Explore P: 0.8904
Episode: 251 Total reward: 17.0 Training loss: 112.4124 Explore P: 0.8904
Episode: 252 Total reward: 22.0 Training loss: 2.7102 Explore P: 0.8904
Episode: 253 Total reward: 24.0 Training loss: 1.4274 Explore P: 0.8903
Episode: 254 Total reward: 12.0 Training loss: 1.4233 Explore P: 0.8903
Episode: 255 Total reward: 19.0 Training loss: 12.5923 Explore P: 0.8903
Episode: 256 Total reward: 19.0 Training loss: 15.5157 Explore P: 0.8902
Episode: 257 Total reward: 16.0 Training loss: 1.4736 Explore P: 0.8902
Episode: 258 Total reward: 26.0 Training loss: 31.3994 Explore P: 0.8902
Episode: 259 Total reward: 32.0 Training loss: 1.4476 Explore P: 0.8901
Episode: 260 Total reward: 37.0 Training loss: 533.6873 Explore P: 0.8901
Episode: 261 Total reward: 20.0 Training loss: 57.5894 Explore P: 0.8900
Episode: 262 Total reward: 12.0 Training loss: 1.9519 Explore P: 0.8900
Episode: 263 Total reward: 13.0 Training loss: 22.3167 Explore P: 0.8900
Episode: 264 Total reward: 19.0 Training loss: 1.6297 Explore P: 0.8899
Episode: 265 Total reward: 29.0 Training loss: 428.9546 Explore P: 0.8899
Episode: 266 Total reward: 10.0 Training loss: 14.3784 Explore P: 0.8899
Episode: 267 Total reward: 28.0 Training loss: 2.9893 Explore P: 0.8898
Episode: 268 Total reward: 34.0 Training loss: 1.8343 Explore P: 0.8898
Episode: 269 Total reward: 17.0 Training loss: 37.6391 Explore P: 0.8897
Episode: 270 Total reward: 23.0 Training loss: 1104.9342 Explore P: 0.8897
Episode: 271 Total reward: 15.0 Training loss: 58.5033 Explore P: 0.8897
Episode: 272 Total reward: 31.0 Training loss: 2.0444 Explore P: 0.8896
Episode: 273 Total reward: 12.0 Training loss: 15.1069 Explore P: 0.8896
Episode: 274 Total reward: 20.0 Training loss: 24.8892 Explore P: 0.8896
Episode: 275 Total reward: 21.0 Training loss: 37.4975 Explore P: 0.8895
Episode: 276 Total reward: 21.0 Training loss: 962.0959 Explore P: 0.8895
Episode: 277 Total reward: 10.0 Training loss: 1.6545 Explore P: 0.8895
Episode: 278 Total reward: 33.0 Training loss: 1.7831 Explore P: 0.8894
Episode: 279 Total reward: 9.0 Training loss: 2.2023 Explore P: 0.8894
Episode: 280 Total reward: 11.0 Training loss: 14.8674 Explore P: 0.8894
Episode: 281 Total reward: 13.0 Training loss: 45.6634 Explore P: 0.8893
Episode: 282 Total reward: 17.0 Training loss: 36.5797 Explore P: 0.8893
Episode: 283 Total reward: 32.0 Training loss: 68.0384 Explore P: 0.8893
Episode: 284 Total reward: 15.0 Training loss: 183.2155 Explore P: 0.8892
Episode: 285 Total reward: 14.0 Training loss: 21.8957 Explore P: 0.8892
Episode: 286 Total reward: 22.0 Training loss: 2.1031 Explore P: 0.8892
Episode: 287 Total reward: 20.0 Training loss: 2.6047 Explore P: 0.8891
Episode: 288 Total reward: 9.0 Training loss: 2.4028 Explore P: 0.8891
Episode: 289 Total reward: 16.0 Training loss: 850.3188 Explore P: 0.8891
Episode: 290 Total reward: 13.0 Training loss: 9.7876 Explore P: 0.8891
Episode: 291 Total reward: 30.0 Training loss: 4.1601 Explore P: 0.8890
Episode: 292 Total reward: 44.0 Training loss: 1.7833 Explore P: 0.8889
Episode: 293 Total reward: 15.0 Training loss: 21.3015 Explore P: 0.8889
Episode: 294 Total reward: 11.0 Training loss: 759.2157 Explore P: 0.8889
Episode: 295 Total reward: 10.0 Training loss: 263.3365 Explore P: 0.8889
Episode: 296 Total reward: 18.0 Training loss: 5.0488 Explore P: 0.8888
Episode: 297 Total reward: 13.0 Training loss: 1.9313 Explore P: 0.8888
Episode: 298 Total reward: 14.0 Training loss: 2.0189 Explore P: 0.8888
Episode: 299 Total reward: 24.0 Training loss: 44.2375 Explore P: 0.8888
Episode: 300 Total reward: 14.0 Training loss: 28.6188 Explore P: 0.8887
Episode: 301 Total reward: 12.0 Training loss: 510.0798 Explore P: 0.8887
Episode: 302 Total reward: 15.0 Training loss: 78.2703 Explore P: 0.8887
Episode: 303 Total reward: 17.0 Training loss: 19.0181 Explore P: 0.8887
Episode: 304 Total reward: 16.0 Training loss: 9.0121 Explore P: 0.8886
Episode: 305 Total reward: 25.0 Training loss: 31.3442 Explore P: 0.8886
Episode: 306 Total reward: 16.0 Training loss: 8.1156 Explore P: 0.8886
Episode: 307 Total reward: 15.0 Training loss: 2.3433 Explore P: 0.8885
Episode: 308 Total reward: 12.0 Training loss: 7.4143 Explore P: 0.8885
Episode: 309 Total reward: 15.0 Training loss: 13.4974 Explore P: 0.8885
Episode: 310 Total reward: 25.0 Training loss: 93.0099 Explore P: 0.8884
Episode: 311 Total reward: 15.0 Training loss: 54.4772 Explore P: 0.8884
Episode: 312 Total reward: 19.0 Training loss: 1.5610 Explore P: 0.8884
Episode: 313 Total reward: 8.0 Training loss: 86.8721 Explore P: 0.8884
Episode: 314 Total reward: 11.0 Training loss: 1.9673 Explore P: 0.8883
Episode: 315 Total reward: 25.0 Training loss: 5.3538 Explore P: 0.8883
Episode: 316 Total reward: 22.0 Training loss: 5.6032 Explore P: 0.8883
Episode: 317 Total reward: 16.0 Training loss: 63.4190 Explore P: 0.8882
Episode: 318 Total reward: 13.0 Training loss: 9.1606 Explore P: 0.8882
Episode: 319 Total reward: 14.0 Training loss: 60.3470 Explore P: 0.8882
Episode: 320 Total reward: 26.0 Training loss: 52.3186 Explore P: 0.8881
Episode: 321 Total reward: 10.0 Training loss: 1.6431 Explore P: 0.8881
Episode: 322 Total reward: 11.0 Training loss: 86.8870 Explore P: 0.8881
Episode: 323 Total reward: 10.0 Training loss: 6.0760 Explore P: 0.8881
Episode: 324 Total reward: 24.0 Training loss: 3.7083 Explore P: 0.8880
Episode: 325 Total reward: 11.0 Training loss: 34.2384 Explore P: 0.8880
Episode: 326 Total reward: 24.0 Training loss: 48.1834 Explore P: 0.8880
Episode: 327 Total reward: 17.0 Training loss: 14.5159 Explore P: 0.8879
Episode: 328 Total reward: 10.0 Training loss: 1.5029 Explore P: 0.8879
Episode: 329 Total reward: 15.0 Training loss: 88.4348 Explore P: 0.8879
Episode: 330 Total reward: 26.0 Training loss: 14.4191 Explore P: 0.8879
Episode: 331 Total reward: 36.0 Training loss: 319.9210 Explore P: 0.8878
Episode: 332 Total reward: 14.0 Training loss: 1.7147 Explore P: 0.8878
Episode: 333 Total reward: 14.0 Training loss: 2.9081 Explore P: 0.8877
Episode: 334 Total reward: 19.0 Training loss: 8.4017 Explore P: 0.8877
Episode: 335 Total reward: 16.0 Training loss: 6.2291 Explore P: 0.8877
Episode: 336 Total reward: 14.0 Training loss: 33.9803 Explore P: 0.8877
Episode: 337 Total reward: 19.0 Training loss: 44.6496 Explore P: 0.8876
Episode: 338 Total reward: 9.0 Training loss: 1.4337 Explore P: 0.8876
Episode: 339 Total reward: 15.0 Training loss: 49.8917 Explore P: 0.8876
Episode: 340 Total reward: 19.0 Training loss: 7.7265 Explore P: 0.8876
Episode: 341 Total reward: 12.0 Training loss: 1.5524 Explore P: 0.8875
Episode: 342 Total reward: 19.0 Training loss: 10.0690 Explore P: 0.8875
Episode: 343 Total reward: 22.0 Training loss: 1.6326 Explore P: 0.8875
Episode: 344 Total reward: 11.0 Training loss: 760.6754 Explore P: 0.8874
Episode: 345 Total reward: 31.0 Training loss: 31.4171 Explore P: 0.8874
Episode: 346 Total reward: 12.0 Training loss: 51.2771 Explore P: 0.8874
Episode: 347 Total reward: 13.0 Training loss: 414.4961 Explore P: 0.8873
Episode: 348 Total reward: 21.0 Training loss: 207.3437 Explore P: 0.8873
Episode: 349 Total reward: 26.0 Training loss: 6.2334 Explore P: 0.8873
Episode: 350 Total reward: 29.0 Training loss: 97.4668 Explore P: 0.8872
Episode: 351 Total reward: 16.0 Training loss: 2.5525 Explore P: 0.8872
Episode: 352 Total reward: 18.0 Training loss: 34.8214 Explore P: 0.8871
Episode: 353 Total reward: 15.0 Training loss: 27.1056 Explore P: 0.8871
Episode: 354 Total reward: 14.0 Training loss: 15.2556 Explore P: 0.8871
Episode: 355 Total reward: 11.0 Training loss: 741.8397 Explore P: 0.8871
Episode: 356 Total reward: 19.0 Training loss: 1127.2250 Explore P: 0.8870
Episode: 357 Total reward: 10.0 Training loss: 1.0237 Explore P: 0.8870
Episode: 358 Total reward: 17.0 Training loss: 5.4861 Explore P: 0.8870
Episode: 359 Total reward: 12.0 Training loss: 133.4911 Explore P: 0.8870
Episode: 360 Total reward: 11.0 Training loss: 10.4477 Explore P: 0.8870
Episode: 361 Total reward: 23.0 Training loss: 27.5752 Explore P: 0.8869
Episode: 362 Total reward: 10.0 Training loss: 12.2573 Explore P: 0.8869
Episode: 363 Total reward: 11.0 Training loss: 10.8894 Explore P: 0.8869
Episode: 364 Total reward: 12.0 Training loss: 28.6991 Explore P: 0.8869
Episode: 365 Total reward: 58.0 Training loss: 50.2274 Explore P: 0.8868
Episode: 366 Total reward: 13.0 Training loss: 1.5223 Explore P: 0.8867
Episode: 367 Total reward: 21.0 Training loss: 166.8322 Explore P: 0.8867
Episode: 368 Total reward: 11.0 Training loss: 40.7095 Explore P: 0.8867
Episode: 369 Total reward: 22.0 Training loss: 1.2679 Explore P: 0.8866
Episode: 370 Total reward: 25.0 Training loss: 1.5727 Explore P: 0.8866
Episode: 371 Total reward: 15.0 Training loss: 1144.8163 Explore P: 0.8866
Episode: 372 Total reward: 37.0 Training loss: 2.2524 Explore P: 0.8865
Episode: 373 Total reward: 21.0 Training loss: 48.2446 Explore P: 0.8865
Episode: 374 Total reward: 9.0 Training loss: 23.4074 Explore P: 0.8865
Episode: 375 Total reward: 12.0 Training loss: 46.7874 Explore P: 0.8864
Episode: 376 Total reward: 18.0 Training loss: 1.9957 Explore P: 0.8864
Episode: 377 Total reward: 82.0 Training loss: 168.6870 Explore P: 0.8863
Episode: 378 Total reward: 11.0 Training loss: 51.0216 Explore P: 0.8862
Episode: 379 Total reward: 22.0 Training loss: 10.9577 Explore P: 0.8862
Episode: 380 Total reward: 14.0 Training loss: 122.9735 Explore P: 0.8862
Episode: 381 Total reward: 12.0 Training loss: 12.7662 Explore P: 0.8862
Episode: 382 Total reward: 13.0 Training loss: 1.6433 Explore P: 0.8861
Episode: 383 Total reward: 20.0 Training loss: 1.6354 Explore P: 0.8861
Episode: 384 Total reward: 38.0 Training loss: 24.3142 Explore P: 0.8860
Episode: 385 Total reward: 20.0 Training loss: 19.6577 Explore P: 0.8860
Episode: 386 Total reward: 19.0 Training loss: 59.8893 Explore P: 0.8860
Episode: 387 Total reward: 13.0 Training loss: 160.6543 Explore P: 0.8859
Episode: 388 Total reward: 80.0 Training loss: 31.3421 Explore P: 0.8858
Episode: 389 Total reward: 28.0 Training loss: 1.5876 Explore P: 0.8857
Episode: 390 Total reward: 30.0 Training loss: 1.9309 Explore P: 0.8857
Episode: 391 Total reward: 13.0 Training loss: 45.9104 Explore P: 0.8857
Episode: 392 Total reward: 19.0 Training loss: 7.7920 Explore P: 0.8856
Episode: 393 Total reward: 33.0 Training loss: 77.7895 Explore P: 0.8856
Episode: 394 Total reward: 10.0 Training loss: 1.9112 Explore P: 0.8856
Episode: 395 Total reward: 13.0 Training loss: 21.5212 Explore P: 0.8855
Episode: 396 Total reward: 19.0 Training loss: 23.2420 Explore P: 0.8855
Episode: 397 Total reward: 20.0 Training loss: 23.1283 Explore P: 0.8855
Episode: 398 Total reward: 12.0 Training loss: 3.0060 Explore P: 0.8855
Episode: 399 Total reward: 15.0 Training loss: 242.5315 Explore P: 0.8854
Episode: 400 Total reward: 15.0 Training loss: 1335.5277 Explore P: 0.8854
Episode: 401 Total reward: 25.0 Training loss: 116.7050 Explore P: 0.8854
Episode: 402 Total reward: 21.0 Training loss: 161.9798 Explore P: 0.8853
Episode: 403 Total reward: 40.0 Training loss: 125.3268 Explore P: 0.8852
Episode: 404 Total reward: 27.0 Training loss: 1586.6104 Explore P: 0.8852
Episode: 405 Total reward: 18.0 Training loss: 1.9508 Explore P: 0.8852
Episode: 406 Total reward: 12.0 Training loss: 243.3567 Explore P: 0.8851
Episode: 407 Total reward: 19.0 Training loss: 1374.3304 Explore P: 0.8851
Episode: 408 Total reward: 13.0 Training loss: 9.2436 Explore P: 0.8851
Episode: 409 Total reward: 27.0 Training loss: 10.8658 Explore P: 0.8850
Episode: 410 Total reward: 15.0 Training loss: 20.9166 Explore P: 0.8850
Episode: 411 Total reward: 53.0 Training loss: 1.2789 Explore P: 0.8849
Episode: 412 Total reward: 22.0 Training loss: 12.5719 Explore P: 0.8849
Episode: 413 Total reward: 9.0 Training loss: 54.7641 Explore P: 0.8849
Episode: 414 Total reward: 21.0 Training loss: 1.5972 Explore P: 0.8848
Episode: 415 Total reward: 41.0 Training loss: 2.2430 Explore P: 0.8848
Episode: 416 Total reward: 15.0 Training loss: 10.5423 Explore P: 0.8847
Episode: 417 Total reward: 11.0 Training loss: 49.9627 Explore P: 0.8847
Episode: 418 Total reward: 12.0 Training loss: 2.1007 Explore P: 0.8847
Episode: 419 Total reward: 14.0 Training loss: 1.9234 Explore P: 0.8847
Episode: 420 Total reward: 15.0 Training loss: 226.9575 Explore P: 0.8846
Episode: 421 Total reward: 16.0 Training loss: 5.4914 Explore P: 0.8846
Episode: 422 Total reward: 10.0 Training loss: 103.7666 Explore P: 0.8846
Episode: 423 Total reward: 21.0 Training loss: 53.6039 Explore P: 0.8846
Episode: 424 Total reward: 28.0 Training loss: 62.1070 Explore P: 0.8845
Episode: 425 Total reward: 17.0 Training loss: 1.9188 Explore P: 0.8845
Episode: 426 Total reward: 15.0 Training loss: 2.4375 Explore P: 0.8845
Episode: 427 Total reward: 11.0 Training loss: 1.6061 Explore P: 0.8844
Episode: 428 Total reward: 18.0 Training loss: 4.1151 Explore P: 0.8844
Episode: 429 Total reward: 16.0 Training loss: 341.2514 Explore P: 0.8844
Episode: 430 Total reward: 35.0 Training loss: 8.4949 Explore P: 0.8843
Episode: 431 Total reward: 20.0 Training loss: 28.8913 Explore P: 0.8843
Episode: 432 Total reward: 16.0 Training loss: 16.4739 Explore P: 0.8843
Episode: 433 Total reward: 14.0 Training loss: 10.0544 Explore P: 0.8842
Episode: 434 Total reward: 12.0 Training loss: 1.9450 Explore P: 0.8842
Episode: 435 Total reward: 19.0 Training loss: 33.0671 Explore P: 0.8842
Episode: 436 Total reward: 11.0 Training loss: 21.9927 Explore P: 0.8842
Episode: 437 Total reward: 13.0 Training loss: 85.1223 Explore P: 0.8841
Episode: 438 Total reward: 46.0 Training loss: 156.3336 Explore P: 0.8841
Episode: 439 Total reward: 79.0 Training loss: 3.9336 Explore P: 0.8839
Episode: 440 Total reward: 26.0 Training loss: 10.7540 Explore P: 0.8839
Episode: 441 Total reward: 17.0 Training loss: 30.5525 Explore P: 0.8838
Episode: 442 Total reward: 38.0 Training loss: 18.1163 Explore P: 0.8838
Episode: 443 Total reward: 39.0 Training loss: 3.4425 Explore P: 0.8837
Episode: 444 Total reward: 18.0 Training loss: 7.2422 Explore P: 0.8837
Episode: 445 Total reward: 18.0 Training loss: 40.2299 Explore P: 0.8836
Episode: 446 Total reward: 18.0 Training loss: 3.3639 Explore P: 0.8836
Episode: 447 Total reward: 11.0 Training loss: 8.3557 Explore P: 0.8836
Episode: 448 Total reward: 17.0 Training loss: 84.7285 Explore P: 0.8836
Episode: 449 Total reward: 28.0 Training loss: 1.3240 Explore P: 0.8835
Episode: 450 Total reward: 11.0 Training loss: 126.4161 Explore P: 0.8835
Episode: 451 Total reward: 33.0 Training loss: 364.5561 Explore P: 0.8834
Episode: 452 Total reward: 17.0 Training loss: 47.0084 Explore P: 0.8834
Episode: 453 Total reward: 21.0 Training loss: 1.8626 Explore P: 0.8834
Episode: 454 Total reward: 41.0 Training loss: 25.0590 Explore P: 0.8833
Episode: 455 Total reward: 26.0 Training loss: 69.2681 Explore P: 0.8833
Episode: 456 Total reward: 22.0 Training loss: 20.1102 Explore P: 0.8832
Episode: 457 Total reward: 34.0 Training loss: 2.3623 Explore P: 0.8832
Episode: 458 Total reward: 14.0 Training loss: 1.7676 Explore P: 0.8831
Episode: 459 Total reward: 59.0 Training loss: 18.7625 Explore P: 0.8830
Episode: 460 Total reward: 15.0 Training loss: 1648.1449 Explore P: 0.8830
Episode: 461 Total reward: 13.0 Training loss: 1486.9767 Explore P: 0.8830
Episode: 462 Total reward: 20.0 Training loss: 46.9730 Explore P: 0.8829
Episode: 463 Total reward: 17.0 Training loss: 71.7918 Explore P: 0.8829
Episode: 464 Total reward: 19.0 Training loss: 1.5552 Explore P: 0.8829
Episode: 465 Total reward: 12.0 Training loss: 1471.5222 Explore P: 0.8829
Episode: 466 Total reward: 18.0 Training loss: 35.7932 Explore P: 0.8828
Episode: 467 Total reward: 17.0 Training loss: 1.5348 Explore P: 0.8828
Episode: 468 Total reward: 22.0 Training loss: 134.5116 Explore P: 0.8828
Episode: 469 Total reward: 12.0 Training loss: 1.3429 Explore P: 0.8827
Episode: 470 Total reward: 21.0 Training loss: 6.5429 Explore P: 0.8827
Episode: 471 Total reward: 15.0 Training loss: 49.4887 Explore P: 0.8827
Episode: 472 Total reward: 9.0 Training loss: 71.7700 Explore P: 0.8827
Episode: 473 Total reward: 9.0 Training loss: 3.3220 Explore P: 0.8826
Episode: 474 Total reward: 18.0 Training loss: 93.1761 Explore P: 0.8826
Episode: 475 Total reward: 21.0 Training loss: 3.6316 Explore P: 0.8826
Episode: 476 Total reward: 13.0 Training loss: 1.6208 Explore P: 0.8826
Episode: 477 Total reward: 17.0 Training loss: 5.4720 Explore P: 0.8825
Episode: 478 Total reward: 18.0 Training loss: 347.9337 Explore P: 0.8825
Episode: 479 Total reward: 15.0 Training loss: 1.7959 Explore P: 0.8825
Episode: 480 Total reward: 19.0 Training loss: 55.4038 Explore P: 0.8824
Episode: 481 Total reward: 14.0 Training loss: 57.5410 Explore P: 0.8824
Episode: 482 Total reward: 12.0 Training loss: 114.4295 Explore P: 0.8824
Episode: 483 Total reward: 20.0 Training loss: 81.9709 Explore P: 0.8824
Episode: 484 Total reward: 20.0 Training loss: 2.9972 Explore P: 0.8823
Episode: 485 Total reward: 32.0 Training loss: 265.3756 Explore P: 0.8823
Episode: 486 Total reward: 41.0 Training loss: 1.7845 Explore P: 0.8822
Episode: 487 Total reward: 8.0 Training loss: 764.8834 Explore P: 0.8822
Episode: 488 Total reward: 31.0 Training loss: 50.2766 Explore P: 0.8821
Episode: 489 Total reward: 29.0 Training loss: 1.2385 Explore P: 0.8821
Episode: 490 Total reward: 40.0 Training loss: 71.1433 Explore P: 0.8820
Episode: 491 Total reward: 19.0 Training loss: 1.0516 Explore P: 0.8820
Episode: 492 Total reward: 16.0 Training loss: 129.6053 Explore P: 0.8819
Episode: 493 Total reward: 9.0 Training loss: 53.4456 Explore P: 0.8819
Episode: 494 Total reward: 12.0 Training loss: 4.0331 Explore P: 0.8819
Episode: 495 Total reward: 24.0 Training loss: 77.1186 Explore P: 0.8819
Episode: 496 Total reward: 20.0 Training loss: 104.9298 Explore P: 0.8818
Episode: 497 Total reward: 19.0 Training loss: 47.9417 Explore P: 0.8818
Episode: 498 Total reward: 13.0 Training loss: 1.6315 Explore P: 0.8818
Episode: 499 Total reward: 16.0 Training loss: 1.5163 Explore P: 0.8817
Episode: 500 Total reward: 20.0 Training loss: 2.0781 Explore P: 0.8817
Episode: 501 Total reward: 10.0 Training loss: 72.5521 Explore P: 0.8817
Episode: 502 Total reward: 13.0 Training loss: 55.5582 Explore P: 0.8817
Episode: 503 Total reward: 12.0 Training loss: 295.1487 Explore P: 0.8817
Episode: 504 Total reward: 17.0 Training loss: 711.7727 Explore P: 0.8816
Episode: 505 Total reward: 13.0 Training loss: 17.0660 Explore P: 0.8816
Episode: 506 Total reward: 16.0 Training loss: 2.8978 Explore P: 0.8816
Episode: 507 Total reward: 36.0 Training loss: 1794.4598 Explore P: 0.8815
Episode: 508 Total reward: 10.0 Training loss: 42.4992 Explore P: 0.8815
Episode: 509 Total reward: 39.0 Training loss: 49.7454 Explore P: 0.8814
Episode: 510 Total reward: 12.0 Training loss: 3.5121 Explore P: 0.8814
Episode: 511 Total reward: 18.0 Training loss: 36.6299 Explore P: 0.8814
Episode: 512 Total reward: 14.0 Training loss: 10.3544 Explore P: 0.8813
Episode: 513 Total reward: 19.0 Training loss: 116.9796 Explore P: 0.8813
Episode: 514 Total reward: 14.0 Training loss: 1.2873 Explore P: 0.8813
Episode: 515 Total reward: 18.0 Training loss: 19.1279 Explore P: 0.8813
Episode: 516 Total reward: 34.0 Training loss: 5.6105 Explore P: 0.8812
Episode: 517 Total reward: 78.0 Training loss: 45.6594 Explore P: 0.8811
Episode: 518 Total reward: 17.0 Training loss: 5.0352 Explore P: 0.8810
Episode: 519 Total reward: 12.0 Training loss: 192.1135 Explore P: 0.8810
Episode: 520 Total reward: 22.0 Training loss: 0.8893 Explore P: 0.8810
Episode: 521 Total reward: 18.0 Training loss: 16.3595 Explore P: 0.8809
Episode: 522 Total reward: 15.0 Training loss: 22.9445 Explore P: 0.8809
Episode: 523 Total reward: 13.0 Training loss: 24.9552 Explore P: 0.8809
Episode: 524 Total reward: 12.0 Training loss: 33.0999 Explore P: 0.8809
Episode: 525 Total reward: 18.0 Training loss: 1.0210 Explore P: 0.8808
Episode: 526 Total reward: 31.0 Training loss: 15.4029 Explore P: 0.8808
Episode: 527 Total reward: 17.0 Training loss: 96.9736 Explore P: 0.8808
Episode: 528 Total reward: 13.0 Training loss: 11.0489 Explore P: 0.8807
Episode: 529 Total reward: 24.0 Training loss: 15.4588 Explore P: 0.8807
Episode: 530 Total reward: 13.0 Training loss: 21.9080 Explore P: 0.8807
Episode: 531 Total reward: 39.0 Training loss: 260.8552 Explore P: 0.8806
Episode: 532 Total reward: 14.0 Training loss: 1.7086 Explore P: 0.8806
Episode: 533 Total reward: 18.0 Training loss: 1.6893 Explore P: 0.8805
Episode: 534 Total reward: 13.0 Training loss: 46.8763 Explore P: 0.8805
Episode: 535 Total reward: 18.0 Training loss: 36.2230 Explore P: 0.8805
Episode: 536 Total reward: 15.0 Training loss: 253.7777 Explore P: 0.8805
Episode: 537 Total reward: 15.0 Training loss: 261.8124 Explore P: 0.8804
Episode: 538 Total reward: 36.0 Training loss: 112.0059 Explore P: 0.8804
Episode: 539 Total reward: 9.0 Training loss: 187.7267 Explore P: 0.8804
Episode: 540 Total reward: 18.0 Training loss: 57.2775 Explore P: 0.8803
Episode: 541 Total reward: 17.0 Training loss: 256.8086 Explore P: 0.8803
Episode: 542 Total reward: 17.0 Training loss: 2.9168 Explore P: 0.8803
Episode: 543 Total reward: 13.0 Training loss: 1.7844 Explore P: 0.8802
Episode: 544 Total reward: 24.0 Training loss: 1.5149 Explore P: 0.8802
Episode: 545 Total reward: 8.0 Training loss: 1.1522 Explore P: 0.8802
Episode: 546 Total reward: 18.0 Training loss: 844.8368 Explore P: 0.8802
Episode: 547 Total reward: 21.0 Training loss: 11.1350 Explore P: 0.8801
Episode: 548 Total reward: 20.0 Training loss: 83.5968 Explore P: 0.8801
Episode: 549 Total reward: 19.0 Training loss: 1.2523 Explore P: 0.8801
Episode: 550 Total reward: 13.0 Training loss: 79.3482 Explore P: 0.8800
Episode: 551 Total reward: 34.0 Training loss: 6.9049 Explore P: 0.8800
Episode: 552 Total reward: 26.0 Training loss: 51.1075 Explore P: 0.8799
Episode: 553 Total reward: 12.0 Training loss: 190.2796 Explore P: 0.8799
Episode: 554 Total reward: 10.0 Training loss: 30.9724 Explore P: 0.8799
Episode: 555 Total reward: 29.0 Training loss: 2.2990 Explore P: 0.8798
Episode: 556 Total reward: 16.0 Training loss: 34.5042 Explore P: 0.8798
Episode: 557 Total reward: 24.0 Training loss: 1.4802 Explore P: 0.8798
Episode: 558 Total reward: 33.0 Training loss: 1.1156 Explore P: 0.8797
Episode: 559 Total reward: 12.0 Training loss: 46.0376 Explore P: 0.8797
Episode: 560 Total reward: 21.0 Training loss: 1.5863 Explore P: 0.8797
Episode: 561 Total reward: 22.0 Training loss: 40.0225 Explore P: 0.8796
Episode: 562 Total reward: 17.0 Training loss: 14.8231 Explore P: 0.8796
Episode: 563 Total reward: 17.0 Training loss: 1276.4786 Explore P: 0.8796
Episode: 564 Total reward: 12.0 Training loss: 21.1766 Explore P: 0.8795
Episode: 565 Total reward: 20.0 Training loss: 50.8628 Explore P: 0.8795
Episode: 566 Total reward: 10.0 Training loss: 3.8476 Explore P: 0.8795
Episode: 567 Total reward: 28.0 Training loss: 0.9138 Explore P: 0.8794
Episode: 568 Total reward: 35.0 Training loss: 0.8170 Explore P: 0.8794
Episode: 569 Total reward: 14.0 Training loss: 162.8155 Explore P: 0.8794
Episode: 570 Total reward: 14.0 Training loss: 14.3438 Explore P: 0.8793
Episode: 571 Total reward: 16.0 Training loss: 1206.4801 Explore P: 0.8793
Episode: 572 Total reward: 11.0 Training loss: 1.3423 Explore P: 0.8793
Episode: 573 Total reward: 14.0 Training loss: 857.1071 Explore P: 0.8793
Episode: 574 Total reward: 11.0 Training loss: 169.8791 Explore P: 0.8792
Episode: 575 Total reward: 11.0 Training loss: 5.9466 Explore P: 0.8792
Episode: 576 Total reward: 10.0 Training loss: 129.1750 Explore P: 0.8792
Episode: 577 Total reward: 20.0 Training loss: 119.8796 Explore P: 0.8792
Episode: 578 Total reward: 21.0 Training loss: 1.4058 Explore P: 0.8791
Episode: 579 Total reward: 20.0 Training loss: 1.2665 Explore P: 0.8791
Episode: 580 Total reward: 18.0 Training loss: 52.3804 Explore P: 0.8791
Episode: 581 Total reward: 12.0 Training loss: 292.3623 Explore P: 0.8790
Episode: 582 Total reward: 21.0 Training loss: 1.1400 Explore P: 0.8790
Episode: 583 Total reward: 13.0 Training loss: 1.0920 Explore P: 0.8790
Episode: 584 Total reward: 35.0 Training loss: 54.1750 Explore P: 0.8789
Episode: 585 Total reward: 12.0 Training loss: 0.9651 Explore P: 0.8789
Episode: 586 Total reward: 13.0 Training loss: 40.2893 Explore P: 0.8789
Episode: 587 Total reward: 9.0 Training loss: 34.6035 Explore P: 0.8789
Episode: 588 Total reward: 16.0 Training loss: 7.2387 Explore P: 0.8788
Episode: 589 Total reward: 15.0 Training loss: 76.0612 Explore P: 0.8788
Episode: 590 Total reward: 54.0 Training loss: 14.0837 Explore P: 0.8787
Episode: 591 Total reward: 8.0 Training loss: 38.7426 Explore P: 0.8787
Episode: 592 Total reward: 12.0 Training loss: 6.2585 Explore P: 0.8787
Episode: 593 Total reward: 19.0 Training loss: 156.2599 Explore P: 0.8786
Episode: 594 Total reward: 12.0 Training loss: 46.5687 Explore P: 0.8786
Episode: 595 Total reward: 12.0 Training loss: 27.7330 Explore P: 0.8786
Episode: 596 Total reward: 13.0 Training loss: 1.7269 Explore P: 0.8786
Episode: 597 Total reward: 16.0 Training loss: 0.9769 Explore P: 0.8786
Episode: 598 Total reward: 37.0 Training loss: 40.9529 Explore P: 0.8785
Episode: 599 Total reward: 13.0 Training loss: 4.8530 Explore P: 0.8785
Episode: 600 Total reward: 11.0 Training loss: 839.8511 Explore P: 0.8785
Episode: 601 Total reward: 14.0 Training loss: 1.4100 Explore P: 0.8784
Episode: 602 Total reward: 12.0 Training loss: 1.7421 Explore P: 0.8784
Episode: 603 Total reward: 11.0 Training loss: 1.7922 Explore P: 0.8784
Episode: 604 Total reward: 20.0 Training loss: 29.3919 Explore P: 0.8784
Episode: 605 Total reward: 22.0 Training loss: 71.8362 Explore P: 0.8783
Episode: 606 Total reward: 23.0 Training loss: 8.3279 Explore P: 0.8783
Episode: 607 Total reward: 34.0 Training loss: 2.0082 Explore P: 0.8782
Episode: 608 Total reward: 25.0 Training loss: 41.2319 Explore P: 0.8782
Episode: 609 Total reward: 10.0 Training loss: 35.7785 Explore P: 0.8782
Episode: 610 Total reward: 17.0 Training loss: 27.8885 Explore P: 0.8781
Episode: 611 Total reward: 30.0 Training loss: 3.1302 Explore P: 0.8781
Episode: 612 Total reward: 9.0 Training loss: 23.6826 Explore P: 0.8781
Episode: 613 Total reward: 14.0 Training loss: 5.1332 Explore P: 0.8780
Episode: 614 Total reward: 19.0 Training loss: 263.7359 Explore P: 0.8780
Episode: 615 Total reward: 22.0 Training loss: 1.6483 Explore P: 0.8780
Episode: 616 Total reward: 19.0 Training loss: 1.4201 Explore P: 0.8779
Episode: 617 Total reward: 10.0 Training loss: 0.8826 Explore P: 0.8779
Episode: 618 Total reward: 13.0 Training loss: 41.2525 Explore P: 0.8779
Episode: 619 Total reward: 9.0 Training loss: 1.1210 Explore P: 0.8779
Episode: 620 Total reward: 11.0 Training loss: 5.9038 Explore P: 0.8779
Episode: 621 Total reward: 14.0 Training loss: 9.7805 Explore P: 0.8778
Episode: 622 Total reward: 13.0 Training loss: 1.0943 Explore P: 0.8778
Episode: 623 Total reward: 12.0 Training loss: 633.2402 Explore P: 0.8778
Episode: 624 Total reward: 22.0 Training loss: 113.0516 Explore P: 0.8777
Episode: 625 Total reward: 17.0 Training loss: 1.4160 Explore P: 0.8777
Episode: 626 Total reward: 27.0 Training loss: 1.3914 Explore P: 0.8777
Episode: 627 Total reward: 32.0 Training loss: 1.4523 Explore P: 0.8776
Episode: 628 Total reward: 16.0 Training loss: 314.3184 Explore P: 0.8776
Episode: 629 Total reward: 23.0 Training loss: 68.8016 Explore P: 0.8775
Episode: 630 Total reward: 12.0 Training loss: 22.1307 Explore P: 0.8775
Episode: 631 Total reward: 23.0 Training loss: 40.9603 Explore P: 0.8775
Episode: 632 Total reward: 12.0 Training loss: 82.0903 Explore P: 0.8775
Episode: 633 Total reward: 48.0 Training loss: 2.7859 Explore P: 0.8774
Episode: 634 Total reward: 29.0 Training loss: 8.7030 Explore P: 0.8773
Episode: 635 Total reward: 12.0 Training loss: 2.0562 Explore P: 0.8773
Episode: 636 Total reward: 18.0 Training loss: 242.7866 Explore P: 0.8773
Episode: 637 Total reward: 15.0 Training loss: 86.8163 Explore P: 0.8773
Episode: 638 Total reward: 30.0 Training loss: 86.7243 Explore P: 0.8772
Episode: 639 Total reward: 39.0 Training loss: 113.0503 Explore P: 0.8771
Episode: 640 Total reward: 13.0 Training loss: 19.4771 Explore P: 0.8771
Episode: 641 Total reward: 16.0 Training loss: 1.1133 Explore P: 0.8771
Episode: 642 Total reward: 40.0 Training loss: 2.4263 Explore P: 0.8770
Episode: 643 Total reward: 19.0 Training loss: 2.2171 Explore P: 0.8770
Episode: 644 Total reward: 10.0 Training loss: 8.8965 Explore P: 0.8770
Episode: 645 Total reward: 82.0 Training loss: 3.6715 Explore P: 0.8768
Episode: 646 Total reward: 15.0 Training loss: 5.9110 Explore P: 0.8768
Episode: 647 Total reward: 25.0 Training loss: 41.8425 Explore P: 0.8768
Episode: 648 Total reward: 15.0 Training loss: 48.0257 Explore P: 0.8767
Episode: 649 Total reward: 26.0 Training loss: 11.5761 Explore P: 0.8767
Episode: 650 Total reward: 14.0 Training loss: 3.3053 Explore P: 0.8767
Episode: 651 Total reward: 37.0 Training loss: 4.2131 Explore P: 0.8766
Episode: 652 Total reward: 31.0 Training loss: 46.7141 Explore P: 0.8765
Episode: 653 Total reward: 30.0 Training loss: 1083.0470 Explore P: 0.8765
Episode: 654 Total reward: 14.0 Training loss: 5.6465 Explore P: 0.8765
Episode: 655 Total reward: 25.0 Training loss: 2.3001 Explore P: 0.8764
Episode: 656 Total reward: 23.0 Training loss: 28.0950 Explore P: 0.8764
Episode: 657 Total reward: 14.0 Training loss: 4.5472 Explore P: 0.8764
Episode: 658 Total reward: 10.0 Training loss: 3207.7803 Explore P: 0.8763
Episode: 659 Total reward: 13.0 Training loss: 22.3672 Explore P: 0.8763
Episode: 660 Total reward: 11.0 Training loss: 8.1780 Explore P: 0.8763
Episode: 661 Total reward: 26.0 Training loss: 21.7542 Explore P: 0.8763
Episode: 662 Total reward: 16.0 Training loss: 42.4077 Explore P: 0.8762
Episode: 663 Total reward: 15.0 Training loss: 1.5661 Explore P: 0.8762
Episode: 664 Total reward: 13.0 Training loss: 2.4282 Explore P: 0.8762
Episode: 665 Total reward: 17.0 Training loss: 1.0837 Explore P: 0.8761
Episode: 666 Total reward: 17.0 Training loss: 2.7738 Explore P: 0.8761
Episode: 667 Total reward: 26.0 Training loss: 68.1016 Explore P: 0.8761
Episode: 668 Total reward: 9.0 Training loss: 153.9762 Explore P: 0.8761
Episode: 669 Total reward: 21.0 Training loss: 16.8364 Explore P: 0.8760
Episode: 670 Total reward: 10.0 Training loss: 1.0914 Explore P: 0.8760
Episode: 671 Total reward: 18.0 Training loss: 1.1803 Explore P: 0.8760
Episode: 672 Total reward: 20.0 Training loss: 0.8375 Explore P: 0.8759
Episode: 673 Total reward: 12.0 Training loss: 99.4468 Explore P: 0.8759
Episode: 674 Total reward: 22.0 Training loss: 18.7018 Explore P: 0.8759
Episode: 675 Total reward: 15.0 Training loss: 1.3156 Explore P: 0.8759
Episode: 676 Total reward: 18.0 Training loss: 7.6456 Explore P: 0.8758
Episode: 677 Total reward: 15.0 Training loss: 30.8055 Explore P: 0.8758
Episode: 678 Total reward: 34.0 Training loss: 14.7232 Explore P: 0.8757
Episode: 679 Total reward: 12.0 Training loss: 1.3936 Explore P: 0.8757
Episode: 680 Total reward: 17.0 Training loss: 2.4809 Explore P: 0.8757
Episode: 681 Total reward: 14.0 Training loss: 37.0612 Explore P: 0.8757
Episode: 682 Total reward: 13.0 Training loss: 256.3737 Explore P: 0.8756
Episode: 683 Total reward: 18.0 Training loss: 3.8273 Explore P: 0.8756
Episode: 684 Total reward: 51.0 Training loss: 4.5533 Explore P: 0.8755
Episode: 685 Total reward: 21.0 Training loss: 41.5945 Explore P: 0.8755
Episode: 686 Total reward: 16.0 Training loss: 136.3358 Explore P: 0.8755
Episode: 687 Total reward: 18.0 Training loss: 51.0797 Explore P: 0.8754
Episode: 688 Total reward: 18.0 Training loss: 2.9252 Explore P: 0.8754
Episode: 689 Total reward: 19.0 Training loss: 3.9109 Explore P: 0.8754
Episode: 690 Total reward: 14.0 Training loss: 2.4372 Explore P: 0.8753
Episode: 691 Total reward: 18.0 Training loss: 1089.3329 Explore P: 0.8753
Episode: 692 Total reward: 9.0 Training loss: 2.2997 Explore P: 0.8753
Episode: 693 Total reward: 12.0 Training loss: 55.9123 Explore P: 0.8753
Episode: 694 Total reward: 10.0 Training loss: 4.3771 Explore P: 0.8753
Episode: 695 Total reward: 12.0 Training loss: 49.8245 Explore P: 0.8752
Episode: 696 Total reward: 13.0 Training loss: 46.5438 Explore P: 0.8752
Episode: 697 Total reward: 33.0 Training loss: 417.8878 Explore P: 0.8752
Episode: 698 Total reward: 33.0 Training loss: 1.8474 Explore P: 0.8751
Episode: 699 Total reward: 9.0 Training loss: 22.9120 Explore P: 0.8751
Episode: 700 Total reward: 16.0 Training loss: 30.3611 Explore P: 0.8751
Episode: 701 Total reward: 45.0 Training loss: 9.2251 Explore P: 0.8750
Episode: 702 Total reward: 18.0 Training loss: 9.9054 Explore P: 0.8749
Episode: 703 Total reward: 18.0 Training loss: 0.7986 Explore P: 0.8749
Episode: 704 Total reward: 11.0 Training loss: 19.0924 Explore P: 0.8749
Episode: 705 Total reward: 14.0 Training loss: 2.3086 Explore P: 0.8749
Episode: 706 Total reward: 43.0 Training loss: 86.5648 Explore P: 0.8748
Episode: 707 Total reward: 19.0 Training loss: 4.5273 Explore P: 0.8748
Episode: 708 Total reward: 15.0 Training loss: 2.9611 Explore P: 0.8747
Episode: 709 Total reward: 36.0 Training loss: 15.0515 Explore P: 0.8747
Episode: 710 Total reward: 18.0 Training loss: 6.9536 Explore P: 0.8746
Episode: 711 Total reward: 12.0 Training loss: 4.9341 Explore P: 0.8746
Episode: 712 Total reward: 24.0 Training loss: 2.0466 Explore P: 0.8746
Episode: 713 Total reward: 14.0 Training loss: 5.6517 Explore P: 0.8746
Episode: 714 Total reward: 14.0 Training loss: 13.4224 Explore P: 0.8745
Episode: 715 Total reward: 13.0 Training loss: 185.6229 Explore P: 0.8745
Episode: 716 Total reward: 8.0 Training loss: 32.1380 Explore P: 0.8745
Episode: 717 Total reward: 19.0 Training loss: 8.5155 Explore P: 0.8745
Episode: 718 Total reward: 40.0 Training loss: 1.4117 Explore P: 0.8744
Episode: 719 Total reward: 15.0 Training loss: 76.6661 Explore P: 0.8744
Episode: 720 Total reward: 17.0 Training loss: 22.1582 Explore P: 0.8743
Episode: 721 Total reward: 21.0 Training loss: 238.8746 Explore P: 0.8743
Episode: 722 Total reward: 23.0 Training loss: 2079.4592 Explore P: 0.8743
Episode: 723 Total reward: 23.0 Training loss: 1.3283 Explore P: 0.8742
Episode: 724 Total reward: 12.0 Training loss: 59.0181 Explore P: 0.8742
Episode: 725 Total reward: 13.0 Training loss: 66.6890 Explore P: 0.8742
Episode: 726 Total reward: 40.0 Training loss: 3.2684 Explore P: 0.8741
Episode: 727 Total reward: 13.0 Training loss: 3.0861 Explore P: 0.8741
Episode: 728 Total reward: 11.0 Training loss: 77.9148 Explore P: 0.8741
Episode: 729 Total reward: 12.0 Training loss: 5.1617 Explore P: 0.8740
Episode: 730 Total reward: 36.0 Training loss: 1.7215 Explore P: 0.8740
Episode: 731 Total reward: 12.0 Training loss: 92.4664 Explore P: 0.8740
Episode: 732 Total reward: 13.0 Training loss: 4.3808 Explore P: 0.8739
Episode: 733 Total reward: 28.0 Training loss: 0.8530 Explore P: 0.8739
Episode: 734 Total reward: 22.0 Training loss: 16.3364 Explore P: 0.8739
Episode: 735 Total reward: 11.0 Training loss: 52.4047 Explore P: 0.8738
Episode: 736 Total reward: 23.0 Training loss: 257.6203 Explore P: 0.8738
Episode: 737 Total reward: 18.0 Training loss: 194.7991 Explore P: 0.8738
Episode: 738 Total reward: 27.0 Training loss: 6.6108 Explore P: 0.8737
Episode: 739 Total reward: 11.0 Training loss: 286.2331 Explore P: 0.8737
Episode: 740 Total reward: 36.0 Training loss: 6.1047 Explore P: 0.8736
Episode: 741 Total reward: 16.0 Training loss: 1.1657 Explore P: 0.8736
Episode: 742 Total reward: 9.0 Training loss: 4.1182 Explore P: 0.8736
Episode: 743 Total reward: 10.0 Training loss: 2.3056 Explore P: 0.8736
Episode: 744 Total reward: 17.0 Training loss: 110.5706 Explore P: 0.8735
Episode: 745 Total reward: 43.0 Training loss: 132.3166 Explore P: 0.8735
Episode: 746 Total reward: 21.0 Training loss: 3.4706 Explore P: 0.8734
Episode: 747 Total reward: 30.0 Training loss: 26.7990 Explore P: 0.8734
Episode: 748 Total reward: 11.0 Training loss: 5.4170 Explore P: 0.8734
Episode: 749 Total reward: 11.0 Training loss: 18.9884 Explore P: 0.8733
Episode: 750 Total reward: 21.0 Training loss: 1.0076 Explore P: 0.8733
Episode: 751 Total reward: 14.0 Training loss: 133.6001 Explore P: 0.8733
Episode: 752 Total reward: 10.0 Training loss: 2.1782 Explore P: 0.8733
Episode: 753 Total reward: 7.0 Training loss: 2.6692 Explore P: 0.8733
Episode: 754 Total reward: 12.0 Training loss: 2.2982 Explore P: 0.8732
Episode: 755 Total reward: 30.0 Training loss: 109.8890 Explore P: 0.8732
Episode: 756 Total reward: 11.0 Training loss: 204.5044 Explore P: 0.8732
Episode: 757 Total reward: 75.0 Training loss: 180.2672 Explore P: 0.8730
Episode: 758 Total reward: 16.0 Training loss: 60.3261 Explore P: 0.8730
Episode: 759 Total reward: 13.0 Training loss: 346.4758 Explore P: 0.8730
Episode: 760 Total reward: 13.0 Training loss: 1.6579 Explore P: 0.8730
Episode: 761 Total reward: 17.0 Training loss: 65.4305 Explore P: 0.8729
Episode: 762 Total reward: 16.0 Training loss: 28.4834 Explore P: 0.8729
Episode: 763 Total reward: 15.0 Training loss: 2.0735 Explore P: 0.8729
Episode: 764 Total reward: 36.0 Training loss: 49.8328 Explore P: 0.8728
Episode: 765 Total reward: 25.0 Training loss: 121.7463 Explore P: 0.8728
Episode: 766 Total reward: 23.0 Training loss: 26.0409 Explore P: 0.8727
Episode: 767 Total reward: 22.0 Training loss: 29.1394 Explore P: 0.8727
Episode: 768 Total reward: 18.0 Training loss: 7.5708 Explore P: 0.8727
Episode: 769 Total reward: 61.0 Training loss: 11.3271 Explore P: 0.8726
Episode: 770 Total reward: 18.0 Training loss: 37.0613 Explore P: 0.8725
Episode: 771 Total reward: 16.0 Training loss: 97.2203 Explore P: 0.8725
Episode: 772 Total reward: 16.0 Training loss: 2.9593 Explore P: 0.8725
Episode: 773 Total reward: 24.0 Training loss: 35.0318 Explore P: 0.8724
Episode: 774 Total reward: 8.0 Training loss: 0.7972 Explore P: 0.8724
Episode: 775 Total reward: 10.0 Training loss: 12.9477 Explore P: 0.8724
Episode: 776 Total reward: 13.0 Training loss: 1.1169 Explore P: 0.8724
Episode: 777 Total reward: 11.0 Training loss: 11.6220 Explore P: 0.8724
Episode: 778 Total reward: 22.0 Training loss: 0.9933 Explore P: 0.8723
Episode: 779 Total reward: 19.0 Training loss: 0.4668 Explore P: 0.8723
Episode: 780 Total reward: 23.0 Training loss: 25.2518 Explore P: 0.8723
Episode: 781 Total reward: 14.0 Training loss: 68.7420 Explore P: 0.8722
Episode: 782 Total reward: 15.0 Training loss: 0.6638 Explore P: 0.8722
Episode: 783 Total reward: 10.0 Training loss: 3.8161 Explore P: 0.8722
Episode: 784 Total reward: 18.0 Training loss: 5.5738 Explore P: 0.8722
Episode: 785 Total reward: 16.0 Training loss: 156.5714 Explore P: 0.8721
Episode: 786 Total reward: 10.0 Training loss: 59.5760 Explore P: 0.8721
Episode: 787 Total reward: 16.0 Training loss: 126.4158 Explore P: 0.8721
Episode: 788 Total reward: 23.0 Training loss: 0.9148 Explore P: 0.8720
Episode: 789 Total reward: 24.0 Training loss: 22.2685 Explore P: 0.8720
Episode: 790 Total reward: 11.0 Training loss: 8.0147 Explore P: 0.8720
Episode: 791 Total reward: 11.0 Training loss: 193.7278 Explore P: 0.8720
Episode: 792 Total reward: 19.0 Training loss: 6.8637 Explore P: 0.8719
Episode: 793 Total reward: 10.0 Training loss: 154.2660 Explore P: 0.8719
Episode: 794 Total reward: 32.0 Training loss: 84.4196 Explore P: 0.8719
Episode: 795 Total reward: 28.0 Training loss: 460.9606 Explore P: 0.8718
Episode: 796 Total reward: 12.0 Training loss: 2.1138 Explore P: 0.8718
Episode: 797 Total reward: 22.0 Training loss: 1.8884 Explore P: 0.8718
Episode: 798 Total reward: 25.0 Training loss: 1.7683 Explore P: 0.8717
Episode: 799 Total reward: 17.0 Training loss: 1.7939 Explore P: 0.8717
Episode: 800 Total reward: 17.0 Training loss: 29.8683 Explore P: 0.8716
Episode: 801 Total reward: 21.0 Training loss: 144.9422 Explore P: 0.8716
Episode: 802 Total reward: 12.0 Training loss: 52.8629 Explore P: 0.8716
Episode: 803 Total reward: 8.0 Training loss: 27.2320 Explore P: 0.8716
Episode: 804 Total reward: 11.0 Training loss: 4.0580 Explore P: 0.8716
Episode: 805 Total reward: 10.0 Training loss: 2.3673 Explore P: 0.8715
Episode: 806 Total reward: 22.0 Training loss: 19.4872 Explore P: 0.8715
Episode: 807 Total reward: 20.0 Training loss: 1.2333 Explore P: 0.8715
Episode: 808 Total reward: 31.0 Training loss: 98.6838 Explore P: 0.8714
Episode: 809 Total reward: 8.0 Training loss: 34.1427 Explore P: 0.8714
Episode: 810 Total reward: 21.0 Training loss: 1.0492 Explore P: 0.8714
Episode: 811 Total reward: 10.0 Training loss: 77.1242 Explore P: 0.8713
Episode: 812 Total reward: 14.0 Training loss: 34.4056 Explore P: 0.8713
Episode: 813 Total reward: 8.0 Training loss: 1.3595 Explore P: 0.8713
Episode: 814 Total reward: 18.0 Training loss: 12.3690 Explore P: 0.8713
Episode: 815 Total reward: 14.0 Training loss: 1.6600 Explore P: 0.8713
Episode: 816 Total reward: 16.0 Training loss: 3.5904 Explore P: 0.8712
Episode: 817 Total reward: 12.0 Training loss: 7.1066 Explore P: 0.8712
Episode: 818 Total reward: 16.0 Training loss: 310.5594 Explore P: 0.8712
Episode: 819 Total reward: 12.0 Training loss: 1.7142 Explore P: 0.8712
Episode: 820 Total reward: 14.0 Training loss: 46.1464 Explore P: 0.8711
Episode: 821 Total reward: 11.0 Training loss: 37.7602 Explore P: 0.8711
Episode: 822 Total reward: 19.0 Training loss: 2.2867 Explore P: 0.8711
Episode: 823 Total reward: 19.0 Training loss: 49.6364 Explore P: 0.8711
Episode: 824 Total reward: 20.0 Training loss: 23.7975 Explore P: 0.8710
Episode: 825 Total reward: 8.0 Training loss: 86.4702 Explore P: 0.8710
Episode: 826 Total reward: 10.0 Training loss: 109.2271 Explore P: 0.8710
Episode: 827 Total reward: 26.0 Training loss: 1.6457 Explore P: 0.8709
Episode: 828 Total reward: 31.0 Training loss: 0.7523 Explore P: 0.8709
Episode: 829 Total reward: 14.0 Training loss: 31.5831 Explore P: 0.8709
Episode: 830 Total reward: 15.0 Training loss: 125.4055 Explore P: 0.8708
Episode: 831 Total reward: 35.0 Training loss: 70.1737 Explore P: 0.8708
Episode: 832 Total reward: 11.0 Training loss: 2.3950 Explore P: 0.8708
Episode: 833 Total reward: 13.0 Training loss: 4.5710 Explore P: 0.8707
Episode: 834 Total reward: 20.0 Training loss: 277.5254 Explore P: 0.8707
Episode: 835 Total reward: 15.0 Training loss: 115.0021 Explore P: 0.8707
Episode: 836 Total reward: 9.0 Training loss: 25.3591 Explore P: 0.8707
Episode: 837 Total reward: 10.0 Training loss: 38.4561 Explore P: 0.8706
Episode: 838 Total reward: 11.0 Training loss: 1.6488 Explore P: 0.8706
Episode: 839 Total reward: 18.0 Training loss: 1.1640 Explore P: 0.8706
Episode: 840 Total reward: 18.0 Training loss: 0.9556 Explore P: 0.8706
Episode: 841 Total reward: 16.0 Training loss: 2.1415 Explore P: 0.8705
Episode: 842 Total reward: 15.0 Training loss: 6.4308 Explore P: 0.8705
Episode: 843 Total reward: 14.0 Training loss: 90.3724 Explore P: 0.8705
Episode: 844 Total reward: 15.0 Training loss: 319.6561 Explore P: 0.8705
Episode: 845 Total reward: 12.0 Training loss: 103.2496 Explore P: 0.8704
Episode: 846 Total reward: 8.0 Training loss: 144.8718 Explore P: 0.8704
Episode: 847 Total reward: 24.0 Training loss: 1.6967 Explore P: 0.8704
Episode: 848 Total reward: 11.0 Training loss: 56.7463 Explore P: 0.8704
Episode: 849 Total reward: 11.0 Training loss: 15.3487 Explore P: 0.8703
Episode: 850 Total reward: 11.0 Training loss: 8.7619 Explore P: 0.8703
Episode: 851 Total reward: 19.0 Training loss: 5.0982 Explore P: 0.8703
Episode: 852 Total reward: 27.0 Training loss: 7.7104 Explore P: 0.8702
Episode: 853 Total reward: 25.0 Training loss: 13.9045 Explore P: 0.8702
Episode: 854 Total reward: 60.0 Training loss: 244.9460 Explore P: 0.8701
Episode: 855 Total reward: 16.0 Training loss: 0.8236 Explore P: 0.8701
Episode: 856 Total reward: 10.0 Training loss: 1.7231 Explore P: 0.8701
Episode: 857 Total reward: 42.0 Training loss: 1.4555 Explore P: 0.8700
Episode: 858 Total reward: 34.0 Training loss: 6.9154 Explore P: 0.8699
Episode: 859 Total reward: 20.0 Training loss: 1098.9368 Explore P: 0.8699
Episode: 860 Total reward: 18.0 Training loss: 11.2132 Explore P: 0.8699
Episode: 861 Total reward: 11.0 Training loss: 19.1270 Explore P: 0.8698
Episode: 862 Total reward: 22.0 Training loss: 4.2847 Explore P: 0.8698
Episode: 863 Total reward: 12.0 Training loss: 3.1288 Explore P: 0.8698
Episode: 864 Total reward: 10.0 Training loss: 57.4067 Explore P: 0.8698
Episode: 865 Total reward: 12.0 Training loss: 1.2967 Explore P: 0.8697
Episode: 866 Total reward: 11.0 Training loss: 86.2742 Explore P: 0.8697
Episode: 867 Total reward: 10.0 Training loss: 4.0775 Explore P: 0.8697
Episode: 868 Total reward: 13.0 Training loss: 0.7639 Explore P: 0.8697
Episode: 869 Total reward: 8.0 Training loss: 2.6341 Explore P: 0.8697
Episode: 870 Total reward: 8.0 Training loss: 116.5058 Explore P: 0.8697
Episode: 871 Total reward: 38.0 Training loss: 1.7197 Explore P: 0.8696
Episode: 872 Total reward: 16.0 Training loss: 0.9525 Explore P: 0.8696
Episode: 873 Total reward: 10.0 Training loss: 15.9026 Explore P: 0.8695
Episode: 874 Total reward: 25.0 Training loss: 263.0744 Explore P: 0.8695
Episode: 875 Total reward: 15.0 Training loss: 77.8433 Explore P: 0.8695
Episode: 876 Total reward: 17.0 Training loss: 9.3909 Explore P: 0.8695
Episode: 877 Total reward: 15.0 Training loss: 86.4009 Explore P: 0.8694
Episode: 878 Total reward: 26.0 Training loss: 15.2522 Explore P: 0.8694
Episode: 879 Total reward: 18.0 Training loss: 1.9531 Explore P: 0.8693
Episode: 880 Total reward: 16.0 Training loss: 22.9299 Explore P: 0.8693
Episode: 881 Total reward: 19.0 Training loss: 26.7886 Explore P: 0.8693
Episode: 882 Total reward: 22.0 Training loss: 1.0828 Explore P: 0.8693
Episode: 883 Total reward: 19.0 Training loss: 388.1439 Explore P: 0.8692
Episode: 884 Total reward: 17.0 Training loss: 1.5505 Explore P: 0.8692
Episode: 885 Total reward: 15.0 Training loss: 33.5648 Explore P: 0.8692
Episode: 886 Total reward: 20.0 Training loss: 24.2722 Explore P: 0.8691
Episode: 887 Total reward: 9.0 Training loss: 58.7125 Explore P: 0.8691
Episode: 888 Total reward: 15.0 Training loss: 138.6774 Explore P: 0.8691
Episode: 889 Total reward: 8.0 Training loss: 20.3498 Explore P: 0.8691
Episode: 890 Total reward: 26.0 Training loss: 29.1326 Explore P: 0.8690
Episode: 891 Total reward: 9.0 Training loss: 2.7245 Explore P: 0.8690
Episode: 892 Total reward: 18.0 Training loss: 63.3749 Explore P: 0.8690
Episode: 893 Total reward: 29.0 Training loss: 201.8742 Explore P: 0.8689
Episode: 894 Total reward: 14.0 Training loss: 584.0474 Explore P: 0.8689
Episode: 895 Total reward: 20.0 Training loss: 0.3428 Explore P: 0.8689
Episode: 896 Total reward: 11.0 Training loss: 48.8032 Explore P: 0.8689
Episode: 897 Total reward: 14.0 Training loss: 93.2137 Explore P: 0.8688
Episode: 898 Total reward: 13.0 Training loss: 64.4537 Explore P: 0.8688
Episode: 899 Total reward: 25.0 Training loss: 1.3915 Explore P: 0.8688
Episode: 900 Total reward: 11.0 Training loss: 32.4393 Explore P: 0.8687
Episode: 901 Total reward: 24.0 Training loss: 0.3685 Explore P: 0.8687
Episode: 902 Total reward: 24.0 Training loss: 176.1371 Explore P: 0.8687
Episode: 903 Total reward: 26.0 Training loss: 1.4419 Explore P: 0.8686
Episode: 904 Total reward: 10.0 Training loss: 62.1251 Explore P: 0.8686
Episode: 905 Total reward: 20.0 Training loss: 185.5738 Explore P: 0.8686
Episode: 906 Total reward: 13.0 Training loss: 35.1169 Explore P: 0.8685
Episode: 907 Total reward: 14.0 Training loss: 15.4903 Explore P: 0.8685
Episode: 908 Total reward: 13.0 Training loss: 34.2666 Explore P: 0.8685
Episode: 909 Total reward: 26.0 Training loss: 2.0310 Explore P: 0.8685
Episode: 910 Total reward: 42.0 Training loss: 7.3427 Explore P: 0.8684
Episode: 911 Total reward: 14.0 Training loss: 5.7956 Explore P: 0.8684
Episode: 912 Total reward: 10.0 Training loss: 1.9275 Explore P: 0.8683
Episode: 913 Total reward: 12.0 Training loss: 22.2067 Explore P: 0.8683
Episode: 914 Total reward: 22.0 Training loss: 48.1205 Explore P: 0.8683
Episode: 915 Total reward: 51.0 Training loss: 34.1146 Explore P: 0.8682
Episode: 916 Total reward: 17.0 Training loss: 8.3798 Explore P: 0.8682
Episode: 917 Total reward: 13.0 Training loss: 3.8494 Explore P: 0.8681
Episode: 918 Total reward: 15.0 Training loss: 1.9174 Explore P: 0.8681
Episode: 919 Total reward: 53.0 Training loss: 109.9532 Explore P: 0.8680
Episode: 920 Total reward: 14.0 Training loss: 18.3663 Explore P: 0.8680
Episode: 921 Total reward: 14.0 Training loss: 12.1441 Explore P: 0.8680
Episode: 922 Total reward: 16.0 Training loss: 28.2551 Explore P: 0.8680
Episode: 923 Total reward: 11.0 Training loss: 1.0999 Explore P: 0.8679
Episode: 924 Total reward: 16.0 Training loss: 72.0011 Explore P: 0.8679
Episode: 925 Total reward: 18.0 Training loss: 3.6337 Explore P: 0.8679
Episode: 926 Total reward: 11.0 Training loss: 0.3317 Explore P: 0.8679
Episode: 927 Total reward: 8.0 Training loss: 1.7805 Explore P: 0.8678
Episode: 928 Total reward: 17.0 Training loss: 725.3488 Explore P: 0.8678
Episode: 929 Total reward: 21.0 Training loss: 82.7016 Explore P: 0.8678
Episode: 930 Total reward: 10.0 Training loss: 165.0646 Explore P: 0.8678
Episode: 931 Total reward: 61.0 Training loss: 53.9629 Explore P: 0.8677
Episode: 932 Total reward: 26.0 Training loss: 0.6524 Explore P: 0.8676
Episode: 933 Total reward: 13.0 Training loss: 0.4382 Explore P: 0.8676
Episode: 934 Total reward: 24.0 Training loss: 195.3371 Explore P: 0.8675
Episode: 935 Total reward: 15.0 Training loss: 483.1305 Explore P: 0.8675
Episode: 936 Total reward: 14.0 Training loss: 391.3560 Explore P: 0.8675
Episode: 937 Total reward: 17.0 Training loss: 3.8151 Explore P: 0.8675
Episode: 938 Total reward: 13.0 Training loss: 0.6513 Explore P: 0.8674
Episode: 939 Total reward: 15.0 Training loss: 0.7877 Explore P: 0.8674
Episode: 940 Total reward: 42.0 Training loss: 58.3950 Explore P: 0.8673
Episode: 941 Total reward: 21.0 Training loss: 59.2467 Explore P: 0.8673
Episode: 942 Total reward: 13.0 Training loss: 12.9747 Explore P: 0.8673
Episode: 943 Total reward: 42.0 Training loss: 571.2751 Explore P: 0.8672
Episode: 944 Total reward: 11.0 Training loss: 98.7200 Explore P: 0.8672
Episode: 945 Total reward: 18.0 Training loss: 76.8376 Explore P: 0.8672
Episode: 946 Total reward: 16.0 Training loss: 91.9570 Explore P: 0.8671
Episode: 947 Total reward: 17.0 Training loss: 8.0970 Explore P: 0.8671
Episode: 948 Total reward: 11.0 Training loss: 1.4146 Explore P: 0.8671
Episode: 949 Total reward: 9.0 Training loss: 10.3098 Explore P: 0.8671
Episode: 950 Total reward: 16.0 Training loss: 9.4432 Explore P: 0.8671
Episode: 951 Total reward: 12.0 Training loss: 1.1276 Explore P: 0.8670
Episode: 952 Total reward: 12.0 Training loss: 27.7444 Explore P: 0.8670
Episode: 953 Total reward: 9.0 Training loss: 0.3916 Explore P: 0.8670
Episode: 954 Total reward: 17.0 Training loss: 30.0691 Explore P: 0.8670
Episode: 955 Total reward: 10.0 Training loss: 124.2943 Explore P: 0.8669
Episode: 956 Total reward: 21.0 Training loss: 39.5326 Explore P: 0.8669
Episode: 957 Total reward: 11.0 Training loss: 3.6330 Explore P: 0.8669
Episode: 958 Total reward: 10.0 Training loss: 327.0910 Explore P: 0.8669
Episode: 959 Total reward: 10.0 Training loss: 98.5786 Explore P: 0.8669
Episode: 960 Total reward: 20.0 Training loss: 53.9721 Explore P: 0.8668
Episode: 961 Total reward: 9.0 Training loss: 124.9466 Explore P: 0.8668
Episode: 962 Total reward: 10.0 Training loss: 1.2004 Explore P: 0.8668
Episode: 963 Total reward: 19.0 Training loss: 78.2959 Explore P: 0.8668
Episode: 964 Total reward: 23.0 Training loss: 103.4348 Explore P: 0.8667
Episode: 965 Total reward: 13.0 Training loss: 5.9452 Explore P: 0.8667
Episode: 966 Total reward: 17.0 Training loss: 152.6158 Explore P: 0.8667
Episode: 967 Total reward: 13.0 Training loss: 197.9980 Explore P: 0.8666
Episode: 968 Total reward: 15.0 Training loss: 161.1636 Explore P: 0.8666
Episode: 969 Total reward: 13.0 Training loss: 31.2520 Explore P: 0.8666
Episode: 970 Total reward: 11.0 Training loss: 62.5622 Explore P: 0.8666
Episode: 971 Total reward: 16.0 Training loss: 12.2510 Explore P: 0.8666
Episode: 972 Total reward: 23.0 Training loss: 0.9798 Explore P: 0.8665
Episode: 973 Total reward: 36.0 Training loss: 1.8572 Explore P: 0.8665
Episode: 974 Total reward: 10.0 Training loss: 9.2899 Explore P: 0.8664
Episode: 975 Total reward: 13.0 Training loss: 484.9580 Explore P: 0.8664
Episode: 976 Total reward: 20.0 Training loss: 1.7671 Explore P: 0.8664
Episode: 977 Total reward: 13.0 Training loss: 1.5215 Explore P: 0.8664
Episode: 978 Total reward: 12.0 Training loss: 121.8538 Explore P: 0.8663
Episode: 979 Total reward: 55.0 Training loss: 1.0524 Explore P: 0.8662
Episode: 980 Total reward: 32.0 Training loss: 44.8162 Explore P: 0.8662
Episode: 981 Total reward: 17.0 Training loss: 0.6821 Explore P: 0.8662
Episode: 982 Total reward: 34.0 Training loss: 35.8631 Explore P: 0.8661
Episode: 983 Total reward: 12.0 Training loss: 167.9542 Explore P: 0.8661
Episode: 984 Total reward: 16.0 Training loss: 120.5470 Explore P: 0.8661
Episode: 985 Total reward: 25.0 Training loss: 5.9041 Explore P: 0.8660
Episode: 986 Total reward: 15.0 Training loss: 0.7043 Explore P: 0.8660
Episode: 987 Total reward: 20.0 Training loss: 38.2633 Explore P: 0.8659
Episode: 988 Total reward: 22.0 Training loss: 1.7328 Explore P: 0.8659
Episode: 989 Total reward: 20.0 Training loss: 22.3459 Explore P: 0.8659
Episode: 990 Total reward: 22.0 Training loss: 39.9502 Explore P: 0.8658
Episode: 991 Total reward: 20.0 Training loss: 32.2512 Explore P: 0.8658
Episode: 992 Total reward: 18.0 Training loss: 1.3736 Explore P: 0.8658
Episode: 993 Total reward: 17.0 Training loss: 43.5016 Explore P: 0.8657
Episode: 994 Total reward: 7.0 Training loss: 2.8078 Explore P: 0.8657
Episode: 995 Total reward: 14.0 Training loss: 4.4453 Explore P: 0.8657
Episode: 996 Total reward: 19.0 Training loss: 12.0091 Explore P: 0.8657
Episode: 997 Total reward: 16.0 Training loss: 828.6116 Explore P: 0.8656
Episode: 998 Total reward: 8.0 Training loss: 3.3303 Explore P: 0.8656
Episode: 999 Total reward: 9.0 Training loss: 4.3334 Explore P: 0.8656
Episode: 1000 Total reward: 20.0 Training loss: 149.0203 Explore P: 0.8656
Episode: 1001 Total reward: 13.0 Training loss: 242.9936 Explore P: 0.8656
Episode: 1002 Total reward: 16.0 Training loss: 39.6663 Explore P: 0.8655
Episode: 1003 Total reward: 19.0 Training loss: 48.4496 Explore P: 0.8655
Episode: 1004 Total reward: 16.0 Training loss: 27.8306 Explore P: 0.8655
Episode: 1005 Total reward: 8.0 Training loss: 0.7244 Explore P: 0.8655
Episode: 1006 Total reward: 30.0 Training loss: 259.5843 Explore P: 0.8654
Episode: 1007 Total reward: 24.0 Training loss: 18.7198 Explore P: 0.8654
Episode: 1008 Total reward: 8.0 Training loss: 88.8950 Explore P: 0.8654
Episode: 1009 Total reward: 20.0 Training loss: 6.7423 Explore P: 0.8653
Episode: 1010 Total reward: 35.0 Training loss: 18.6298 Explore P: 0.8653
Episode: 1011 Total reward: 16.0 Training loss: 34.2709 Explore P: 0.8652
Episode: 1012 Total reward: 55.0 Training loss: 66.0041 Explore P: 0.8651
Episode: 1013 Total reward: 15.0 Training loss: 0.6895 Explore P: 0.8651
Episode: 1014 Total reward: 16.0 Training loss: 64.2612 Explore P: 0.8651
Episode: 1015 Total reward: 12.0 Training loss: 54.2994 Explore P: 0.8651
Episode: 1016 Total reward: 16.0 Training loss: 1.0006 Explore P: 0.8650
Episode: 1017 Total reward: 45.0 Training loss: 880.6622 Explore P: 0.8650
Episode: 1018 Total reward: 15.0 Training loss: 485.5296 Explore P: 0.8649
Episode: 1019 Total reward: 13.0 Training loss: 96.6988 Explore P: 0.8649
Episode: 1020 Total reward: 27.0 Training loss: 18.9052 Explore P: 0.8649
Episode: 1021 Total reward: 21.0 Training loss: 37.1608 Explore P: 0.8648
Episode: 1022 Total reward: 21.0 Training loss: 70.7373 Explore P: 0.8648
Episode: 1023 Total reward: 13.0 Training loss: 10.1999 Explore P: 0.8648
Episode: 1024 Total reward: 10.0 Training loss: 29.3048 Explore P: 0.8648
Episode: 1025 Total reward: 15.0 Training loss: 43.6142 Explore P: 0.8647
Episode: 1026 Total reward: 16.0 Training loss: 94.2779 Explore P: 0.8647
Episode: 1027 Total reward: 14.0 Training loss: 8.7830 Explore P: 0.8647
Episode: 1028 Total reward: 20.0 Training loss: 448.7372 Explore P: 0.8646
Episode: 1029 Total reward: 10.0 Training loss: 88.1143 Explore P: 0.8646
Episode: 1030 Total reward: 19.0 Training loss: 0.9048 Explore P: 0.8646
Episode: 1031 Total reward: 10.0 Training loss: 67.3392 Explore P: 0.8646
Episode: 1032 Total reward: 20.0 Training loss: 0.9820 Explore P: 0.8645
Episode: 1033 Total reward: 15.0 Training loss: 56.3960 Explore P: 0.8645
Episode: 1034 Total reward: 27.0 Training loss: 23.2483 Explore P: 0.8645
Episode: 1035 Total reward: 19.0 Training loss: 202.2029 Explore P: 0.8644
Episode: 1036 Total reward: 15.0 Training loss: 26.6172 Explore P: 0.8644
Episode: 1037 Total reward: 22.0 Training loss: 2.0733 Explore P: 0.8644
Episode: 1038 Total reward: 16.0 Training loss: 13.3513 Explore P: 0.8644
Episode: 1039 Total reward: 35.0 Training loss: 0.3478 Explore P: 0.8643
Episode: 1040 Total reward: 11.0 Training loss: 13.0964 Explore P: 0.8643
Episode: 1041 Total reward: 10.0 Training loss: 1.9482 Explore P: 0.8643
Episode: 1042 Total reward: 15.0 Training loss: 4.8057 Explore P: 0.8642
Episode: 1043 Total reward: 27.0 Training loss: 0.6974 Explore P: 0.8642
Episode: 1044 Total reward: 19.0 Training loss: 0.8460 Explore P: 0.8642
Episode: 1045 Total reward: 17.0 Training loss: 0.7009 Explore P: 0.8641
Episode: 1046 Total reward: 18.0 Training loss: 55.3609 Explore P: 0.8641
Episode: 1047 Total reward: 13.0 Training loss: 50.6880 Explore P: 0.8641
Episode: 1048 Total reward: 40.0 Training loss: 26.9630 Explore P: 0.8640
Episode: 1049 Total reward: 8.0 Training loss: 17.7888 Explore P: 0.8640
Episode: 1050 Total reward: 21.0 Training loss: 79.0243 Explore P: 0.8640
Episode: 1051 Total reward: 14.0 Training loss: 24.5809 Explore P: 0.8639
Episode: 1052 Total reward: 25.0 Training loss: 135.8655 Explore P: 0.8639
Episode: 1053 Total reward: 16.0 Training loss: 522.8463 Explore P: 0.8639
Episode: 1054 Total reward: 24.0 Training loss: 32.8187 Explore P: 0.8638
Episode: 1055 Total reward: 24.0 Training loss: 1.3007 Explore P: 0.8638
Episode: 1056 Total reward: 26.0 Training loss: 0.6584 Explore P: 0.8637
Episode: 1057 Total reward: 10.0 Training loss: 11.3529 Explore P: 0.8637
Episode: 1058 Total reward: 11.0 Training loss: 110.7684 Explore P: 0.8637
Episode: 1059 Total reward: 13.0 Training loss: 0.3326 Explore P: 0.8637
Episode: 1060 Total reward: 32.0 Training loss: 16.1873 Explore P: 0.8636
Episode: 1061 Total reward: 25.0 Training loss: 272.5909 Explore P: 0.8636
Episode: 1062 Total reward: 12.0 Training loss: 221.3753 Explore P: 0.8636
Episode: 1063 Total reward: 9.0 Training loss: 70.3665 Explore P: 0.8635
Episode: 1064 Total reward: 12.0 Training loss: 239.9044 Explore P: 0.8635
Episode: 1065 Total reward: 26.0 Training loss: 330.1533 Explore P: 0.8635
Episode: 1066 Total reward: 17.0 Training loss: 20.9069 Explore P: 0.8634
Episode: 1067 Total reward: 10.0 Training loss: 159.3775 Explore P: 0.8634
Episode: 1068 Total reward: 11.0 Training loss: 222.2307 Explore P: 0.8634
Episode: 1069 Total reward: 10.0 Training loss: 22.2060 Explore P: 0.8634
Episode: 1070 Total reward: 15.0 Training loss: 32.7508 Explore P: 0.8634
Episode: 1071 Total reward: 14.0 Training loss: 112.0443 Explore P: 0.8633
Episode: 1072 Total reward: 20.0 Training loss: 83.7535 Explore P: 0.8633
Episode: 1073 Total reward: 14.0 Training loss: 91.9406 Explore P: 0.8633
Episode: 1074 Total reward: 18.0 Training loss: 0.7020 Explore P: 0.8633
Episode: 1075 Total reward: 25.0 Training loss: 2.6268 Explore P: 0.8632
Episode: 1076 Total reward: 22.0 Training loss: 32.3065 Explore P: 0.8632
Episode: 1077 Total reward: 14.0 Training loss: 1.5998 Explore P: 0.8632
Episode: 1078 Total reward: 15.0 Training loss: 148.7352 Explore P: 0.8631
Episode: 1079 Total reward: 21.0 Training loss: 1.7483 Explore P: 0.8631
Episode: 1080 Total reward: 8.0 Training loss: 128.6562 Explore P: 0.8631
Episode: 1081 Total reward: 10.0 Training loss: 330.6219 Explore P: 0.8631
Episode: 1082 Total reward: 10.0 Training loss: 29.0238 Explore P: 0.8630
Episode: 1083 Total reward: 22.0 Training loss: 1.1466 Explore P: 0.8630
Episode: 1084 Total reward: 23.0 Training loss: 14.7792 Explore P: 0.8630
Episode: 1085 Total reward: 37.0 Training loss: 1.4712 Explore P: 0.8629
Episode: 1086 Total reward: 12.0 Training loss: 1.5231 Explore P: 0.8629
Episode: 1087 Total reward: 18.0 Training loss: 1561.3081 Explore P: 0.8628
Episode: 1088 Total reward: 19.0 Training loss: 149.2739 Explore P: 0.8628
Episode: 1089 Total reward: 10.0 Training loss: 81.1016 Explore P: 0.8628
Episode: 1090 Total reward: 8.0 Training loss: 0.6186 Explore P: 0.8628
Episode: 1091 Total reward: 10.0 Training loss: 14.5699 Explore P: 0.8628
Episode: 1092 Total reward: 10.0 Training loss: 0.6636 Explore P: 0.8628
Episode: 1093 Total reward: 35.0 Training loss: 17.1928 Explore P: 0.8627
Episode: 1094 Total reward: 10.0 Training loss: 15.0307 Explore P: 0.8627
Episode: 1095 Total reward: 13.0 Training loss: 67.2443 Explore P: 0.8627
Episode: 1096 Total reward: 8.0 Training loss: 0.8293 Explore P: 0.8626
Episode: 1097 Total reward: 22.0 Training loss: 78.6992 Explore P: 0.8626
Episode: 1098 Total reward: 13.0 Training loss: 244.9372 Explore P: 0.8626
Episode: 1099 Total reward: 20.0 Training loss: 84.3728 Explore P: 0.8625
Episode: 1100 Total reward: 17.0 Training loss: 59.8489 Explore P: 0.8625
Episode: 1101 Total reward: 14.0 Training loss: 146.7916 Explore P: 0.8625
Episode: 1102 Total reward: 12.0 Training loss: 0.8124 Explore P: 0.8625
Episode: 1103 Total reward: 29.0 Training loss: 25.9568 Explore P: 0.8624
Episode: 1104 Total reward: 30.0 Training loss: 2043.8829 Explore P: 0.8624
Episode: 1105 Total reward: 9.0 Training loss: 1.4210 Explore P: 0.8624
Episode: 1106 Total reward: 12.0 Training loss: 11.5727 Explore P: 0.8623
Episode: 1107 Total reward: 18.0 Training loss: 115.7102 Explore P: 0.8623
Episode: 1108 Total reward: 18.0 Training loss: 35.1896 Explore P: 0.8623
Episode: 1109 Total reward: 28.0 Training loss: 61.5485 Explore P: 0.8622
Episode: 1110 Total reward: 13.0 Training loss: 3.4400 Explore P: 0.8622
Episode: 1111 Total reward: 35.0 Training loss: 194.3743 Explore P: 0.8621
Episode: 1112 Total reward: 12.0 Training loss: 66.4255 Explore P: 0.8621
Episode: 1113 Total reward: 21.0 Training loss: 138.3519 Explore P: 0.8621
Episode: 1114 Total reward: 13.0 Training loss: 1.4803 Explore P: 0.8621
Episode: 1115 Total reward: 14.0 Training loss: 5.6077 Explore P: 0.8620
Episode: 1116 Total reward: 8.0 Training loss: 36.1652 Explore P: 0.8620
Episode: 1117 Total reward: 9.0 Training loss: 13.9861 Explore P: 0.8620
Episode: 1118 Total reward: 50.0 Training loss: 49.5371 Explore P: 0.8619
Episode: 1119 Total reward: 9.0 Training loss: 22.2845 Explore P: 0.8619
Episode: 1120 Total reward: 14.0 Training loss: 1.6362 Explore P: 0.8619
Episode: 1121 Total reward: 26.0 Training loss: 59.9263 Explore P: 0.8618
Episode: 1122 Total reward: 20.0 Training loss: 32.3116 Explore P: 0.8618
Episode: 1123 Total reward: 11.0 Training loss: 190.2613 Explore P: 0.8618
Episode: 1124 Total reward: 30.0 Training loss: 77.3302 Explore P: 0.8617
Episode: 1125 Total reward: 17.0 Training loss: 60.5439 Explore P: 0.8617
Episode: 1126 Total reward: 15.0 Training loss: 2.3195 Explore P: 0.8617
Episode: 1127 Total reward: 25.0 Training loss: 12.8901 Explore P: 0.8616
Episode: 1128 Total reward: 20.0 Training loss: 75.0747 Explore P: 0.8616
Episode: 1129 Total reward: 9.0 Training loss: 1.1710 Explore P: 0.8616
Episode: 1130 Total reward: 12.0 Training loss: 1.4494 Explore P: 0.8616
Episode: 1131 Total reward: 9.0 Training loss: 1730.6224 Explore P: 0.8616
Episode: 1132 Total reward: 11.0 Training loss: 206.5483 Explore P: 0.8615
Episode: 1133 Total reward: 15.0 Training loss: 1.1732 Explore P: 0.8615
Episode: 1134 Total reward: 18.0 Training loss: 14.3311 Explore P: 0.8615
Episode: 1135 Total reward: 18.0 Training loss: 6.9552 Explore P: 0.8615
Episode: 1136 Total reward: 9.0 Training loss: 73.0393 Explore P: 0.8614
Episode: 1137 Total reward: 17.0 Training loss: 1.2127 Explore P: 0.8614
Episode: 1138 Total reward: 12.0 Training loss: 92.0641 Explore P: 0.8614
Episode: 1139 Total reward: 16.0 Training loss: 0.3935 Explore P: 0.8614
Episode: 1140 Total reward: 16.0 Training loss: 80.3715 Explore P: 0.8613
Episode: 1141 Total reward: 13.0 Training loss: 80.5781 Explore P: 0.8613
Episode: 1142 Total reward: 12.0 Training loss: 24.2634 Explore P: 0.8613
Episode: 1143 Total reward: 9.0 Training loss: 6.5516 Explore P: 0.8613
Episode: 1144 Total reward: 12.0 Training loss: 8.5232 Explore P: 0.8613
Episode: 1145 Total reward: 15.0 Training loss: 24.2217 Explore P: 0.8612
Episode: 1146 Total reward: 9.0 Training loss: 8.8703 Explore P: 0.8612
Episode: 1147 Total reward: 21.0 Training loss: 1.3032 Explore P: 0.8612
Episode: 1148 Total reward: 18.0 Training loss: 1.2387 Explore P: 0.8611
Episode: 1149 Total reward: 15.0 Training loss: 0.6839 Explore P: 0.8611
Episode: 1150 Total reward: 22.0 Training loss: 0.7082 Explore P: 0.8611
Episode: 1151 Total reward: 17.0 Training loss: 27.2439 Explore P: 0.8611
Episode: 1152 Total reward: 18.0 Training loss: 1.9045 Explore P: 0.8610
Episode: 1153 Total reward: 10.0 Training loss: 3.4157 Explore P: 0.8610
Episode: 1154 Total reward: 28.0 Training loss: 211.2260 Explore P: 0.8610
Episode: 1155 Total reward: 12.0 Training loss: 0.6298 Explore P: 0.8609
Episode: 1156 Total reward: 12.0 Training loss: 1658.0641 Explore P: 0.8609
Episode: 1157 Total reward: 17.0 Training loss: 46.2694 Explore P: 0.8609
Episode: 1158 Total reward: 14.0 Training loss: 30.9341 Explore P: 0.8609
Episode: 1159 Total reward: 9.0 Training loss: 2.1883 Explore P: 0.8609
Episode: 1160 Total reward: 34.0 Training loss: 3.2066 Explore P: 0.8608
Episode: 1161 Total reward: 11.0 Training loss: 5.5075 Explore P: 0.8608
Episode: 1162 Total reward: 13.0 Training loss: 10.8271 Explore P: 0.8608
Episode: 1163 Total reward: 13.0 Training loss: 446.9505 Explore P: 0.8607
Episode: 1164 Total reward: 10.0 Training loss: 0.8316 Explore P: 0.8607
Episode: 1165 Total reward: 15.0 Training loss: 16.8221 Explore P: 0.8607
Episode: 1166 Total reward: 16.0 Training loss: 56.2611 Explore P: 0.8607
Episode: 1167 Total reward: 47.0 Training loss: 48.0637 Explore P: 0.8606
Episode: 1168 Total reward: 10.0 Training loss: 30.7616 Explore P: 0.8606
Episode: 1169 Total reward: 13.0 Training loss: 24.5482 Explore P: 0.8605
Episode: 1170 Total reward: 14.0 Training loss: 70.6244 Explore P: 0.8605
Episode: 1171 Total reward: 27.0 Training loss: 141.8067 Explore P: 0.8605
Episode: 1172 Total reward: 11.0 Training loss: 75.9390 Explore P: 0.8605
Episode: 1173 Total reward: 13.0 Training loss: 0.9033 Explore P: 0.8604
Episode: 1174 Total reward: 15.0 Training loss: 131.3541 Explore P: 0.8604
Episode: 1175 Total reward: 21.0 Training loss: 61.5482 Explore P: 0.8604
Episode: 1176 Total reward: 14.0 Training loss: 37.7317 Explore P: 0.8603
Episode: 1177 Total reward: 23.0 Training loss: 111.7249 Explore P: 0.8603
Episode: 1178 Total reward: 15.0 Training loss: 3.9848 Explore P: 0.8603
Episode: 1179 Total reward: 17.0 Training loss: 124.9603 Explore P: 0.8603
Episode: 1180 Total reward: 13.0 Training loss: 376.6940 Explore P: 0.8602
Episode: 1181 Total reward: 14.0 Training loss: 1.4579 Explore P: 0.8602
Episode: 1182 Total reward: 17.0 Training loss: 55.0123 Explore P: 0.8602
Episode: 1183 Total reward: 16.0 Training loss: 1.2546 Explore P: 0.8602
Episode: 1184 Total reward: 18.0 Training loss: 39.5461 Explore P: 0.8601
Episode: 1185 Total reward: 82.0 Training loss: 19.5840 Explore P: 0.8600
Episode: 1186 Total reward: 12.0 Training loss: 152.3882 Explore P: 0.8600
Episode: 1187 Total reward: 21.0 Training loss: 0.4155 Explore P: 0.8599
Episode: 1188 Total reward: 15.0 Training loss: 105.7349 Explore P: 0.8599
Episode: 1189 Total reward: 8.0 Training loss: 7.6973 Explore P: 0.8599
Episode: 1190 Total reward: 16.0 Training loss: 102.1322 Explore P: 0.8599
Episode: 1191 Total reward: 9.0 Training loss: 9.2112 Explore P: 0.8598
Episode: 1192 Total reward: 26.0 Training loss: 106.3115 Explore P: 0.8598
Episode: 1193 Total reward: 9.0 Training loss: 5.1786 Explore P: 0.8598
Episode: 1194 Total reward: 37.0 Training loss: 0.6489 Explore P: 0.8597
Episode: 1195 Total reward: 16.0 Training loss: 2.6552 Explore P: 0.8597
Episode: 1196 Total reward: 22.0 Training loss: 60.4466 Explore P: 0.8597
Episode: 1197 Total reward: 16.0 Training loss: 71.2098 Explore P: 0.8596
Episode: 1198 Total reward: 16.0 Training loss: 5.4045 Explore P: 0.8596
Episode: 1199 Total reward: 18.0 Training loss: 39.9832 Explore P: 0.8596
Episode: 1200 Total reward: 15.0 Training loss: 3.4010 Explore P: 0.8595
Episode: 1201 Total reward: 32.0 Training loss: 88.2401 Explore P: 0.8595
Episode: 1202 Total reward: 13.0 Training loss: 20.1414 Explore P: 0.8595
Episode: 1203 Total reward: 9.0 Training loss: 1434.2767 Explore P: 0.8595
Episode: 1204 Total reward: 14.0 Training loss: 73.3728 Explore P: 0.8594
Episode: 1205 Total reward: 65.0 Training loss: 1.3824 Explore P: 0.8593
Episode: 1206 Total reward: 16.0 Training loss: 2.8171 Explore P: 0.8593
Episode: 1207 Total reward: 19.0 Training loss: 56.7401 Explore P: 0.8593
Episode: 1208 Total reward: 20.0 Training loss: 3.2093 Explore P: 0.8592
Episode: 1209 Total reward: 20.0 Training loss: 34.1503 Explore P: 0.8592
Episode: 1210 Total reward: 11.0 Training loss: 64.7938 Explore P: 0.8592
Episode: 1211 Total reward: 14.0 Training loss: 0.8829 Explore P: 0.8592
Episode: 1212 Total reward: 12.0 Training loss: 0.2867 Explore P: 0.8591
Episode: 1213 Total reward: 15.0 Training loss: 251.2783 Explore P: 0.8591
Episode: 1214 Total reward: 18.0 Training loss: 64.3507 Explore P: 0.8591
Episode: 1215 Total reward: 54.0 Training loss: 1.3003 Explore P: 0.8590
Episode: 1216 Total reward: 57.0 Training loss: 65.8682 Explore P: 0.8589
Episode: 1217 Total reward: 10.0 Training loss: 21.4664 Explore P: 0.8589
Episode: 1218 Total reward: 16.0 Training loss: 1.2447 Explore P: 0.8588
Episode: 1219 Total reward: 34.0 Training loss: 23.4533 Explore P: 0.8588
Episode: 1220 Total reward: 34.0 Training loss: 141.6346 Explore P: 0.8587
Episode: 1221 Total reward: 17.0 Training loss: 41.7676 Explore P: 0.8587
Episode: 1222 Total reward: 8.0 Training loss: 1.4490 Explore P: 0.8587
Episode: 1223 Total reward: 14.0 Training loss: 91.2478 Explore P: 0.8587
Episode: 1224 Total reward: 22.0 Training loss: 0.3907 Explore P: 0.8586
Episode: 1225 Total reward: 17.0 Training loss: 12.2829 Explore P: 0.8586
Episode: 1226 Total reward: 32.0 Training loss: 36.7827 Explore P: 0.8585
Episode: 1227 Total reward: 13.0 Training loss: 80.9706 Explore P: 0.8585
Episode: 1228 Total reward: 15.0 Training loss: 86.0594 Explore P: 0.8585
Episode: 1229 Total reward: 27.0 Training loss: 94.0301 Explore P: 0.8584
Episode: 1230 Total reward: 10.0 Training loss: 35.1042 Explore P: 0.8584
Episode: 1231 Total reward: 23.0 Training loss: 83.0868 Explore P: 0.8584
Episode: 1232 Total reward: 11.0 Training loss: 269.4339 Explore P: 0.8584
Episode: 1233 Total reward: 16.0 Training loss: 53.8730 Explore P: 0.8583
Episode: 1234 Total reward: 9.0 Training loss: 2.5001 Explore P: 0.8583
Episode: 1235 Total reward: 19.0 Training loss: 2.8019 Explore P: 0.8583
Episode: 1236 Total reward: 16.0 Training loss: 248.9938 Explore P: 0.8583
Episode: 1237 Total reward: 17.0 Training loss: 166.1120 Explore P: 0.8582
Episode: 1238 Total reward: 10.0 Training loss: 0.7545 Explore P: 0.8582
Episode: 1239 Total reward: 11.0 Training loss: 0.6658 Explore P: 0.8582
Episode: 1240 Total reward: 16.0 Training loss: 5.5684 Explore P: 0.8582
Episode: 1241 Total reward: 15.0 Training loss: 24.6783 Explore P: 0.8582
Episode: 1242 Total reward: 13.0 Training loss: 8.6809 Explore P: 0.8581
Episode: 1243 Total reward: 14.0 Training loss: 17.5472 Explore P: 0.8581
Episode: 1244 Total reward: 12.0 Training loss: 28.0575 Explore P: 0.8581
Episode: 1245 Total reward: 38.0 Training loss: 366.5919 Explore P: 0.8580
Episode: 1246 Total reward: 17.0 Training loss: 1.1952 Explore P: 0.8580
Episode: 1247 Total reward: 10.0 Training loss: 0.5434 Explore P: 0.8580
Episode: 1248 Total reward: 12.0 Training loss: 0.6540 Explore P: 0.8580
Episode: 1249 Total reward: 10.0 Training loss: 0.4648 Explore P: 0.8579
Episode: 1250 Total reward: 11.0 Training loss: 120.1035 Explore P: 0.8579
Episode: 1251 Total reward: 11.0 Training loss: 0.9904 Explore P: 0.8579
Episode: 1252 Total reward: 18.0 Training loss: 46.3699 Explore P: 0.8579
Episode: 1253 Total reward: 10.0 Training loss: 71.1886 Explore P: 0.8579
Episode: 1254 Total reward: 18.0 Training loss: 5.5928 Explore P: 0.8578
Episode: 1255 Total reward: 12.0 Training loss: 18.2734 Explore P: 0.8578
Episode: 1256 Total reward: 8.0 Training loss: 0.7894 Explore P: 0.8578
Episode: 1257 Total reward: 54.0 Training loss: 62.5027 Explore P: 0.8577
Episode: 1258 Total reward: 11.0 Training loss: 14.7507 Explore P: 0.8577
Episode: 1259 Total reward: 9.0 Training loss: 236.0306 Explore P: 0.8577
Episode: 1260 Total reward: 11.0 Training loss: 220.7000 Explore P: 0.8576
Episode: 1261 Total reward: 40.0 Training loss: 18.1699 Explore P: 0.8576
Episode: 1262 Total reward: 35.0 Training loss: 11.8063 Explore P: 0.8575
Episode: 1263 Total reward: 20.0 Training loss: 28.9219 Explore P: 0.8575
Episode: 1264 Total reward: 15.0 Training loss: 31.3480 Explore P: 0.8575
Episode: 1265 Total reward: 10.0 Training loss: 39.2332 Explore P: 0.8574
Episode: 1266 Total reward: 18.0 Training loss: 2.2371 Explore P: 0.8574
Episode: 1267 Total reward: 10.0 Training loss: 10.1290 Explore P: 0.8574
Episode: 1268 Total reward: 26.0 Training loss: 205.0921 Explore P: 0.8574
Episode: 1269 Total reward: 18.0 Training loss: 1.3707 Explore P: 0.8573
Episode: 1270 Total reward: 21.0 Training loss: 455.4078 Explore P: 0.8573
Episode: 1271 Total reward: 17.0 Training loss: 119.7544 Explore P: 0.8573
Episode: 1272 Total reward: 24.0 Training loss: 17.4261 Explore P: 0.8572
Episode: 1273 Total reward: 16.0 Training loss: 170.4865 Explore P: 0.8572
Episode: 1274 Total reward: 20.0 Training loss: 18.9549 Explore P: 0.8572
Episode: 1275 Total reward: 19.0 Training loss: 0.7552 Explore P: 0.8571
Episode: 1276 Total reward: 15.0 Training loss: 93.9869 Explore P: 0.8571
Episode: 1277 Total reward: 57.0 Training loss: 526.9294 Explore P: 0.8570
Episode: 1278 Total reward: 13.0 Training loss: 0.3669 Explore P: 0.8570
Episode: 1279 Total reward: 19.0 Training loss: 22.1111 Explore P: 0.8569
Episode: 1280 Total reward: 12.0 Training loss: 0.3545 Explore P: 0.8569
Episode: 1281 Total reward: 9.0 Training loss: 77.7767 Explore P: 0.8569
Episode: 1282 Total reward: 16.0 Training loss: 53.8722 Explore P: 0.8569
Episode: 1283 Total reward: 19.0 Training loss: 150.4598 Explore P: 0.8569
Episode: 1284 Total reward: 53.0 Training loss: 57.5277 Explore P: 0.8568
Episode: 1285 Total reward: 12.0 Training loss: 0.3813 Explore P: 0.8567
Episode: 1286 Total reward: 17.0 Training loss: 0.5062 Explore P: 0.8567
Episode: 1287 Total reward: 33.0 Training loss: 77.7610 Explore P: 0.8567
Episode: 1288 Total reward: 10.0 Training loss: 39.2920 Explore P: 0.8566
Episode: 1289 Total reward: 16.0 Training loss: 25.4784 Explore P: 0.8566
Episode: 1290 Total reward: 11.0 Training loss: 398.0323 Explore P: 0.8566
Episode: 1291 Total reward: 26.0 Training loss: 4.6629 Explore P: 0.8566
Episode: 1292 Total reward: 16.0 Training loss: 153.9001 Explore P: 0.8565
Episode: 1293 Total reward: 20.0 Training loss: 0.3528 Explore P: 0.8565
Episode: 1294 Total reward: 17.0 Training loss: 20.0037 Explore P: 0.8565
Episode: 1295 Total reward: 39.0 Training loss: 0.2744 Explore P: 0.8564
Episode: 1296 Total reward: 14.0 Training loss: 2.1989 Explore P: 0.8564
Episode: 1297 Total reward: 12.0 Training loss: 0.4957 Explore P: 0.8564
Episode: 1298 Total reward: 25.0 Training loss: 47.3826 Explore P: 0.8563
Episode: 1299 Total reward: 17.0 Training loss: 8.8213 Explore P: 0.8563
Episode: 1300 Total reward: 16.0 Training loss: 38.2982 Explore P: 0.8563
Episode: 1301 Total reward: 26.0 Training loss: 87.6133 Explore P: 0.8562
Episode: 1302 Total reward: 11.0 Training loss: 28.6648 Explore P: 0.8562
Episode: 1303 Total reward: 9.0 Training loss: 1.5138 Explore P: 0.8562
Episode: 1304 Total reward: 18.0 Training loss: 359.2305 Explore P: 0.8561
Episode: 1305 Total reward: 12.0 Training loss: 75.4904 Explore P: 0.8561
Episode: 1306 Total reward: 34.0 Training loss: 0.7709 Explore P: 0.8561
Episode: 1307 Total reward: 10.0 Training loss: 128.3052 Explore P: 0.8560
Episode: 1308 Total reward: 19.0 Training loss: 3.1082 Explore P: 0.8560
Episode: 1309 Total reward: 21.0 Training loss: 45.2088 Explore P: 0.8560
Episode: 1310 Total reward: 16.0 Training loss: 76.4169 Explore P: 0.8560
Episode: 1311 Total reward: 22.0 Training loss: 2.0957 Explore P: 0.8559
Episode: 1312 Total reward: 13.0 Training loss: 20.6805 Explore P: 0.8559
Episode: 1313 Total reward: 8.0 Training loss: 22.3062 Explore P: 0.8559
Episode: 1314 Total reward: 14.0 Training loss: 42.9747 Explore P: 0.8559
Episode: 1315 Total reward: 21.0 Training loss: 111.0733 Explore P: 0.8558
Episode: 1316 Total reward: 18.0 Training loss: 8.0345 Explore P: 0.8558
Episode: 1317 Total reward: 13.0 Training loss: 242.7442 Explore P: 0.8558
Episode: 1318 Total reward: 17.0 Training loss: 180.7040 Explore P: 0.8557
Episode: 1319 Total reward: 15.0 Training loss: 0.5599 Explore P: 0.8557
Episode: 1320 Total reward: 29.0 Training loss: 258.6678 Explore P: 0.8557
Episode: 1321 Total reward: 15.0 Training loss: 2.7427 Explore P: 0.8556
Episode: 1322 Total reward: 14.0 Training loss: 59.3747 Explore P: 0.8556
Episode: 1323 Total reward: 14.0 Training loss: 24.0203 Explore P: 0.8556
Episode: 1324 Total reward: 9.0 Training loss: 104.7786 Explore P: 0.8556
Episode: 1325 Total reward: 15.0 Training loss: 23.1507 Explore P: 0.8556
Episode: 1326 Total reward: 32.0 Training loss: 142.8242 Explore P: 0.8555
Episode: 1327 Total reward: 63.0 Training loss: 11.8394 Explore P: 0.8554
Episode: 1328 Total reward: 11.0 Training loss: 763.0668 Explore P: 0.8554
Episode: 1329 Total reward: 29.0 Training loss: 0.7339 Explore P: 0.8553
Episode: 1330 Total reward: 13.0 Training loss: 46.5375 Explore P: 0.8553
Episode: 1331 Total reward: 56.0 Training loss: 159.9045 Explore P: 0.8552
Episode: 1332 Total reward: 16.0 Training loss: 350.5565 Explore P: 0.8552
Episode: 1333 Total reward: 43.0 Training loss: 588.7885 Explore P: 0.8551
Episode: 1334 Total reward: 19.0 Training loss: 2.4736 Explore P: 0.8551
Episode: 1335 Total reward: 13.0 Training loss: 118.8556 Explore P: 0.8551
Episode: 1336 Total reward: 15.0 Training loss: 82.8522 Explore P: 0.8550
Episode: 1337 Total reward: 13.0 Training loss: 46.3868 Explore P: 0.8550
Episode: 1338 Total reward: 14.0 Training loss: 37.7548 Explore P: 0.8550
Episode: 1339 Total reward: 22.0 Training loss: 0.5503 Explore P: 0.8549
Episode: 1340 Total reward: 11.0 Training loss: 65.9091 Explore P: 0.8549
Episode: 1341 Total reward: 11.0 Training loss: 42.3030 Explore P: 0.8549
Episode: 1342 Total reward: 33.0 Training loss: 0.5937 Explore P: 0.8549
Episode: 1343 Total reward: 18.0 Training loss: 5.0274 Explore P: 0.8548
Episode: 1344 Total reward: 15.0 Training loss: 80.6605 Explore P: 0.8548
Episode: 1345 Total reward: 10.0 Training loss: 1.1543 Explore P: 0.8548
Episode: 1346 Total reward: 9.0 Training loss: 40.7426 Explore P: 0.8548
Episode: 1347 Total reward: 16.0 Training loss: 3.3454 Explore P: 0.8547
Episode: 1348 Total reward: 23.0 Training loss: 19.7646 Explore P: 0.8547
Episode: 1349 Total reward: 11.0 Training loss: 10.2888 Explore P: 0.8547
Episode: 1350 Total reward: 21.0 Training loss: 3.7646 Explore P: 0.8546
Episode: 1351 Total reward: 10.0 Training loss: 62.3556 Explore P: 0.8546
Episode: 1352 Total reward: 64.0 Training loss: 13.7090 Explore P: 0.8545
Episode: 1353 Total reward: 12.0 Training loss: 10.5719 Explore P: 0.8545
Episode: 1354 Total reward: 22.0 Training loss: 88.4840 Explore P: 0.8545
Episode: 1355 Total reward: 14.0 Training loss: 239.9965 Explore P: 0.8544
Episode: 1356 Total reward: 8.0 Training loss: 21.4568 Explore P: 0.8544
Episode: 1357 Total reward: 8.0 Training loss: 14.3533 Explore P: 0.8544
Episode: 1358 Total reward: 17.0 Training loss: 24.1525 Explore P: 0.8544
Episode: 1359 Total reward: 9.0 Training loss: 14.3757 Explore P: 0.8544
Episode: 1360 Total reward: 16.0 Training loss: 2.8385 Explore P: 0.8543
Episode: 1361 Total reward: 19.0 Training loss: 60.1208 Explore P: 0.8543
Episode: 1362 Total reward: 14.0 Training loss: 2.3039 Explore P: 0.8543
Episode: 1363 Total reward: 17.0 Training loss: 91.7804 Explore P: 0.8543
Episode: 1364 Total reward: 11.0 Training loss: 538.8853 Explore P: 0.8542
Episode: 1365 Total reward: 15.0 Training loss: 0.8258 Explore P: 0.8542
Episode: 1366 Total reward: 16.0 Training loss: 1.8170 Explore P: 0.8542
Episode: 1367 Total reward: 8.0 Training loss: 8.5761 Explore P: 0.8542
Episode: 1368 Total reward: 21.0 Training loss: 85.0230 Explore P: 0.8541
Episode: 1369 Total reward: 29.0 Training loss: 0.5900 Explore P: 0.8541
Episode: 1370 Total reward: 27.0 Training loss: 18.6764 Explore P: 0.8540
Episode: 1371 Total reward: 17.0 Training loss: 597.8807 Explore P: 0.8540
Episode: 1372 Total reward: 22.0 Training loss: 2.3255 Explore P: 0.8540
Episode: 1373 Total reward: 37.0 Training loss: 333.0883 Explore P: 0.8539
Episode: 1374 Total reward: 32.0 Training loss: 16.7042 Explore P: 0.8539
Episode: 1375 Total reward: 10.0 Training loss: 126.6569 Explore P: 0.8538
Episode: 1376 Total reward: 11.0 Training loss: 100.5999 Explore P: 0.8538
Episode: 1377 Total reward: 18.0 Training loss: 0.6255 Explore P: 0.8538
Episode: 1378 Total reward: 13.0 Training loss: 0.3468 Explore P: 0.8538
Episode: 1379 Total reward: 21.0 Training loss: 0.3987 Explore P: 0.8537
Episode: 1380 Total reward: 14.0 Training loss: 0.8790 Explore P: 0.8537
Episode: 1381 Total reward: 11.0 Training loss: 27.0921 Explore P: 0.8537
Episode: 1382 Total reward: 18.0 Training loss: 28.4854 Explore P: 0.8537
Episode: 1383 Total reward: 10.0 Training loss: 0.9644 Explore P: 0.8536
Episode: 1384 Total reward: 13.0 Training loss: 316.1596 Explore P: 0.8536
Episode: 1385 Total reward: 15.0 Training loss: 187.4357 Explore P: 0.8536
Episode: 1386 Total reward: 13.0 Training loss: 136.5900 Explore P: 0.8536
Episode: 1387 Total reward: 22.0 Training loss: 43.0479 Explore P: 0.8535
Episode: 1388 Total reward: 14.0 Training loss: 1.0742 Explore P: 0.8535
Episode: 1389 Total reward: 33.0 Training loss: 78.4620 Explore P: 0.8535
Episode: 1390 Total reward: 23.0 Training loss: 3.1446 Explore P: 0.8534
Episode: 1391 Total reward: 21.0 Training loss: 41.0204 Explore P: 0.8534
Episode: 1392 Total reward: 15.0 Training loss: 1.0554 Explore P: 0.8534
Episode: 1393 Total reward: 16.0 Training loss: 0.6149 Explore P: 0.8533
Episode: 1394 Total reward: 22.0 Training loss: 0.7311 Explore P: 0.8533
Episode: 1395 Total reward: 17.0 Training loss: 0.8454 Explore P: 0.8533
Episode: 1396 Total reward: 18.0 Training loss: 245.8980 Explore P: 0.8532
Episode: 1397 Total reward: 10.0 Training loss: 34.8512 Explore P: 0.8532
Episode: 1398 Total reward: 15.0 Training loss: 5.1760 Explore P: 0.8532
Episode: 1399 Total reward: 19.0 Training loss: 0.8621 Explore P: 0.8532
Episode: 1400 Total reward: 44.0 Training loss: 223.8586 Explore P: 0.8531
Episode: 1401 Total reward: 17.0 Training loss: 0.8626 Explore P: 0.8531
Episode: 1402 Total reward: 10.0 Training loss: 1.0958 Explore P: 0.8530
Episode: 1403 Total reward: 12.0 Training loss: 100.3622 Explore P: 0.8530
Episode: 1404 Total reward: 11.0 Training loss: 8.6644 Explore P: 0.8530
Episode: 1405 Total reward: 17.0 Training loss: 85.8953 Explore P: 0.8530
Episode: 1406 Total reward: 24.0 Training loss: 338.4204 Explore P: 0.8529
Episode: 1407 Total reward: 11.0 Training loss: 70.5827 Explore P: 0.8529
Episode: 1408 Total reward: 15.0 Training loss: 0.8458 Explore P: 0.8529
Episode: 1409 Total reward: 20.0 Training loss: 11.9258 Explore P: 0.8529
Episode: 1410 Total reward: 15.0 Training loss: 53.0292 Explore P: 0.8528
Episode: 1411 Total reward: 23.0 Training loss: 29.0846 Explore P: 0.8528
Episode: 1412 Total reward: 29.0 Training loss: 0.5801 Explore P: 0.8527
Episode: 1413 Total reward: 12.0 Training loss: 161.2972 Explore P: 0.8527
Episode: 1414 Total reward: 12.0 Training loss: 81.9655 Explore P: 0.8527
Episode: 1415 Total reward: 28.0 Training loss: 2.1995 Explore P: 0.8527
Episode: 1416 Total reward: 13.0 Training loss: 74.4669 Explore P: 0.8526
Episode: 1417 Total reward: 26.0 Training loss: 83.2997 Explore P: 0.8526
Episode: 1418 Total reward: 19.0 Training loss: 42.9657 Explore P: 0.8526
Episode: 1419 Total reward: 20.0 Training loss: 6.7425 Explore P: 0.8525
Episode: 1420 Total reward: 18.0 Training loss: 3.4153 Explore P: 0.8525
Episode: 1421 Total reward: 13.0 Training loss: 0.3019 Explore P: 0.8525
Episode: 1422 Total reward: 19.0 Training loss: 0.8328 Explore P: 0.8524
Episode: 1423 Total reward: 22.0 Training loss: 10.0706 Explore P: 0.8524
Episode: 1424 Total reward: 11.0 Training loss: 132.1068 Explore P: 0.8524
Episode: 1425 Total reward: 24.0 Training loss: 238.9674 Explore P: 0.8523
Episode: 1426 Total reward: 10.0 Training loss: 180.2352 Explore P: 0.8523
Episode: 1427 Total reward: 12.0 Training loss: 2.7980 Explore P: 0.8523
Episode: 1428 Total reward: 17.0 Training loss: 6.7646 Explore P: 0.8523
Episode: 1429 Total reward: 19.0 Training loss: 183.1075 Explore P: 0.8523
Episode: 1430 Total reward: 46.0 Training loss: 232.3355 Explore P: 0.8522
Episode: 1431 Total reward: 12.0 Training loss: 0.6492 Explore P: 0.8522
Episode: 1432 Total reward: 39.0 Training loss: 138.7361 Explore P: 0.8521
Episode: 1433 Total reward: 14.0 Training loss: 0.9683 Explore P: 0.8521
Episode: 1434 Total reward: 23.0 Training loss: 159.9323 Explore P: 0.8520
Episode: 1435 Total reward: 10.0 Training loss: 25.1151 Explore P: 0.8520
Episode: 1436 Total reward: 10.0 Training loss: 25.3224 Explore P: 0.8520
Episode: 1437 Total reward: 12.0 Training loss: 15.0338 Explore P: 0.8520
Episode: 1438 Total reward: 9.0 Training loss: 0.6022 Explore P: 0.8520
Episode: 1439 Total reward: 21.0 Training loss: 0.1912 Explore P: 0.8519
Episode: 1440 Total reward: 39.0 Training loss: 68.3780 Explore P: 0.8519
Episode: 1441 Total reward: 15.0 Training loss: 20.3755 Explore P: 0.8518
Episode: 1442 Total reward: 12.0 Training loss: 0.4399 Explore P: 0.8518
Episode: 1443 Total reward: 12.0 Training loss: 125.0693 Explore P: 0.8518
Episode: 1444 Total reward: 44.0 Training loss: 0.3951 Explore P: 0.8517
Episode: 1445 Total reward: 26.0 Training loss: 53.9916 Explore P: 0.8517
Episode: 1446 Total reward: 14.0 Training loss: 83.8515 Explore P: 0.8516
Episode: 1447 Total reward: 14.0 Training loss: 12.3837 Explore P: 0.8516
Episode: 1448 Total reward: 14.0 Training loss: 2.3184 Explore P: 0.8516
Episode: 1449 Total reward: 39.0 Training loss: 127.9484 Explore P: 0.8515
Episode: 1450 Total reward: 88.0 Training loss: 0.4809 Explore P: 0.8514
Episode: 1451 Total reward: 21.0 Training loss: 2.9346 Explore P: 0.8514
Episode: 1452 Total reward: 13.0 Training loss: 0.5480 Explore P: 0.8513
Episode: 1453 Total reward: 10.0 Training loss: 9.7682 Explore P: 0.8513
Episode: 1454 Total reward: 12.0 Training loss: 0.5963 Explore P: 0.8513
Episode: 1455 Total reward: 15.0 Training loss: 0.5599 Explore P: 0.8513
Episode: 1456 Total reward: 26.0 Training loss: 23.4673 Explore P: 0.8512
Episode: 1457 Total reward: 24.0 Training loss: 1.0778 Explore P: 0.8512
Episode: 1458 Total reward: 27.0 Training loss: 37.5760 Explore P: 0.8511
Episode: 1459 Total reward: 22.0 Training loss: 0.2679 Explore P: 0.8511
Episode: 1460 Total reward: 16.0 Training loss: 0.2613 Explore P: 0.8511
Episode: 1461 Total reward: 14.0 Training loss: 1.5302 Explore P: 0.8511
Episode: 1462 Total reward: 26.0 Training loss: 114.7149 Explore P: 0.8510
Episode: 1463 Total reward: 15.0 Training loss: 46.2111 Explore P: 0.8510
Episode: 1464 Total reward: 12.0 Training loss: 76.8221 Explore P: 0.8510
Episode: 1465 Total reward: 18.0 Training loss: 14.1465 Explore P: 0.8509
Episode: 1466 Total reward: 18.0 Training loss: 0.5651 Explore P: 0.8509
Episode: 1467 Total reward: 12.0 Training loss: 9.1791 Explore P: 0.8509
Episode: 1468 Total reward: 9.0 Training loss: 50.6530 Explore P: 0.8509
Episode: 1469 Total reward: 11.0 Training loss: 0.5016 Explore P: 0.8508
Episode: 1470 Total reward: 14.0 Training loss: 14.3831 Explore P: 0.8508
Episode: 1471 Total reward: 10.0 Training loss: 265.0599 Explore P: 0.8508
Episode: 1472 Total reward: 14.0 Training loss: 10.9830 Explore P: 0.8508
Episode: 1473 Total reward: 27.0 Training loss: 90.7514 Explore P: 0.8507
Episode: 1474 Total reward: 10.0 Training loss: 9.4366 Explore P: 0.8507
Episode: 1475 Total reward: 10.0 Training loss: 12.2007 Explore P: 0.8507
Episode: 1476 Total reward: 20.0 Training loss: 38.6064 Explore P: 0.8507
Episode: 1477 Total reward: 34.0 Training loss: 29.0668 Explore P: 0.8506
Episode: 1478 Total reward: 11.0 Training loss: 21.7834 Explore P: 0.8506
Episode: 1479 Total reward: 17.0 Training loss: 107.7909 Explore P: 0.8506
Episode: 1480 Total reward: 12.0 Training loss: 183.2960 Explore P: 0.8505
Episode: 1481 Total reward: 15.0 Training loss: 110.8928 Explore P: 0.8505
Episode: 1482 Total reward: 29.0 Training loss: 28.1840 Explore P: 0.8505
Episode: 1483 Total reward: 21.0 Training loss: 3.4063 Explore P: 0.8504
Episode: 1484 Total reward: 14.0 Training loss: 23.2258 Explore P: 0.8504
Episode: 1485 Total reward: 14.0 Training loss: 0.3001 Explore P: 0.8504
Episode: 1486 Total reward: 12.0 Training loss: 0.5278 Explore P: 0.8504
Episode: 1487 Total reward: 13.0 Training loss: 0.4694 Explore P: 0.8503
Episode: 1488 Total reward: 19.0 Training loss: 252.3925 Explore P: 0.8503
Episode: 1489 Total reward: 14.0 Training loss: 0.8227 Explore P: 0.8503
Episode: 1490 Total reward: 15.0 Training loss: 14.0679 Explore P: 0.8503
Episode: 1491 Total reward: 15.0 Training loss: 4.0991 Explore P: 0.8502
Episode: 1492 Total reward: 10.0 Training loss: 0.4285 Explore P: 0.8502
Episode: 1493 Total reward: 39.0 Training loss: 1.3329 Explore P: 0.8502
Episode: 1494 Total reward: 17.0 Training loss: 0.7252 Explore P: 0.8501
Episode: 1495 Total reward: 17.0 Training loss: 291.8201 Explore P: 0.8501
Episode: 1496 Total reward: 13.0 Training loss: 0.2553 Explore P: 0.8501
Episode: 1497 Total reward: 20.0 Training loss: 152.0466 Explore P: 0.8500
Episode: 1498 Total reward: 22.0 Training loss: 4.6196 Explore P: 0.8500
Episode: 1499 Total reward: 12.0 Training loss: 214.1653 Explore P: 0.8500
Episode: 1500 Total reward: 35.0 Training loss: 161.0020 Explore P: 0.8499
Episode: 1501 Total reward: 18.0 Training loss: 49.8050 Explore P: 0.8499
Episode: 1502 Total reward: 14.0 Training loss: 21.6473 Explore P: 0.8499
Episode: 1503 Total reward: 36.0 Training loss: 271.9687 Explore P: 0.8498
Episode: 1504 Total reward: 18.0 Training loss: 57.8712 Explore P: 0.8498
Episode: 1505 Total reward: 75.0 Training loss: 66.8623 Explore P: 0.8497
Episode: 1506 Total reward: 21.0 Training loss: 21.3313 Explore P: 0.8496
Episode: 1507 Total reward: 23.0 Training loss: 0.3941 Explore P: 0.8496
Episode: 1508 Total reward: 77.0 Training loss: 2.9160 Explore P: 0.8495
Episode: 1509 Total reward: 23.0 Training loss: 0.3584 Explore P: 0.8494
Episode: 1510 Total reward: 8.0 Training loss: 0.5890 Explore P: 0.8494
Episode: 1511 Total reward: 16.0 Training loss: 5.2191 Explore P: 0.8494
Episode: 1512 Total reward: 10.0 Training loss: 7.3623 Explore P: 0.8494
Episode: 1513 Total reward: 25.0 Training loss: 19.0184 Explore P: 0.8493
Episode: 1514 Total reward: 38.0 Training loss: 49.8647 Explore P: 0.8493
Episode: 1515 Total reward: 11.0 Training loss: 1.3198 Explore P: 0.8492
Episode: 1516 Total reward: 23.0 Training loss: 0.3135 Explore P: 0.8492
Episode: 1517 Total reward: 14.0 Training loss: 365.8937 Explore P: 0.8492
Episode: 1518 Total reward: 14.0 Training loss: 44.1261 Explore P: 0.8492
Episode: 1519 Total reward: 12.0 Training loss: 148.7922 Explore P: 0.8491
Episode: 1520 Total reward: 39.0 Training loss: 6.9505 Explore P: 0.8491
Episode: 1521 Total reward: 25.0 Training loss: 83.2204 Explore P: 0.8490
Episode: 1522 Total reward: 14.0 Training loss: 18.7210 Explore P: 0.8490
Episode: 1523 Total reward: 22.0 Training loss: 92.8298 Explore P: 0.8490
Episode: 1524 Total reward: 25.0 Training loss: 34.5161 Explore P: 0.8489
Episode: 1525 Total reward: 20.0 Training loss: 92.6501 Explore P: 0.8489
Episode: 1526 Total reward: 14.0 Training loss: 0.4353 Explore P: 0.8489
Episode: 1527 Total reward: 11.0 Training loss: 255.7188 Explore P: 0.8488
Episode: 1528 Total reward: 18.0 Training loss: 160.0725 Explore P: 0.8488
Episode: 1529 Total reward: 15.0 Training loss: 0.9416 Explore P: 0.8488
Episode: 1530 Total reward: 29.0 Training loss: 59.6473 Explore P: 0.8487
Episode: 1531 Total reward: 25.0 Training loss: 55.9463 Explore P: 0.8487
Episode: 1532 Total reward: 26.0 Training loss: 3.1398 Explore P: 0.8487
Episode: 1533 Total reward: 42.0 Training loss: 0.3716 Explore P: 0.8486
Episode: 1534 Total reward: 12.0 Training loss: 14.3426 Explore P: 0.8486
Episode: 1535 Total reward: 28.0 Training loss: 2.8966 Explore P: 0.8485
Episode: 1536 Total reward: 21.0 Training loss: 0.4164 Explore P: 0.8485
Episode: 1537 Total reward: 25.0 Training loss: 11.1799 Explore P: 0.8484
Episode: 1538 Total reward: 23.0 Training loss: 4.2013 Explore P: 0.8484
Episode: 1539 Total reward: 13.0 Training loss: 240.0740 Explore P: 0.8484
Episode: 1540 Total reward: 12.0 Training loss: 1.0018 Explore P: 0.8484
Episode: 1541 Total reward: 33.0 Training loss: 51.9272 Explore P: 0.8483
Episode: 1542 Total reward: 9.0 Training loss: 23.4759 Explore P: 0.8483
Episode: 1543 Total reward: 16.0 Training loss: 5.8943 Explore P: 0.8483
Episode: 1544 Total reward: 10.0 Training loss: 5.4989 Explore P: 0.8482
Episode: 1545 Total reward: 23.0 Training loss: 13.1978 Explore P: 0.8482
Episode: 1546 Total reward: 29.0 Training loss: 13.8592 Explore P: 0.8482
Episode: 1547 Total reward: 23.0 Training loss: 0.4306 Explore P: 0.8481
Episode: 1548 Total reward: 22.0 Training loss: 0.3882 Explore P: 0.8481
Episode: 1549 Total reward: 67.0 Training loss: 31.6975 Explore P: 0.8480
Episode: 1550 Total reward: 18.0 Training loss: 38.9140 Explore P: 0.8479
Episode: 1551 Total reward: 24.0 Training loss: 39.0417 Explore P: 0.8479
Episode: 1552 Total reward: 12.0 Training loss: 17.8781 Explore P: 0.8479
Episode: 1553 Total reward: 24.0 Training loss: 0.5355 Explore P: 0.8478
Episode: 1554 Total reward: 10.0 Training loss: 82.5895 Explore P: 0.8478
Episode: 1555 Total reward: 17.0 Training loss: 56.8944 Explore P: 0.8478
Episode: 1556 Total reward: 10.0 Training loss: 4.9739 Explore P: 0.8478
Episode: 1557 Total reward: 22.0 Training loss: 15.2737 Explore P: 0.8477
Episode: 1558 Total reward: 24.0 Training loss: 38.7641 Explore P: 0.8477
Episode: 1559 Total reward: 15.0 Training loss: 0.3064 Explore P: 0.8477
Episode: 1560 Total reward: 22.0 Training loss: 0.3315 Explore P: 0.8476
Episode: 1561 Total reward: 17.0 Training loss: 50.2766 Explore P: 0.8476
Episode: 1562 Total reward: 27.0 Training loss: 7.3169 Explore P: 0.8476
Episode: 1563 Total reward: 17.0 Training loss: 381.0888 Explore P: 0.8475
Episode: 1564 Total reward: 23.0 Training loss: 58.5792 Explore P: 0.8475
Episode: 1565 Total reward: 20.0 Training loss: 30.8476 Explore P: 0.8475
Episode: 1566 Total reward: 16.0 Training loss: 58.9570 Explore P: 0.8474
Episode: 1567 Total reward: 23.0 Training loss: 0.2287 Explore P: 0.8474
Episode: 1568 Total reward: 11.0 Training loss: 3.4175 Explore P: 0.8474
Episode: 1569 Total reward: 13.0 Training loss: 17.7385 Explore P: 0.8474
Episode: 1570 Total reward: 16.0 Training loss: 72.0412 Explore P: 0.8473
Episode: 1571 Total reward: 13.0 Training loss: 0.8407 Explore P: 0.8473
Episode: 1572 Total reward: 11.0 Training loss: 2.2643 Explore P: 0.8473
Episode: 1573 Total reward: 38.0 Training loss: 17.8570 Explore P: 0.8472
Episode: 1574 Total reward: 13.0 Training loss: 0.2999 Explore P: 0.8472
Episode: 1575 Total reward: 13.0 Training loss: 64.6170 Explore P: 0.8472
Episode: 1576 Total reward: 11.0 Training loss: 0.4676 Explore P: 0.8472
Episode: 1577 Total reward: 16.0 Training loss: 178.8111 Explore P: 0.8471
Episode: 1578 Total reward: 39.0 Training loss: 0.4214 Explore P: 0.8471
Episode: 1579 Total reward: 19.0 Training loss: 54.8125 Explore P: 0.8470
Episode: 1580 Total reward: 18.0 Training loss: 131.6946 Explore P: 0.8470
Episode: 1581 Total reward: 10.0 Training loss: 20.7736 Explore P: 0.8470
Episode: 1582 Total reward: 16.0 Training loss: 148.4650 Explore P: 0.8470
Episode: 1583 Total reward: 12.0 Training loss: 75.8148 Explore P: 0.8470
Episode: 1584 Total reward: 31.0 Training loss: 38.7492 Explore P: 0.8469
Episode: 1585 Total reward: 26.0 Training loss: 6.1866 Explore P: 0.8469
Episode: 1586 Total reward: 18.0 Training loss: 149.7228 Explore P: 0.8468
Episode: 1587 Total reward: 23.0 Training loss: 13.1566 Explore P: 0.8468
Episode: 1588 Total reward: 13.0 Training loss: 1.3031 Explore P: 0.8468
Episode: 1589 Total reward: 53.0 Training loss: 0.5702 Explore P: 0.8467
Episode: 1590 Total reward: 16.0 Training loss: 52.9560 Explore P: 0.8466
Episode: 1591 Total reward: 18.0 Training loss: 4.1715 Explore P: 0.8466
Episode: 1592 Total reward: 15.0 Training loss: 9.8629 Explore P: 0.8466
Episode: 1593 Total reward: 17.0 Training loss: 124.3441 Explore P: 0.8466
Episode: 1594 Total reward: 10.0 Training loss: 48.7737 Explore P: 0.8465
Episode: 1595 Total reward: 19.0 Training loss: 0.1618 Explore P: 0.8465
Episode: 1596 Total reward: 13.0 Training loss: 8.1532 Explore P: 0.8465
Episode: 1597 Total reward: 24.0 Training loss: 9.0774 Explore P: 0.8465
Episode: 1598 Total reward: 17.0 Training loss: 21.3515 Explore P: 0.8464
Episode: 1599 Total reward: 14.0 Training loss: 50.6606 Explore P: 0.8464
Episode: 1600 Total reward: 15.0 Training loss: 0.4074 Explore P: 0.8464
Episode: 1601 Total reward: 34.0 Training loss: 62.5675 Explore P: 0.8463
Episode: 1602 Total reward: 15.0 Training loss: 14.2236 Explore P: 0.8463
Episode: 1603 Total reward: 32.0 Training loss: 31.5191 Explore P: 0.8462
Episode: 1604 Total reward: 10.0 Training loss: 36.9709 Explore P: 0.8462
Episode: 1605 Total reward: 9.0 Training loss: 0.5441 Explore P: 0.8462
Episode: 1606 Total reward: 10.0 Training loss: 0.3405 Explore P: 0.8462
Episode: 1607 Total reward: 12.0 Training loss: 54.2809 Explore P: 0.8462
Episode: 1608 Total reward: 11.0 Training loss: 0.2555 Explore P: 0.8462
Episode: 1609 Total reward: 21.0 Training loss: 0.2926 Explore P: 0.8461
Episode: 1610 Total reward: 21.0 Training loss: 0.3994 Explore P: 0.8461
Episode: 1611 Total reward: 13.0 Training loss: 44.3414 Explore P: 0.8461
Episode: 1612 Total reward: 15.0 Training loss: 0.2780 Explore P: 0.8460
Episode: 1613 Total reward: 22.0 Training loss: 0.9120 Explore P: 0.8460
Episode: 1614 Total reward: 14.0 Training loss: 68.8803 Explore P: 0.8460
Episode: 1615 Total reward: 18.0 Training loss: 51.7365 Explore P: 0.8459
Episode: 1616 Total reward: 25.0 Training loss: 43.2783 Explore P: 0.8459
Episode: 1617 Total reward: 28.0 Training loss: 261.6901 Explore P: 0.8459
Episode: 1618 Total reward: 20.0 Training loss: 9.8847 Explore P: 0.8458
Episode: 1619 Total reward: 17.0 Training loss: 162.1758 Explore P: 0.8458
Episode: 1620 Total reward: 16.0 Training loss: 15.7666 Explore P: 0.8458
Episode: 1621 Total reward: 13.0 Training loss: 12.3761 Explore P: 0.8457
Episode: 1622 Total reward: 11.0 Training loss: 0.2714 Explore P: 0.8457
Episode: 1623 Total reward: 12.0 Training loss: 8.1128 Explore P: 0.8457
Episode: 1624 Total reward: 34.0 Training loss: 0.6548 Explore P: 0.8457
Episode: 1625 Total reward: 19.0 Training loss: 7.8058 Explore P: 0.8456
Episode: 1626 Total reward: 26.0 Training loss: 41.4233 Explore P: 0.8456
Episode: 1627 Total reward: 20.0 Training loss: 0.4456 Explore P: 0.8455
Episode: 1628 Total reward: 13.0 Training loss: 0.7119 Explore P: 0.8455
Episode: 1629 Total reward: 51.0 Training loss: 65.4348 Explore P: 0.8454
Episode: 1630 Total reward: 10.0 Training loss: 7.1154 Explore P: 0.8454
Episode: 1631 Total reward: 16.0 Training loss: 28.2758 Explore P: 0.8454
Episode: 1632 Total reward: 21.0 Training loss: 45.7075 Explore P: 0.8454
Episode: 1633 Total reward: 15.0 Training loss: 65.1720 Explore P: 0.8453
Episode: 1634 Total reward: 9.0 Training loss: 8.1307 Explore P: 0.8453
Episode: 1635 Total reward: 30.0 Training loss: 0.6793 Explore P: 0.8453
Episode: 1636 Total reward: 11.0 Training loss: 0.4364 Explore P: 0.8453
Episode: 1637 Total reward: 12.0 Training loss: 28.5590 Explore P: 0.8452
Episode: 1638 Total reward: 13.0 Training loss: 4.3047 Explore P: 0.8452
Episode: 1639 Total reward: 18.0 Training loss: 7.7336 Explore P: 0.8452
Episode: 1640 Total reward: 30.0 Training loss: 0.3643 Explore P: 0.8451
Episode: 1641 Total reward: 18.0 Training loss: 76.9867 Explore P: 0.8451
Episode: 1642 Total reward: 13.0 Training loss: 50.2407 Explore P: 0.8451
Episode: 1643 Total reward: 12.0 Training loss: 0.3066 Explore P: 0.8451
Episode: 1644 Total reward: 23.0 Training loss: 0.5176 Explore P: 0.8450
Episode: 1645 Total reward: 33.0 Training loss: 12.7861 Explore P: 0.8450
Episode: 1646 Total reward: 21.0 Training loss: 41.4141 Explore P: 0.8449
Episode: 1647 Total reward: 22.0 Training loss: 0.4276 Explore P: 0.8449
Episode: 1648 Total reward: 15.0 Training loss: 0.2275 Explore P: 0.8449
Episode: 1649 Total reward: 12.0 Training loss: 0.4492 Explore P: 0.8448
Episode: 1650 Total reward: 26.0 Training loss: 31.6384 Explore P: 0.8448
Episode: 1651 Total reward: 26.0 Training loss: 173.1135 Explore P: 0.8448
Episode: 1652 Total reward: 29.0 Training loss: 79.4713 Explore P: 0.8447
Episode: 1653 Total reward: 14.0 Training loss: 102.8719 Explore P: 0.8447
Episode: 1654 Total reward: 19.0 Training loss: 24.9234 Explore P: 0.8447
Episode: 1655 Total reward: 37.0 Training loss: 0.2094 Explore P: 0.8446
Episode: 1656 Total reward: 44.0 Training loss: 153.1243 Explore P: 0.8445
Episode: 1657 Total reward: 13.0 Training loss: 168.4324 Explore P: 0.8445
Episode: 1658 Total reward: 13.0 Training loss: 0.8829 Explore P: 0.8445
Episode: 1659 Total reward: 8.0 Training loss: 17.5952 Explore P: 0.8445
Episode: 1660 Total reward: 20.0 Training loss: 35.3239 Explore P: 0.8444
Episode: 1661 Total reward: 12.0 Training loss: 56.6834 Explore P: 0.8444
Episode: 1662 Total reward: 13.0 Training loss: 101.2176 Explore P: 0.8444
Episode: 1663 Total reward: 32.0 Training loss: 0.2811 Explore P: 0.8443
Episode: 1664 Total reward: 30.0 Training loss: 26.8616 Explore P: 0.8443
Episode: 1665 Total reward: 8.0 Training loss: 2.2289 Explore P: 0.8443
Episode: 1666 Total reward: 9.0 Training loss: 221.0055 Explore P: 0.8443
Episode: 1667 Total reward: 14.0 Training loss: 35.1130 Explore P: 0.8442
Episode: 1668 Total reward: 8.0 Training loss: 2.6395 Explore P: 0.8442
Episode: 1669 Total reward: 32.0 Training loss: 22.7563 Explore P: 0.8442
Episode: 1670 Total reward: 18.0 Training loss: 30.1491 Explore P: 0.8441
Episode: 1671 Total reward: 16.0 Training loss: 17.4358 Explore P: 0.8441
Episode: 1672 Total reward: 27.0 Training loss: 0.3152 Explore P: 0.8441
Episode: 1673 Total reward: 14.0 Training loss: 191.7091 Explore P: 0.8440
Episode: 1674 Total reward: 24.0 Training loss: 76.3256 Explore P: 0.8440
Episode: 1675 Total reward: 42.0 Training loss: 82.3724 Explore P: 0.8439
Episode: 1676 Total reward: 31.0 Training loss: 0.3540 Explore P: 0.8439
Episode: 1677 Total reward: 9.0 Training loss: 14.5634 Explore P: 0.8439
Episode: 1678 Total reward: 43.0 Training loss: 3.2421 Explore P: 0.8438
Episode: 1679 Total reward: 32.0 Training loss: 63.4616 Explore P: 0.8437
Episode: 1680 Total reward: 22.0 Training loss: 66.7922 Explore P: 0.8437
Episode: 1681 Total reward: 13.0 Training loss: 10.5259 Explore P: 0.8437
Episode: 1682 Total reward: 16.0 Training loss: 36.5462 Explore P: 0.8437
Episode: 1683 Total reward: 23.0 Training loss: 24.2960 Explore P: 0.8436
Episode: 1684 Total reward: 20.0 Training loss: 9.9089 Explore P: 0.8436
Episode: 1685 Total reward: 32.0 Training loss: 109.2089 Explore P: 0.8435
Episode: 1686 Total reward: 11.0 Training loss: 79.6771 Explore P: 0.8435
Episode: 1687 Total reward: 19.0 Training loss: 0.4571 Explore P: 0.8435
Episode: 1688 Total reward: 13.0 Training loss: 0.5347 Explore P: 0.8435
Episode: 1689 Total reward: 16.0 Training loss: 0.6911 Explore P: 0.8434
Episode: 1690 Total reward: 9.0 Training loss: 94.8914 Explore P: 0.8434
Episode: 1691 Total reward: 24.0 Training loss: 0.4376 Explore P: 0.8434
Episode: 1692 Total reward: 18.0 Training loss: 18.3450 Explore P: 0.8433
Episode: 1693 Total reward: 22.0 Training loss: 29.4743 Explore P: 0.8433
Episode: 1694 Total reward: 15.0 Training loss: 15.8033 Explore P: 0.8433
Episode: 1695 Total reward: 14.0 Training loss: 7.9196 Explore P: 0.8433
Episode: 1696 Total reward: 23.0 Training loss: 0.1695 Explore P: 0.8432
Episode: 1697 Total reward: 13.0 Training loss: 0.4021 Explore P: 0.8432
Episode: 1698 Total reward: 27.0 Training loss: 11.9491 Explore P: 0.8432
Episode: 1699 Total reward: 16.0 Training loss: 16.3354 Explore P: 0.8431
Episode: 1700 Total reward: 11.0 Training loss: 0.3878 Explore P: 0.8431
Episode: 1701 Total reward: 15.0 Training loss: 144.7490 Explore P: 0.8431
Episode: 1702 Total reward: 12.0 Training loss: 95.5646 Explore P: 0.8431
Episode: 1703 Total reward: 14.0 Training loss: 0.7037 Explore P: 0.8430
Episode: 1704 Total reward: 38.0 Training loss: 12.5760 Explore P: 0.8430
Episode: 1705 Total reward: 19.0 Training loss: 19.9036 Explore P: 0.8429
Episode: 1706 Total reward: 19.0 Training loss: 120.3360 Explore P: 0.8429
Episode: 1707 Total reward: 8.0 Training loss: 12.2705 Explore P: 0.8429
Episode: 1708 Total reward: 29.0 Training loss: 1.6901 Explore P: 0.8429
Episode: 1709 Total reward: 16.0 Training loss: 211.4122 Explore P: 0.8428
Episode: 1710 Total reward: 10.0 Training loss: 17.4009 Explore P: 0.8428
Episode: 1711 Total reward: 13.0 Training loss: 0.6530 Explore P: 0.8428
Episode: 1712 Total reward: 19.0 Training loss: 107.4127 Explore P: 0.8428
Episode: 1713 Total reward: 29.0 Training loss: 14.2557 Explore P: 0.8427
Episode: 1714 Total reward: 15.0 Training loss: 88.5436 Explore P: 0.8427
Episode: 1715 Total reward: 9.0 Training loss: 0.1195 Explore P: 0.8427
Episode: 1716 Total reward: 18.0 Training loss: 8.5857 Explore P: 0.8426
Episode: 1717 Total reward: 30.0 Training loss: 95.0698 Explore P: 0.8426
Episode: 1718 Total reward: 20.0 Training loss: 23.8056 Explore P: 0.8426
Episode: 1719 Total reward: 17.0 Training loss: 188.5769 Explore P: 0.8425
Episode: 1720 Total reward: 55.0 Training loss: 19.4682 Explore P: 0.8424
Episode: 1721 Total reward: 18.0 Training loss: 0.7845 Explore P: 0.8424
Episode: 1722 Total reward: 10.0 Training loss: 40.6068 Explore P: 0.8424
Episode: 1723 Total reward: 15.0 Training loss: 22.9170 Explore P: 0.8424
Episode: 1724 Total reward: 19.0 Training loss: 0.6984 Explore P: 0.8423
Episode: 1725 Total reward: 10.0 Training loss: 4.6652 Explore P: 0.8423
Episode: 1726 Total reward: 10.0 Training loss: 0.8051 Explore P: 0.8423
Episode: 1727 Total reward: 31.0 Training loss: 8.9230 Explore P: 0.8423
Episode: 1728 Total reward: 15.0 Training loss: 1.1797 Explore P: 0.8422
Episode: 1729 Total reward: 14.0 Training loss: 17.3441 Explore P: 0.8422
Episode: 1730 Total reward: 15.0 Training loss: 0.2756 Explore P: 0.8422
Episode: 1731 Total reward: 20.0 Training loss: 69.9388 Explore P: 0.8421
Episode: 1732 Total reward: 37.0 Training loss: 2.8101 Explore P: 0.8421
Episode: 1733 Total reward: 11.0 Training loss: 24.3051 Explore P: 0.8421
Episode: 1734 Total reward: 12.0 Training loss: 0.3199 Explore P: 0.8420
Episode: 1735 Total reward: 14.0 Training loss: 2.9539 Explore P: 0.8420
Episode: 1736 Total reward: 22.0 Training loss: 148.7767 Explore P: 0.8420
Episode: 1737 Total reward: 41.0 Training loss: 262.9824 Explore P: 0.8419
Episode: 1738 Total reward: 14.0 Training loss: 7.2469 Explore P: 0.8419
Episode: 1739 Total reward: 25.0 Training loss: 76.8884 Explore P: 0.8419
Episode: 1740 Total reward: 12.0 Training loss: 13.7468 Explore P: 0.8418
Episode: 1741 Total reward: 26.0 Training loss: 47.8011 Explore P: 0.8418
Episode: 1742 Total reward: 47.0 Training loss: 18.8540 Explore P: 0.8417
Episode: 1743 Total reward: 17.0 Training loss: 65.2670 Explore P: 0.8417
Episode: 1744 Total reward: 41.0 Training loss: 101.6100 Explore P: 0.8416
Episode: 1745 Total reward: 22.0 Training loss: 0.2764 Explore P: 0.8416
Episode: 1746 Total reward: 11.0 Training loss: 36.8225 Explore P: 0.8416
Episode: 1747 Total reward: 12.0 Training loss: 84.6648 Explore P: 0.8415
Episode: 1748 Total reward: 9.0 Training loss: 124.1463 Explore P: 0.8415
Episode: 1749 Total reward: 17.0 Training loss: 0.5683 Explore P: 0.8415
Episode: 1750 Total reward: 27.0 Training loss: 89.2330 Explore P: 0.8415
Episode: 1751 Total reward: 15.0 Training loss: 0.8872 Explore P: 0.8414
Episode: 1752 Total reward: 38.0 Training loss: 55.7598 Explore P: 0.8414
Episode: 1753 Total reward: 12.0 Training loss: 5.4146 Explore P: 0.8413
Episode: 1754 Total reward: 29.0 Training loss: 22.5862 Explore P: 0.8413
Episode: 1755 Total reward: 27.0 Training loss: 137.3419 Explore P: 0.8412
Episode: 1756 Total reward: 22.0 Training loss: 279.9194 Explore P: 0.8412
Episode: 1757 Total reward: 15.0 Training loss: 10.8543 Explore P: 0.8412
Episode: 1758 Total reward: 25.0 Training loss: 92.0731 Explore P: 0.8411
Episode: 1759 Total reward: 11.0 Training loss: 45.8558 Explore P: 0.8411
Episode: 1760 Total reward: 7.0 Training loss: 201.1218 Explore P: 0.8411
Episode: 1761 Total reward: 23.0 Training loss: 92.1977 Explore P: 0.8411
Episode: 1762 Total reward: 18.0 Training loss: 0.1626 Explore P: 0.8410
Episode: 1763 Total reward: 18.0 Training loss: 11.8601 Explore P: 0.8410
Episode: 1764 Total reward: 11.0 Training loss: 40.5512 Explore P: 0.8410
Episode: 1765 Total reward: 16.0 Training loss: 0.5036 Explore P: 0.8410
Episode: 1766 Total reward: 27.0 Training loss: 5.8575 Explore P: 0.8409
Episode: 1767 Total reward: 16.0 Training loss: 50.3780 Explore P: 0.8409
Episode: 1768 Total reward: 16.0 Training loss: 2.8762 Explore P: 0.8409
Episode: 1769 Total reward: 12.0 Training loss: 0.3647 Explore P: 0.8409
Episode: 1770 Total reward: 19.0 Training loss: 15.7053 Explore P: 0.8408
Episode: 1771 Total reward: 20.0 Training loss: 18.6241 Explore P: 0.8408
Episode: 1772 Total reward: 23.0 Training loss: 35.1663 Explore P: 0.8408
Episode: 1773 Total reward: 26.0 Training loss: 113.8194 Explore P: 0.8407
Episode: 1774 Total reward: 10.0 Training loss: 78.9388 Explore P: 0.8407
Episode: 1775 Total reward: 40.0 Training loss: 30.3027 Explore P: 0.8406
Episode: 1776 Total reward: 25.0 Training loss: 0.8072 Explore P: 0.8406
Episode: 1777 Total reward: 19.0 Training loss: 54.6671 Explore P: 0.8406
Episode: 1778 Total reward: 30.0 Training loss: 0.3710 Explore P: 0.8405
Episode: 1779 Total reward: 24.0 Training loss: 43.6646 Explore P: 0.8405
Episode: 1780 Total reward: 21.0 Training loss: 0.5169 Explore P: 0.8404
Episode: 1781 Total reward: 37.0 Training loss: 21.3935 Explore P: 0.8404
Episode: 1782 Total reward: 11.0 Training loss: 25.9214 Explore P: 0.8403
Episode: 1783 Total reward: 8.0 Training loss: 2.2102 Explore P: 0.8403
Episode: 1784 Total reward: 43.0 Training loss: 0.4170 Explore P: 0.8403
Episode: 1785 Total reward: 12.0 Training loss: 129.3382 Explore P: 0.8402
Episode: 1786 Total reward: 14.0 Training loss: 0.6427 Explore P: 0.8402
Episode: 1787 Total reward: 23.0 Training loss: 104.7844 Explore P: 0.8402
Episode: 1788 Total reward: 19.0 Training loss: 72.5255 Explore P: 0.8402
Episode: 1789 Total reward: 19.0 Training loss: 50.7702 Explore P: 0.8401
Episode: 1790 Total reward: 18.0 Training loss: 22.0629 Explore P: 0.8401
Episode: 1791 Total reward: 23.0 Training loss: 1.2990 Explore P: 0.8401
Episode: 1792 Total reward: 10.0 Training loss: 22.8029 Explore P: 0.8400
Episode: 1793 Total reward: 27.0 Training loss: 4.2866 Explore P: 0.8400
Episode: 1794 Total reward: 8.0 Training loss: 56.3876 Explore P: 0.8400
Episode: 1795 Total reward: 12.0 Training loss: 4.5685 Explore P: 0.8400
Episode: 1796 Total reward: 11.0 Training loss: 52.2321 Explore P: 0.8399
Episode: 1797 Total reward: 15.0 Training loss: 3.9159 Explore P: 0.8399
Episode: 1798 Total reward: 13.0 Training loss: 75.1815 Explore P: 0.8399
Episode: 1799 Total reward: 54.0 Training loss: 1.0607 Explore P: 0.8398
Episode: 1800 Total reward: 9.0 Training loss: 251.6601 Explore P: 0.8398
Episode: 1801 Total reward: 19.0 Training loss: 0.2533 Explore P: 0.8398
Episode: 1802 Total reward: 29.0 Training loss: 0.4312 Explore P: 0.8397
Episode: 1803 Total reward: 14.0 Training loss: 2.5462 Explore P: 0.8397
Episode: 1804 Total reward: 13.0 Training loss: 696.2091 Explore P: 0.8397
Episode: 1805 Total reward: 23.0 Training loss: 8.2616 Explore P: 0.8396
Episode: 1806 Total reward: 19.0 Training loss: 1.5383 Explore P: 0.8396
Episode: 1807 Total reward: 27.0 Training loss: 25.7563 Explore P: 0.8395
Episode: 1808 Total reward: 58.0 Training loss: 84.2057 Explore P: 0.8395
Episode: 1809 Total reward: 14.0 Training loss: 10.8086 Explore P: 0.8394
Episode: 1810 Total reward: 10.0 Training loss: 1.3455 Explore P: 0.8394
Episode: 1811 Total reward: 15.0 Training loss: 26.8563 Explore P: 0.8394
Episode: 1812 Total reward: 16.0 Training loss: 20.7581 Explore P: 0.8394
Episode: 1813 Total reward: 29.0 Training loss: 171.1056 Explore P: 0.8393
Episode: 1814 Total reward: 26.0 Training loss: 0.3124 Explore P: 0.8393
Episode: 1815 Total reward: 11.0 Training loss: 0.2639 Explore P: 0.8393
Episode: 1816 Total reward: 19.0 Training loss: 2.1119 Explore P: 0.8392
Episode: 1817 Total reward: 11.0 Training loss: 78.8396 Explore P: 0.8392
Episode: 1818 Total reward: 11.0 Training loss: 33.1357 Explore P: 0.8392
Episode: 1819 Total reward: 27.0 Training loss: 1123.2087 Explore P: 0.8391
Episode: 1820 Total reward: 22.0 Training loss: 2.7890 Explore P: 0.8391
Episode: 1821 Total reward: 40.0 Training loss: 0.5822 Explore P: 0.8390
Episode: 1822 Total reward: 27.0 Training loss: 47.8757 Explore P: 0.8390
Episode: 1823 Total reward: 23.0 Training loss: 29.1185 Explore P: 0.8390
Episode: 1824 Total reward: 65.0 Training loss: 26.5032 Explore P: 0.8388
Episode: 1825 Total reward: 20.0 Training loss: 42.1638 Explore P: 0.8388
Episode: 1826 Total reward: 40.0 Training loss: 2.7934 Explore P: 0.8387
Episode: 1827 Total reward: 30.0 Training loss: 124.5308 Explore P: 0.8387
Episode: 1828 Total reward: 10.0 Training loss: 0.2694 Explore P: 0.8387
Episode: 1829 Total reward: 33.0 Training loss: 28.3449 Explore P: 0.8386
Episode: 1830 Total reward: 26.0 Training loss: 4.6378 Explore P: 0.8386
Episode: 1831 Total reward: 15.0 Training loss: 0.2198 Explore P: 0.8386
Episode: 1832 Total reward: 17.0 Training loss: 5.4826 Explore P: 0.8385
Episode: 1833 Total reward: 19.0 Training loss: 6.2520 Explore P: 0.8385
Episode: 1834 Total reward: 18.0 Training loss: 84.9594 Explore P: 0.8385
Episode: 1835 Total reward: 9.0 Training loss: 1.6896 Explore P: 0.8385
Episode: 1836 Total reward: 9.0 Training loss: 19.9522 Explore P: 0.8384
Episode: 1837 Total reward: 32.0 Training loss: 1.0139 Explore P: 0.8384
Episode: 1838 Total reward: 11.0 Training loss: 59.2516 Explore P: 0.8384
Episode: 1839 Total reward: 13.0 Training loss: 75.0917 Explore P: 0.8383
Episode: 1840 Total reward: 18.0 Training loss: 1.5615 Explore P: 0.8383
Episode: 1841 Total reward: 13.0 Training loss: 2.0549 Explore P: 0.8383
Episode: 1842 Total reward: 30.0 Training loss: 27.4210 Explore P: 0.8382
Episode: 1843 Total reward: 24.0 Training loss: 11.2203 Explore P: 0.8382
Episode: 1844 Total reward: 50.0 Training loss: 0.2914 Explore P: 0.8381
Episode: 1845 Total reward: 28.0 Training loss: 82.1981 Explore P: 0.8381
Episode: 1846 Total reward: 14.0 Training loss: 24.4120 Explore P: 0.8381
Episode: 1847 Total reward: 14.0 Training loss: 22.8713 Explore P: 0.8380
Episode: 1848 Total reward: 14.0 Training loss: 165.1102 Explore P: 0.8380
Episode: 1849 Total reward: 30.0 Training loss: 2.5278 Explore P: 0.8380
Episode: 1850 Total reward: 17.0 Training loss: 91.8844 Explore P: 0.8379
Episode: 1851 Total reward: 40.0 Training loss: 1.9507 Explore P: 0.8379
Episode: 1852 Total reward: 25.0 Training loss: 131.3742 Explore P: 0.8378
Episode: 1853 Total reward: 20.0 Training loss: 12.6383 Explore P: 0.8378
Episode: 1854 Total reward: 9.0 Training loss: 0.8826 Explore P: 0.8378
Episode: 1855 Total reward: 22.0 Training loss: 109.9785 Explore P: 0.8377
Episode: 1856 Total reward: 67.0 Training loss: 62.6141 Explore P: 0.8376
Episode: 1857 Total reward: 13.0 Training loss: 16.2944 Explore P: 0.8376
Episode: 1858 Total reward: 7.0 Training loss: 16.5278 Explore P: 0.8376
Episode: 1859 Total reward: 23.0 Training loss: 0.3095 Explore P: 0.8376
Episode: 1860 Total reward: 31.0 Training loss: 47.2919 Explore P: 0.8375
Episode: 1861 Total reward: 12.0 Training loss: 43.8811 Explore P: 0.8375
Episode: 1862 Total reward: 14.0 Training loss: 14.8936 Explore P: 0.8375
Episode: 1863 Total reward: 16.0 Training loss: 180.5855 Explore P: 0.8374
Episode: 1864 Total reward: 19.0 Training loss: 14.5179 Explore P: 0.8374
Episode: 1865 Total reward: 33.0 Training loss: 0.9388 Explore P: 0.8373
Episode: 1866 Total reward: 22.0 Training loss: 0.3309 Explore P: 0.8373
Episode: 1867 Total reward: 29.0 Training loss: 29.6374 Explore P: 0.8373
Episode: 1868 Total reward: 43.0 Training loss: 0.1218 Explore P: 0.8372
Episode: 1869 Total reward: 27.0 Training loss: 1.8999 Explore P: 0.8371
Episode: 1870 Total reward: 9.0 Training loss: 21.5663 Explore P: 0.8371
Episode: 1871 Total reward: 21.0 Training loss: 0.4228 Explore P: 0.8371
Episode: 1872 Total reward: 22.0 Training loss: 0.2321 Explore P: 0.8371
Episode: 1873 Total reward: 12.0 Training loss: 3.0041 Explore P: 0.8370
Episode: 1874 Total reward: 58.0 Training loss: 38.7738 Explore P: 0.8369
Episode: 1875 Total reward: 15.0 Training loss: 5.4011 Explore P: 0.8369
Episode: 1876 Total reward: 11.0 Training loss: 11.9144 Explore P: 0.8369
Episode: 1877 Total reward: 17.0 Training loss: 58.2679 Explore P: 0.8369
Episode: 1878 Total reward: 27.0 Training loss: 147.6437 Explore P: 0.8368
Episode: 1879 Total reward: 21.0 Training loss: 60.6561 Explore P: 0.8368
Episode: 1880 Total reward: 19.0 Training loss: 0.3445 Explore P: 0.8368
Episode: 1881 Total reward: 12.0 Training loss: 7.3381 Explore P: 0.8367
Episode: 1882 Total reward: 14.0 Training loss: 4.1383 Explore P: 0.8367
Episode: 1883 Total reward: 17.0 Training loss: 11.7346 Explore P: 0.8367
Episode: 1884 Total reward: 28.0 Training loss: 0.3093 Explore P: 0.8366
Episode: 1885 Total reward: 23.0 Training loss: 0.1478 Explore P: 0.8366
Episode: 1886 Total reward: 13.0 Training loss: 68.3662 Explore P: 0.8366
Episode: 1887 Total reward: 21.0 Training loss: 173.1798 Explore P: 0.8366
Episode: 1888 Total reward: 11.0 Training loss: 25.3202 Explore P: 0.8365
Episode: 1889 Total reward: 28.0 Training loss: 25.7568 Explore P: 0.8365
Episode: 1890 Total reward: 10.0 Training loss: 21.5695 Explore P: 0.8365
Episode: 1891 Total reward: 8.0 Training loss: 217.1860 Explore P: 0.8365
Episode: 1892 Total reward: 18.0 Training loss: 40.8747 Explore P: 0.8364
Episode: 1893 Total reward: 19.0 Training loss: 6.0903 Explore P: 0.8364
Episode: 1894 Total reward: 14.0 Training loss: 23.6014 Explore P: 0.8364
Episode: 1895 Total reward: 13.0 Training loss: 50.0854 Explore P: 0.8364
Episode: 1896 Total reward: 32.0 Training loss: 30.8889 Explore P: 0.8363
Episode: 1897 Total reward: 12.0 Training loss: 113.9115 Explore P: 0.8363
Episode: 1898 Total reward: 47.0 Training loss: 27.3846 Explore P: 0.8362
Episode: 1899 Total reward: 26.0 Training loss: 2.4263 Explore P: 0.8362
Episode: 1900 Total reward: 20.0 Training loss: 0.2275 Explore P: 0.8361
Episode: 1901 Total reward: 44.0 Training loss: 42.0200 Explore P: 0.8361
Episode: 1902 Total reward: 28.0 Training loss: 3.3359 Explore P: 0.8360
Episode: 1903 Total reward: 17.0 Training loss: 18.3916 Explore P: 0.8360
Episode: 1904 Total reward: 21.0 Training loss: 3.6125 Explore P: 0.8359
Episode: 1905 Total reward: 31.0 Training loss: 68.3210 Explore P: 0.8359
Episode: 1906 Total reward: 14.0 Training loss: 83.6855 Explore P: 0.8359
Episode: 1907 Total reward: 30.0 Training loss: 21.9444 Explore P: 0.8358
Episode: 1908 Total reward: 17.0 Training loss: 0.2144 Explore P: 0.8358
Episode: 1909 Total reward: 14.0 Training loss: 0.3170 Explore P: 0.8358
Episode: 1910 Total reward: 14.0 Training loss: 0.2819 Explore P: 0.8357
Episode: 1911 Total reward: 14.0 Training loss: 2.6047 Explore P: 0.8357
Episode: 1912 Total reward: 17.0 Training loss: 62.1211 Explore P: 0.8357
Episode: 1913 Total reward: 11.0 Training loss: 9.2189 Explore P: 0.8357
Episode: 1914 Total reward: 29.0 Training loss: 7.0241 Explore P: 0.8356
Episode: 1915 Total reward: 60.0 Training loss: 0.1854 Explore P: 0.8355
Episode: 1916 Total reward: 17.0 Training loss: 99.0713 Explore P: 0.8355
Episode: 1917 Total reward: 10.0 Training loss: 17.7510 Explore P: 0.8355
Episode: 1918 Total reward: 28.0 Training loss: 40.7380 Explore P: 0.8354
Episode: 1919 Total reward: 25.0 Training loss: 19.5144 Explore P: 0.8354
Episode: 1920 Total reward: 32.0 Training loss: 0.6122 Explore P: 0.8353
Episode: 1921 Total reward: 11.0 Training loss: 28.2335 Explore P: 0.8353
Episode: 1922 Total reward: 12.0 Training loss: 46.6274 Explore P: 0.8353
Episode: 1923 Total reward: 15.0 Training loss: 10.2183 Explore P: 0.8353
Episode: 1924 Total reward: 18.0 Training loss: 2.2439 Explore P: 0.8353
Episode: 1925 Total reward: 12.0 Training loss: 11.5733 Explore P: 0.8352
Episode: 1926 Total reward: 20.0 Training loss: 29.6595 Explore P: 0.8352
Episode: 1927 Total reward: 17.0 Training loss: 55.9112 Explore P: 0.8352
Episode: 1928 Total reward: 27.0 Training loss: 0.1489 Explore P: 0.8351
Episode: 1929 Total reward: 25.0 Training loss: 1.7834 Explore P: 0.8351
Episode: 1930 Total reward: 38.0 Training loss: 70.8651 Explore P: 0.8350
Episode: 1931 Total reward: 18.0 Training loss: 155.7203 Explore P: 0.8350
Episode: 1932 Total reward: 14.0 Training loss: 65.2150 Explore P: 0.8350
Episode: 1933 Total reward: 16.0 Training loss: 42.2573 Explore P: 0.8349
Episode: 1934 Total reward: 16.0 Training loss: 28.1530 Explore P: 0.8349
Episode: 1935 Total reward: 9.0 Training loss: 115.4218 Explore P: 0.8349
Episode: 1936 Total reward: 19.0 Training loss: 67.9335 Explore P: 0.8349
Episode: 1937 Total reward: 19.0 Training loss: 0.3027 Explore P: 0.8348
Episode: 1938 Total reward: 27.0 Training loss: 8.6209 Explore P: 0.8348
Episode: 1939 Total reward: 19.0 Training loss: 48.1734 Explore P: 0.8348
Episode: 1940 Total reward: 18.0 Training loss: 0.4528 Explore P: 0.8347
Episode: 1941 Total reward: 43.0 Training loss: 0.7011 Explore P: 0.8347
Episode: 1942 Total reward: 29.0 Training loss: 0.7656 Explore P: 0.8346
Episode: 1943 Total reward: 36.0 Training loss: 44.6392 Explore P: 0.8346
Episode: 1944 Total reward: 33.0 Training loss: 63.2559 Explore P: 0.8345
Episode: 1945 Total reward: 13.0 Training loss: 14.1568 Explore P: 0.8345
Episode: 1946 Total reward: 12.0 Training loss: 29.2909 Explore P: 0.8345
Episode: 1947 Total reward: 31.0 Training loss: 28.2678 Explore P: 0.8344
Episode: 1948 Total reward: 8.0 Training loss: 59.0136 Explore P: 0.8344
Episode: 1949 Total reward: 47.0 Training loss: 8.1716 Explore P: 0.8343
Episode: 1950 Total reward: 12.0 Training loss: 0.4211 Explore P: 0.8343
Episode: 1951 Total reward: 28.0 Training loss: 1.0031 Explore P: 0.8343
Episode: 1952 Total reward: 38.0 Training loss: 0.3402 Explore P: 0.8342
Episode: 1953 Total reward: 16.0 Training loss: 22.0030 Explore P: 0.8342
Episode: 1954 Total reward: 18.0 Training loss: 3.6476 Explore P: 0.8341
Episode: 1955 Total reward: 13.0 Training loss: 40.7424 Explore P: 0.8341
Episode: 1956 Total reward: 11.0 Training loss: 5.7679 Explore P: 0.8341
Episode: 1957 Total reward: 29.0 Training loss: 15.6563 Explore P: 0.8340
Episode: 1958 Total reward: 20.0 Training loss: 145.0466 Explore P: 0.8340
Episode: 1959 Total reward: 20.0 Training loss: 38.8798 Explore P: 0.8340
Episode: 1960 Total reward: 21.0 Training loss: 58.0890 Explore P: 0.8339
Episode: 1961 Total reward: 17.0 Training loss: 5.2254 Explore P: 0.8339
Episode: 1962 Total reward: 24.0 Training loss: 5.4717 Explore P: 0.8339
Episode: 1963 Total reward: 20.0 Training loss: 4.7160 Explore P: 0.8338
Episode: 1964 Total reward: 12.0 Training loss: 193.5934 Explore P: 0.8338
Episode: 1965 Total reward: 11.0 Training loss: 0.2887 Explore P: 0.8338
Episode: 1966 Total reward: 14.0 Training loss: 1.5293 Explore P: 0.8338
Episode: 1967 Total reward: 16.0 Training loss: 0.1323 Explore P: 0.8338
Episode: 1968 Total reward: 16.0 Training loss: 173.9671 Explore P: 0.8337
Episode: 1969 Total reward: 40.0 Training loss: 7.8233 Explore P: 0.8337
Episode: 1970 Total reward: 14.0 Training loss: 15.7091 Explore P: 0.8336
Episode: 1971 Total reward: 35.0 Training loss: 150.3453 Explore P: 0.8336
Episode: 1972 Total reward: 12.0 Training loss: 91.0317 Explore P: 0.8336
Episode: 1973 Total reward: 26.0 Training loss: 0.2168 Explore P: 0.8335
Episode: 1974 Total reward: 14.0 Training loss: 0.2641 Explore P: 0.8335
Episode: 1975 Total reward: 10.0 Training loss: 0.3985 Explore P: 0.8335
Episode: 1976 Total reward: 26.0 Training loss: 11.7638 Explore P: 0.8334
Episode: 1977 Total reward: 12.0 Training loss: 0.1904 Explore P: 0.8334
Episode: 1978 Total reward: 10.0 Training loss: 71.6919 Explore P: 0.8334
Episode: 1979 Total reward: 7.0 Training loss: 15.0600 Explore P: 0.8334
Episode: 1980 Total reward: 19.0 Training loss: 0.4475 Explore P: 0.8334
Episode: 1981 Total reward: 14.0 Training loss: 46.2413 Explore P: 0.8333
Episode: 1982 Total reward: 12.0 Training loss: 0.2924 Explore P: 0.8333
Episode: 1983 Total reward: 11.0 Training loss: 65.3592 Explore P: 0.8333
Episode: 1984 Total reward: 30.0 Training loss: 0.1958 Explore P: 0.8332
Episode: 1985 Total reward: 16.0 Training loss: 40.9860 Explore P: 0.8332
Episode: 1986 Total reward: 36.0 Training loss: 101.2750 Explore P: 0.8332
Episode: 1987 Total reward: 13.0 Training loss: 58.2216 Explore P: 0.8331
Episode: 1988 Total reward: 18.0 Training loss: 20.8417 Explore P: 0.8331
Episode: 1989 Total reward: 26.0 Training loss: 10.9922 Explore P: 0.8331
Episode: 1990 Total reward: 13.0 Training loss: 10.0640 Explore P: 0.8330
Episode: 1991 Total reward: 10.0 Training loss: 24.9986 Explore P: 0.8330
Episode: 1992 Total reward: 84.0 Training loss: 83.2652 Explore P: 0.8329
Episode: 1993 Total reward: 14.0 Training loss: 74.8886 Explore P: 0.8329
Episode: 1994 Total reward: 46.0 Training loss: 0.2257 Explore P: 0.8328
Episode: 1995 Total reward: 15.0 Training loss: 7.9199 Explore P: 0.8328
Episode: 1996 Total reward: 18.0 Training loss: 18.1415 Explore P: 0.8327
Episode: 1997 Total reward: 10.0 Training loss: 1.1147 Explore P: 0.8327
Episode: 1998 Total reward: 16.0 Training loss: 0.3225 Explore P: 0.8327
Episode: 1999 Total reward: 24.0 Training loss: 125.7672 Explore P: 0.8327
Episode: 2000 Total reward: 20.0 Training loss: 4.8424 Explore P: 0.8326
Episode: 2001 Total reward: 20.0 Training loss: 0.5130 Explore P: 0.8326
Episode: 2002 Total reward: 16.0 Training loss: 0.4983 Explore P: 0.8326
Episode: 2003 Total reward: 11.0 Training loss: 0.0736 Explore P: 0.8325
Episode: 2004 Total reward: 34.0 Training loss: 32.9047 Explore P: 0.8325
Episode: 2005 Total reward: 19.0 Training loss: 3.3657 Explore P: 0.8325
Episode: 2006 Total reward: 20.0 Training loss: 275.6960 Explore P: 0.8324
Episode: 2007 Total reward: 12.0 Training loss: 0.3590 Explore P: 0.8324
Episode: 2008 Total reward: 30.0 Training loss: 0.8839 Explore P: 0.8324
Episode: 2009 Total reward: 11.0 Training loss: 8.2208 Explore P: 0.8323
Episode: 2010 Total reward: 29.0 Training loss: 2.5747 Explore P: 0.8323
Episode: 2011 Total reward: 9.0 Training loss: 0.8281 Explore P: 0.8323
Episode: 2012 Total reward: 17.0 Training loss: 113.2967 Explore P: 0.8323
Episode: 2013 Total reward: 30.0 Training loss: 0.5999 Explore P: 0.8322
Episode: 2014 Total reward: 11.0 Training loss: 69.2471 Explore P: 0.8322
Episode: 2015 Total reward: 29.0 Training loss: 0.1753 Explore P: 0.8321
Episode: 2016 Total reward: 28.0 Training loss: 0.2755 Explore P: 0.8321
Episode: 2017 Total reward: 28.0 Training loss: 23.2306 Explore P: 0.8320
Episode: 2018 Total reward: 12.0 Training loss: 0.2837 Explore P: 0.8320
Episode: 2019 Total reward: 11.0 Training loss: 5.8202 Explore P: 0.8320
Episode: 2020 Total reward: 32.0 Training loss: 0.0801 Explore P: 0.8320
Episode: 2021 Total reward: 15.0 Training loss: 75.0485 Explore P: 0.8319
Episode: 2022 Total reward: 66.0 Training loss: 70.8593 Explore P: 0.8318
Episode: 2023 Total reward: 13.0 Training loss: 95.6334 Explore P: 0.8318
Episode: 2024 Total reward: 10.0 Training loss: 54.9574 Explore P: 0.8318
Episode: 2025 Total reward: 18.0 Training loss: 3.0681 Explore P: 0.8318
Episode: 2026 Total reward: 13.0 Training loss: 11.6964 Explore P: 0.8317
Episode: 2027 Total reward: 19.0 Training loss: 11.4509 Explore P: 0.8317
Episode: 2028 Total reward: 12.0 Training loss: 61.0631 Explore P: 0.8317
Episode: 2029 Total reward: 11.0 Training loss: 7.2394 Explore P: 0.8317
Episode: 2030 Total reward: 37.0 Training loss: 1.0960 Explore P: 0.8316
Episode: 2031 Total reward: 24.0 Training loss: 21.1970 Explore P: 0.8316
Episode: 2032 Total reward: 22.0 Training loss: 3.2306 Explore P: 0.8315
Episode: 2033 Total reward: 15.0 Training loss: 16.0925 Explore P: 0.8315
Episode: 2034 Total reward: 12.0 Training loss: 0.2052 Explore P: 0.8315
Episode: 2035 Total reward: 63.0 Training loss: 17.2485 Explore P: 0.8314
Episode: 2036 Total reward: 16.0 Training loss: 20.8048 Explore P: 0.8314
Episode: 2037 Total reward: 17.0 Training loss: 2.4275 Explore P: 0.8313
Episode: 2038 Total reward: 16.0 Training loss: 26.5179 Explore P: 0.8313
Episode: 2039 Total reward: 16.0 Training loss: 0.2928 Explore P: 0.8313
Episode: 2040 Total reward: 11.0 Training loss: 14.1466 Explore P: 0.8313
Episode: 2041 Total reward: 12.0 Training loss: 15.5753 Explore P: 0.8312
Episode: 2042 Total reward: 14.0 Training loss: 20.3961 Explore P: 0.8312
Episode: 2043 Total reward: 14.0 Training loss: 14.4480 Explore P: 0.8312
Episode: 2044 Total reward: 19.0 Training loss: 34.3278 Explore P: 0.8312
Episode: 2045 Total reward: 34.0 Training loss: 10.1636 Explore P: 0.8311
Episode: 2046 Total reward: 13.0 Training loss: 5.4814 Explore P: 0.8311
Episode: 2047 Total reward: 17.0 Training loss: 1.8949 Explore P: 0.8311
Episode: 2048 Total reward: 44.0 Training loss: 7.9412 Explore P: 0.8310
Episode: 2049 Total reward: 23.0 Training loss: 0.3862 Explore P: 0.8309
Episode: 2050 Total reward: 32.0 Training loss: 11.4618 Explore P: 0.8309
Episode: 2051 Total reward: 26.0 Training loss: 6.5598 Explore P: 0.8308
Episode: 2052 Total reward: 19.0 Training loss: 54.7647 Explore P: 0.8308
Episode: 2053 Total reward: 13.0 Training loss: 0.3210 Explore P: 0.8308
Episode: 2054 Total reward: 10.0 Training loss: 0.5023 Explore P: 0.8308
Episode: 2055 Total reward: 34.0 Training loss: 1.1273 Explore P: 0.8307
Episode: 2056 Total reward: 18.0 Training loss: 6.3853 Explore P: 0.8307
Episode: 2057 Total reward: 24.0 Training loss: 0.3658 Explore P: 0.8307
Episode: 2058 Total reward: 35.0 Training loss: 13.2229 Explore P: 0.8306
Episode: 2059 Total reward: 18.0 Training loss: 0.4368 Explore P: 0.8306
Episode: 2060 Total reward: 23.0 Training loss: 4.2737 Explore P: 0.8305
Episode: 2061 Total reward: 43.0 Training loss: 0.1816 Explore P: 0.8305
Episode: 2062 Total reward: 15.0 Training loss: 55.3363 Explore P: 0.8304
Episode: 2063 Total reward: 34.0 Training loss: 5.9539 Explore P: 0.8304
Episode: 2064 Total reward: 27.0 Training loss: 1.6832 Explore P: 0.8303
Episode: 2065 Total reward: 19.0 Training loss: 36.4999 Explore P: 0.8303
Episode: 2066 Total reward: 16.0 Training loss: 19.3574 Explore P: 0.8303
Episode: 2067 Total reward: 18.0 Training loss: 56.9484 Explore P: 0.8302
Episode: 2068 Total reward: 18.0 Training loss: 26.8662 Explore P: 0.8302
Episode: 2069 Total reward: 10.0 Training loss: 2.2797 Explore P: 0.8302
Episode: 2070 Total reward: 13.0 Training loss: 12.3404 Explore P: 0.8302
Episode: 2071 Total reward: 10.0 Training loss: 41.7028 Explore P: 0.8302
Episode: 2072 Total reward: 13.0 Training loss: 102.9689 Explore P: 0.8301
Episode: 2073 Total reward: 12.0 Training loss: 52.6643 Explore P: 0.8301
Episode: 2074 Total reward: 11.0 Training loss: 16.3968 Explore P: 0.8301
Episode: 2075 Total reward: 24.0 Training loss: 0.1252 Explore P: 0.8301
Episode: 2076 Total reward: 22.0 Training loss: 19.5690 Explore P: 0.8300
Episode: 2077 Total reward: 21.0 Training loss: 88.7420 Explore P: 0.8300
Episode: 2078 Total reward: 21.0 Training loss: 94.0637 Explore P: 0.8300
Episode: 2079 Total reward: 43.0 Training loss: 14.0532 Explore P: 0.8299
Episode: 2080 Total reward: 15.0 Training loss: 27.2350 Explore P: 0.8299
Episode: 2081 Total reward: 17.0 Training loss: 0.3798 Explore P: 0.8298
Episode: 2082 Total reward: 11.0 Training loss: 41.6940 Explore P: 0.8298
Episode: 2083 Total reward: 25.0 Training loss: 16.9201 Explore P: 0.8298
Episode: 2084 Total reward: 11.0 Training loss: 57.8840 Explore P: 0.8298
Episode: 2085 Total reward: 16.0 Training loss: 0.1467 Explore P: 0.8297
Episode: 2086 Total reward: 15.0 Training loss: 4.5321 Explore P: 0.8297
Episode: 2087 Total reward: 48.0 Training loss: 54.2771 Explore P: 0.8296
Episode: 2088 Total reward: 16.0 Training loss: 188.2805 Explore P: 0.8296
Episode: 2089 Total reward: 25.0 Training loss: 27.2159 Explore P: 0.8296
Episode: 2090 Total reward: 19.0 Training loss: 2.9304 Explore P: 0.8295
Episode: 2091 Total reward: 15.0 Training loss: 132.7059 Explore P: 0.8295
Episode: 2092 Total reward: 16.0 Training loss: 6.3135 Explore P: 0.8295
Episode: 2093 Total reward: 18.0 Training loss: 0.1847 Explore P: 0.8295
Episode: 2094 Total reward: 27.0 Training loss: 0.1658 Explore P: 0.8294
Episode: 2095 Total reward: 10.0 Training loss: 13.6532 Explore P: 0.8294
Episode: 2096 Total reward: 9.0 Training loss: 36.9716 Explore P: 0.8294
Episode: 2097 Total reward: 23.0 Training loss: 58.9500 Explore P: 0.8293
Episode: 2098 Total reward: 11.0 Training loss: 54.8751 Explore P: 0.8293
Episode: 2099 Total reward: 14.0 Training loss: 4.0933 Explore P: 0.8293
Episode: 2100 Total reward: 20.0 Training loss: 29.8624 Explore P: 0.8293
Episode: 2101 Total reward: 23.0 Training loss: 0.1127 Explore P: 0.8292
Episode: 2102 Total reward: 27.0 Training loss: 0.1613 Explore P: 0.8292
Episode: 2103 Total reward: 17.0 Training loss: 4.5677 Explore P: 0.8292
Episode: 2104 Total reward: 37.0 Training loss: 38.3696 Explore P: 0.8291
Episode: 2105 Total reward: 14.0 Training loss: 4.9003 Explore P: 0.8291
Episode: 2106 Total reward: 15.0 Training loss: 44.8267 Explore P: 0.8290
Episode: 2107 Total reward: 12.0 Training loss: 24.5366 Explore P: 0.8290
Episode: 2108 Total reward: 27.0 Training loss: 42.8278 Explore P: 0.8290
Episode: 2109 Total reward: 20.0 Training loss: 10.6656 Explore P: 0.8289
Episode: 2110 Total reward: 13.0 Training loss: 57.9728 Explore P: 0.8289
Episode: 2111 Total reward: 13.0 Training loss: 6.1840 Explore P: 0.8289
Episode: 2112 Total reward: 31.0 Training loss: 45.0077 Explore P: 0.8289
Episode: 2113 Total reward: 15.0 Training loss: 0.3093 Explore P: 0.8288
Episode: 2114 Total reward: 15.0 Training loss: 0.1299 Explore P: 0.8288
Episode: 2115 Total reward: 18.0 Training loss: 64.8539 Explore P: 0.8288
Episode: 2116 Total reward: 28.0 Training loss: 0.1809 Explore P: 0.8287
Episode: 2117 Total reward: 16.0 Training loss: 29.6320 Explore P: 0.8287
Episode: 2118 Total reward: 23.0 Training loss: 5.2647 Explore P: 0.8287
Episode: 2119 Total reward: 15.0 Training loss: 157.2950 Explore P: 0.8286
Episode: 2120 Total reward: 55.0 Training loss: 36.0007 Explore P: 0.8286
Episode: 2121 Total reward: 18.0 Training loss: 11.7143 Explore P: 0.8285
Episode: 2122 Total reward: 9.0 Training loss: 41.1416 Explore P: 0.8285
Episode: 2123 Total reward: 54.0 Training loss: 28.8178 Explore P: 0.8284
Episode: 2124 Total reward: 26.0 Training loss: 78.6327 Explore P: 0.8284
Episode: 2125 Total reward: 12.0 Training loss: 5.3827 Explore P: 0.8284
Episode: 2126 Total reward: 9.0 Training loss: 45.5519 Explore P: 0.8283
Episode: 2127 Total reward: 19.0 Training loss: 0.1520 Explore P: 0.8283
Episode: 2128 Total reward: 33.0 Training loss: 103.5453 Explore P: 0.8283
Episode: 2129 Total reward: 17.0 Training loss: 80.0333 Explore P: 0.8282
Episode: 2130 Total reward: 37.0 Training loss: 66.7548 Explore P: 0.8282
Episode: 2131 Total reward: 27.0 Training loss: 0.4116 Explore P: 0.8281
Episode: 2132 Total reward: 11.0 Training loss: 17.0825 Explore P: 0.8281
Episode: 2133 Total reward: 19.0 Training loss: 0.0865 Explore P: 0.8281
Episode: 2134 Total reward: 36.0 Training loss: 14.2466 Explore P: 0.8280
Episode: 2135 Total reward: 16.0 Training loss: 1.5197 Explore P: 0.8280
Episode: 2136 Total reward: 12.0 Training loss: 0.7781 Explore P: 0.8280
Episode: 2137 Total reward: 11.0 Training loss: 75.6594 Explore P: 0.8280
Episode: 2138 Total reward: 12.0 Training loss: 46.8348 Explore P: 0.8279
Episode: 2139 Total reward: 12.0 Training loss: 74.3178 Explore P: 0.8279
Episode: 2140 Total reward: 31.0 Training loss: 17.8661 Explore P: 0.8279
Episode: 2141 Total reward: 19.0 Training loss: 0.2687 Explore P: 0.8278
Episode: 2142 Total reward: 11.0 Training loss: 25.9542 Explore P: 0.8278
Episode: 2143 Total reward: 45.0 Training loss: 9.5611 Explore P: 0.8277
Episode: 2144 Total reward: 16.0 Training loss: 335.7135 Explore P: 0.8277
Episode: 2145 Total reward: 10.0 Training loss: 12.6353 Explore P: 0.8277
Episode: 2146 Total reward: 25.0 Training loss: 0.2271 Explore P: 0.8277
Episode: 2147 Total reward: 14.0 Training loss: 0.2890 Explore P: 0.8276
Episode: 2148 Total reward: 11.0 Training loss: 7.9152 Explore P: 0.8276
Episode: 2149 Total reward: 14.0 Training loss: 1.3774 Explore P: 0.8276
Episode: 2150 Total reward: 15.0 Training loss: 40.5972 Explore P: 0.8276
Episode: 2151 Total reward: 12.0 Training loss: 12.4496 Explore P: 0.8275
Episode: 2152 Total reward: 11.0 Training loss: 23.3532 Explore P: 0.8275
Episode: 2153 Total reward: 47.0 Training loss: 15.4496 Explore P: 0.8275
Episode: 2154 Total reward: 28.0 Training loss: 9.5671 Explore P: 0.8274
Episode: 2155 Total reward: 12.0 Training loss: 0.3758 Explore P: 0.8274
Episode: 2156 Total reward: 20.0 Training loss: 16.7206 Explore P: 0.8274
Episode: 2157 Total reward: 16.0 Training loss: 25.9688 Explore P: 0.8273
Episode: 2158 Total reward: 15.0 Training loss: 0.3342 Explore P: 0.8273
Episode: 2159 Total reward: 16.0 Training loss: 4.5192 Explore P: 0.8273
Episode: 2160 Total reward: 34.0 Training loss: 0.1563 Explore P: 0.8272
Episode: 2161 Total reward: 13.0 Training loss: 1.8592 Explore P: 0.8272
Episode: 2162 Total reward: 28.0 Training loss: 4.9313 Explore P: 0.8272
Episode: 2163 Total reward: 8.0 Training loss: 108.1981 Explore P: 0.8271
Episode: 2164 Total reward: 17.0 Training loss: 48.3146 Explore P: 0.8271
Episode: 2165 Total reward: 10.0 Training loss: 0.1691 Explore P: 0.8271
Episode: 2166 Total reward: 21.0 Training loss: 10.7804 Explore P: 0.8271
Episode: 2167 Total reward: 15.0 Training loss: 1.2087 Explore P: 0.8270
Episode: 2168 Total reward: 19.0 Training loss: 23.1407 Explore P: 0.8270
Episode: 2169 Total reward: 12.0 Training loss: 0.2456 Explore P: 0.8270
Episode: 2170 Total reward: 26.0 Training loss: 35.0988 Explore P: 0.8269
Episode: 2171 Total reward: 21.0 Training loss: 26.4136 Explore P: 0.8269
Episode: 2172 Total reward: 19.0 Training loss: 0.2082 Explore P: 0.8269
Episode: 2173 Total reward: 25.0 Training loss: 0.1294 Explore P: 0.8268
Episode: 2174 Total reward: 8.0 Training loss: 0.5127 Explore P: 0.8268
Episode: 2175 Total reward: 11.0 Training loss: 7.8023 Explore P: 0.8268
Episode: 2176 Total reward: 22.0 Training loss: 7.0298 Explore P: 0.8268
Episode: 2177 Total reward: 16.0 Training loss: 11.5300 Explore P: 0.8267
Episode: 2178 Total reward: 29.0 Training loss: 94.4545 Explore P: 0.8267
Episode: 2179 Total reward: 24.0 Training loss: 1.2793 Explore P: 0.8267
Episode: 2180 Total reward: 12.0 Training loss: 4.5799 Explore P: 0.8266
Episode: 2181 Total reward: 14.0 Training loss: 20.5345 Explore P: 0.8266
Episode: 2182 Total reward: 41.0 Training loss: 19.9753 Explore P: 0.8266
Episode: 2183 Total reward: 19.0 Training loss: 37.4255 Explore P: 0.8265
Episode: 2184 Total reward: 13.0 Training loss: 0.1735 Explore P: 0.8265
Episode: 2185 Total reward: 11.0 Training loss: 17.3524 Explore P: 0.8265
Episode: 2186 Total reward: 17.0 Training loss: 50.8467 Explore P: 0.8265
Episode: 2187 Total reward: 23.0 Training loss: 0.2333 Explore P: 0.8264
Episode: 2188 Total reward: 50.0 Training loss: 41.5030 Explore P: 0.8263
Episode: 2189 Total reward: 22.0 Training loss: 17.4506 Explore P: 0.8263
Episode: 2190 Total reward: 15.0 Training loss: 0.3145 Explore P: 0.8263
Episode: 2191 Total reward: 41.0 Training loss: 0.1067 Explore P: 0.8262
Episode: 2192 Total reward: 39.0 Training loss: 6.9491 Explore P: 0.8261
Episode: 2193 Total reward: 26.0 Training loss: 0.2703 Explore P: 0.8261
Episode: 2194 Total reward: 13.0 Training loss: 0.2580 Explore P: 0.8261
Episode: 2195 Total reward: 28.0 Training loss: 0.2163 Explore P: 0.8260
Episode: 2196 Total reward: 37.0 Training loss: 26.9681 Explore P: 0.8260
Episode: 2197 Total reward: 20.0 Training loss: 0.1833 Explore P: 0.8259
Episode: 2198 Total reward: 21.0 Training loss: 0.7757 Explore P: 0.8259
Episode: 2199 Total reward: 22.0 Training loss: 0.1962 Explore P: 0.8259
Episode: 2200 Total reward: 16.0 Training loss: 0.0735 Explore P: 0.8258
Episode: 2201 Total reward: 10.0 Training loss: 33.8358 Explore P: 0.8258
Episode: 2202 Total reward: 19.0 Training loss: 9.7228 Explore P: 0.8258
Episode: 2203 Total reward: 19.0 Training loss: 0.1639 Explore P: 0.8258
Episode: 2204 Total reward: 19.0 Training loss: 31.2711 Explore P: 0.8257
Episode: 2205 Total reward: 18.0 Training loss: 7.1367 Explore P: 0.8257
Episode: 2206 Total reward: 18.0 Training loss: 28.1622 Explore P: 0.8257
Episode: 2207 Total reward: 16.0 Training loss: 1.9562 Explore P: 0.8257
Episode: 2208 Total reward: 24.0 Training loss: 116.4906 Explore P: 0.8256
Episode: 2209 Total reward: 16.0 Training loss: 0.2656 Explore P: 0.8256
Episode: 2210 Total reward: 18.0 Training loss: 14.6628 Explore P: 0.8256
Episode: 2211 Total reward: 20.0 Training loss: 8.4104 Explore P: 0.8255
Episode: 2212 Total reward: 35.0 Training loss: 0.2020 Explore P: 0.8255
Episode: 2213 Total reward: 26.0 Training loss: 111.1063 Explore P: 0.8254
Episode: 2214 Total reward: 26.0 Training loss: 0.1391 Explore P: 0.8254
Episode: 2215 Total reward: 12.0 Training loss: 86.1268 Explore P: 0.8254
Episode: 2216 Total reward: 22.0 Training loss: 17.9403 Explore P: 0.8253
Episode: 2217 Total reward: 33.0 Training loss: 0.6297 Explore P: 0.8253
Episode: 2218 Total reward: 11.0 Training loss: 6.8646 Explore P: 0.8253
Episode: 2219 Total reward: 15.0 Training loss: 8.2034 Explore P: 0.8252
Episode: 2220 Total reward: 23.0 Training loss: 65.2650 Explore P: 0.8252
Episode: 2221 Total reward: 24.0 Training loss: 0.2494 Explore P: 0.8252
Episode: 2222 Total reward: 21.0 Training loss: 41.8822 Explore P: 0.8251
Episode: 2223 Total reward: 14.0 Training loss: 9.6181 Explore P: 0.8251
Episode: 2224 Total reward: 12.0 Training loss: 49.1777 Explore P: 0.8251
Episode: 2225 Total reward: 18.0 Training loss: 4.7947 Explore P: 0.8250
Episode: 2226 Total reward: 16.0 Training loss: 1.7056 Explore P: 0.8250
Episode: 2227 Total reward: 21.0 Training loss: 33.2857 Explore P: 0.8250
Episode: 2228 Total reward: 87.0 Training loss: 15.6177 Explore P: 0.8248
Episode: 2229 Total reward: 17.0 Training loss: 0.4293 Explore P: 0.8248
Episode: 2230 Total reward: 11.0 Training loss: 0.4032 Explore P: 0.8248
Episode: 2231 Total reward: 22.0 Training loss: 41.4246 Explore P: 0.8248
Episode: 2232 Total reward: 13.0 Training loss: 3.2747 Explore P: 0.8247
Episode: 2233 Total reward: 29.0 Training loss: 103.3947 Explore P: 0.8247
Episode: 2234 Total reward: 13.0 Training loss: 0.3095 Explore P: 0.8247
Episode: 2235 Total reward: 10.0 Training loss: 26.1825 Explore P: 0.8247
Episode: 2236 Total reward: 11.0 Training loss: 11.8126 Explore P: 0.8246
Episode: 2237 Total reward: 12.0 Training loss: 0.7114 Explore P: 0.8246
Episode: 2238 Total reward: 24.0 Training loss: 0.1747 Explore P: 0.8246
Episode: 2239 Total reward: 12.0 Training loss: 28.0252 Explore P: 0.8246
Episode: 2240 Total reward: 14.0 Training loss: 41.6438 Explore P: 0.8245
Episode: 2241 Total reward: 9.0 Training loss: 3.0440 Explore P: 0.8245
Episode: 2242 Total reward: 20.0 Training loss: 75.7741 Explore P: 0.8245
Episode: 2243 Total reward: 17.0 Training loss: 7.7548 Explore P: 0.8245
Episode: 2244 Total reward: 40.0 Training loss: 0.1113 Explore P: 0.8244
Episode: 2245 Total reward: 37.0 Training loss: 192.4139 Explore P: 0.8243
Episode: 2246 Total reward: 28.0 Training loss: 53.4504 Explore P: 0.8243
Episode: 2247 Total reward: 11.0 Training loss: 176.3156 Explore P: 0.8243
Episode: 2248 Total reward: 36.0 Training loss: 23.8023 Explore P: 0.8242
Episode: 2249 Total reward: 25.0 Training loss: 21.6986 Explore P: 0.8242
Episode: 2250 Total reward: 29.0 Training loss: 0.3204 Explore P: 0.8241
Episode: 2251 Total reward: 43.0 Training loss: 9.1375 Explore P: 0.8241
Episode: 2252 Total reward: 14.0 Training loss: 97.5254 Explore P: 0.8240
Episode: 2253 Total reward: 12.0 Training loss: 27.4715 Explore P: 0.8240
Episode: 2254 Total reward: 14.0 Training loss: 0.1484 Explore P: 0.8240
Episode: 2255 Total reward: 10.0 Training loss: 10.8022 Explore P: 0.8240
Episode: 2256 Total reward: 21.0 Training loss: 1.0849 Explore P: 0.8239
Episode: 2257 Total reward: 19.0 Training loss: 23.8596 Explore P: 0.8239
Episode: 2258 Total reward: 12.0 Training loss: 364.6421 Explore P: 0.8239
Episode: 2259 Total reward: 30.0 Training loss: 36.1137 Explore P: 0.8238
Episode: 2260 Total reward: 19.0 Training loss: 46.3097 Explore P: 0.8238
Episode: 2261 Total reward: 15.0 Training loss: 4.8719 Explore P: 0.8238
Episode: 2262 Total reward: 17.0 Training loss: 2.4622 Explore P: 0.8238
Episode: 2263 Total reward: 9.0 Training loss: 11.1838 Explore P: 0.8237
Episode: 2264 Total reward: 32.0 Training loss: 13.5646 Explore P: 0.8237
Episode: 2265 Total reward: 21.0 Training loss: 0.2961 Explore P: 0.8237
Episode: 2266 Total reward: 18.0 Training loss: 0.2662 Explore P: 0.8236
Episode: 2267 Total reward: 33.0 Training loss: 171.7545 Explore P: 0.8236
Episode: 2268 Total reward: 19.0 Training loss: 6.7844 Explore P: 0.8235
Episode: 2269 Total reward: 15.0 Training loss: 55.2513 Explore P: 0.8235
Episode: 2270 Total reward: 12.0 Training loss: 0.1070 Explore P: 0.8235
Episode: 2271 Total reward: 28.0 Training loss: 6.2524 Explore P: 0.8235
Episode: 2272 Total reward: 14.0 Training loss: 12.3154 Explore P: 0.8234
Episode: 2273 Total reward: 17.0 Training loss: 7.1780 Explore P: 0.8234
Episode: 2274 Total reward: 28.0 Training loss: 1.2662 Explore P: 0.8234
Episode: 2275 Total reward: 17.0 Training loss: 31.9266 Explore P: 0.8233
Episode: 2276 Total reward: 22.0 Training loss: 96.3995 Explore P: 0.8233
Episode: 2277 Total reward: 24.0 Training loss: 1.5175 Explore P: 0.8233
Episode: 2278 Total reward: 8.0 Training loss: 0.5984 Explore P: 0.8232
Episode: 2279 Total reward: 14.0 Training loss: 0.1344 Explore P: 0.8232
Episode: 2280 Total reward: 45.0 Training loss: 0.8969 Explore P: 0.8231
Episode: 2281 Total reward: 15.0 Training loss: 80.6000 Explore P: 0.8231
Episode: 2282 Total reward: 10.0 Training loss: 1.4815 Explore P: 0.8231
Episode: 2283 Total reward: 15.0 Training loss: 142.3335 Explore P: 0.8231
Episode: 2284 Total reward: 10.0 Training loss: 2.9136 Explore P: 0.8231
Episode: 2285 Total reward: 10.0 Training loss: 1.0811 Explore P: 0.8231
Episode: 2286 Total reward: 18.0 Training loss: 1.3119 Explore P: 0.8230
Episode: 2287 Total reward: 13.0 Training loss: 0.1485 Explore P: 0.8230
Episode: 2288 Total reward: 21.0 Training loss: 98.3905 Explore P: 0.8230
Episode: 2289 Total reward: 13.0 Training loss: 15.0879 Explore P: 0.8229
Episode: 2290 Total reward: 24.0 Training loss: 0.1490 Explore P: 0.8229
Episode: 2291 Total reward: 13.0 Training loss: 148.6178 Explore P: 0.8229
Episode: 2292 Total reward: 28.0 Training loss: 10.0264 Explore P: 0.8228
Episode: 2293 Total reward: 19.0 Training loss: 0.1366 Explore P: 0.8228
Episode: 2294 Total reward: 16.0 Training loss: 1.3930 Explore P: 0.8228
Episode: 2295 Total reward: 11.0 Training loss: 151.1282 Explore P: 0.8228
Episode: 2296 Total reward: 14.0 Training loss: 0.4829 Explore P: 0.8227
Episode: 2297 Total reward: 41.0 Training loss: 0.9193 Explore P: 0.8227
Episode: 2298 Total reward: 39.0 Training loss: 0.1845 Explore P: 0.8226
Episode: 2299 Total reward: 19.0 Training loss: 45.4274 Explore P: 0.8226
Episode: 2300 Total reward: 8.0 Training loss: 0.2819 Explore P: 0.8226
Episode: 2301 Total reward: 11.0 Training loss: 5.2875 Explore P: 0.8226
Episode: 2302 Total reward: 26.0 Training loss: 25.3572 Explore P: 0.8225
Episode: 2303 Total reward: 21.0 Training loss: 0.2694 Explore P: 0.8225
Episode: 2304 Total reward: 35.0 Training loss: 15.9534 Explore P: 0.8224
Episode: 2305 Total reward: 16.0 Training loss: 0.2812 Explore P: 0.8224
Episode: 2306 Total reward: 12.0 Training loss: 20.4804 Explore P: 0.8224
Episode: 2307 Total reward: 25.0 Training loss: 2.4059 Explore P: 0.8223
Episode: 2308 Total reward: 31.0 Training loss: 4.7860 Explore P: 0.8223
Episode: 2309 Total reward: 24.0 Training loss: 0.2609 Explore P: 0.8222
Episode: 2310 Total reward: 10.0 Training loss: 19.9097 Explore P: 0.8222
Episode: 2311 Total reward: 11.0 Training loss: 39.5807 Explore P: 0.8222
Episode: 2312 Total reward: 15.0 Training loss: 0.2148 Explore P: 0.8222
Episode: 2313 Total reward: 12.0 Training loss: 40.3659 Explore P: 0.8222
Episode: 2314 Total reward: 33.0 Training loss: 39.0816 Explore P: 0.8221
Episode: 2315 Total reward: 16.0 Training loss: 0.1977 Explore P: 0.8221
Episode: 2316 Total reward: 17.0 Training loss: 0.7657 Explore P: 0.8221
Episode: 2317 Total reward: 13.0 Training loss: 32.0620 Explore P: 0.8220
Episode: 2318 Total reward: 10.0 Training loss: 23.2760 Explore P: 0.8220
Episode: 2319 Total reward: 9.0 Training loss: 1.4209 Explore P: 0.8220
Episode: 2320 Total reward: 36.0 Training loss: 0.1109 Explore P: 0.8219
Episode: 2321 Total reward: 17.0 Training loss: 74.9655 Explore P: 0.8219
Episode: 2322 Total reward: 23.0 Training loss: 8.8767 Explore P: 0.8219
Episode: 2323 Total reward: 19.0 Training loss: 136.1105 Explore P: 0.8219
Episode: 2324 Total reward: 19.0 Training loss: 0.2153 Explore P: 0.8218
Episode: 2325 Total reward: 16.0 Training loss: 0.1366 Explore P: 0.8218
Episode: 2326 Total reward: 11.0 Training loss: 0.2459 Explore P: 0.8218
Episode: 2327 Total reward: 11.0 Training loss: 65.4040 Explore P: 0.8218
Episode: 2328 Total reward: 15.0 Training loss: 3.8891 Explore P: 0.8217
Episode: 2329 Total reward: 14.0 Training loss: 35.2019 Explore P: 0.8217
Episode: 2330 Total reward: 24.0 Training loss: 27.3993 Explore P: 0.8217
Episode: 2331 Total reward: 97.0 Training loss: 31.9933 Explore P: 0.8215
Episode: 2332 Total reward: 45.0 Training loss: 85.0585 Explore P: 0.8214
Episode: 2333 Total reward: 36.0 Training loss: 9.2908 Explore P: 0.8214
Episode: 2334 Total reward: 49.0 Training loss: 51.8687 Explore P: 0.8213
Episode: 2335 Total reward: 20.0 Training loss: 20.9245 Explore P: 0.8213
Episode: 2336 Total reward: 22.0 Training loss: 0.5087 Explore P: 0.8212
Episode: 2337 Total reward: 13.0 Training loss: 15.0823 Explore P: 0.8212
Episode: 2338 Total reward: 15.0 Training loss: 0.0780 Explore P: 0.8212
Episode: 2339 Total reward: 16.0 Training loss: 33.0276 Explore P: 0.8212
Episode: 2340 Total reward: 38.0 Training loss: 36.0128 Explore P: 0.8211
Episode: 2341 Total reward: 18.0 Training loss: 1.6159 Explore P: 0.8211
Episode: 2342 Total reward: 35.0 Training loss: 83.2526 Explore P: 0.8210
Episode: 2343 Total reward: 28.0 Training loss: 24.5610 Explore P: 0.8210
Episode: 2344 Total reward: 11.0 Training loss: 1.3677 Explore P: 0.8210
Episode: 2345 Total reward: 24.0 Training loss: 0.3629 Explore P: 0.8209
Episode: 2346 Total reward: 10.0 Training loss: 2.9066 Explore P: 0.8209
Episode: 2347 Total reward: 12.0 Training loss: 0.1618 Explore P: 0.8209
Episode: 2348 Total reward: 47.0 Training loss: 0.6548 Explore P: 0.8208
Episode: 2349 Total reward: 18.0 Training loss: 63.4354 Explore P: 0.8208
Episode: 2350 Total reward: 14.0 Training loss: 0.1597 Explore P: 0.8208
Episode: 2351 Total reward: 15.0 Training loss: 10.0001 Explore P: 0.8207
Episode: 2352 Total reward: 14.0 Training loss: 2.6461 Explore P: 0.8207
Episode: 2353 Total reward: 14.0 Training loss: 1.7278 Explore P: 0.8207
Episode: 2354 Total reward: 15.0 Training loss: 0.1466 Explore P: 0.8207
Episode: 2355 Total reward: 16.0 Training loss: 6.2444 Explore P: 0.8206
Episode: 2356 Total reward: 19.0 Training loss: 52.9822 Explore P: 0.8206
Episode: 2357 Total reward: 15.0 Training loss: 1.5803 Explore P: 0.8206
Episode: 2358 Total reward: 21.0 Training loss: 38.9906 Explore P: 0.8205
Episode: 2359 Total reward: 15.0 Training loss: 82.8216 Explore P: 0.8205
Episode: 2360 Total reward: 21.0 Training loss: 39.7654 Explore P: 0.8205
Episode: 2361 Total reward: 29.0 Training loss: 4.1493 Explore P: 0.8204
Episode: 2362 Total reward: 25.0 Training loss: 4.8101 Explore P: 0.8204
Episode: 2363 Total reward: 14.0 Training loss: 0.2369 Explore P: 0.8204
Episode: 2364 Total reward: 11.0 Training loss: 338.2070 Explore P: 0.8204
Episode: 2365 Total reward: 20.0 Training loss: 59.3712 Explore P: 0.8203
Episode: 2366 Total reward: 10.0 Training loss: 6.9533 Explore P: 0.8203
Episode: 2367 Total reward: 11.0 Training loss: 59.0381 Explore P: 0.8203
Episode: 2368 Total reward: 45.0 Training loss: 0.1480 Explore P: 0.8202
Episode: 2369 Total reward: 14.0 Training loss: 0.1924 Explore P: 0.8202
Episode: 2370 Total reward: 37.0 Training loss: 29.7678 Explore P: 0.8201
Episode: 2371 Total reward: 32.0 Training loss: 86.2259 Explore P: 0.8201
Episode: 2372 Total reward: 21.0 Training loss: 54.9072 Explore P: 0.8200
Episode: 2373 Total reward: 19.0 Training loss: 28.4283 Explore P: 0.8200
Episode: 2374 Total reward: 31.0 Training loss: 5.4393 Explore P: 0.8200
Episode: 2375 Total reward: 11.0 Training loss: 17.4554 Explore P: 0.8199
Episode: 2376 Total reward: 11.0 Training loss: 0.2357 Explore P: 0.8199
Episode: 2377 Total reward: 8.0 Training loss: 43.0101 Explore P: 0.8199
Episode: 2378 Total reward: 54.0 Training loss: 2.2508 Explore P: 0.8198
Episode: 2379 Total reward: 27.0 Training loss: 0.1391 Explore P: 0.8198
Episode: 2380 Total reward: 10.0 Training loss: 0.2337 Explore P: 0.8198
Episode: 2381 Total reward: 36.0 Training loss: 15.4150 Explore P: 0.8197
Episode: 2382 Total reward: 18.0 Training loss: 34.6537 Explore P: 0.8197
Episode: 2383 Total reward: 18.0 Training loss: 0.1108 Explore P: 0.8197
Episode: 2384 Total reward: 13.0 Training loss: 9.3479 Explore P: 0.8196
Episode: 2385 Total reward: 12.0 Training loss: 28.2813 Explore P: 0.8196
Episode: 2386 Total reward: 10.0 Training loss: 0.2496 Explore P: 0.8196
Episode: 2387 Total reward: 10.0 Training loss: 17.6476 Explore P: 0.8196
Episode: 2388 Total reward: 18.0 Training loss: 0.1672 Explore P: 0.8196
Episode: 2389 Total reward: 23.0 Training loss: 32.9148 Explore P: 0.8195
Episode: 2390 Total reward: 20.0 Training loss: 69.4962 Explore P: 0.8195
Episode: 2391 Total reward: 20.0 Training loss: 0.1880 Explore P: 0.8195
Episode: 2392 Total reward: 25.0 Training loss: 20.3292 Explore P: 0.8194
Episode: 2393 Total reward: 40.0 Training loss: 29.0400 Explore P: 0.8193
Episode: 2394 Total reward: 22.0 Training loss: 0.2803 Explore P: 0.8193
Episode: 2395 Total reward: 23.0 Training loss: 10.4505 Explore P: 0.8193
Episode: 2396 Total reward: 15.0 Training loss: 7.4296 Explore P: 0.8192
Episode: 2397 Total reward: 18.0 Training loss: 0.3812 Explore P: 0.8192
Episode: 2398 Total reward: 30.0 Training loss: 0.2126 Explore P: 0.8192
Episode: 2399 Total reward: 39.0 Training loss: 0.2103 Explore P: 0.8191
Episode: 2400 Total reward: 16.0 Training loss: 0.2730 Explore P: 0.8191
Episode: 2401 Total reward: 17.0 Training loss: 62.1964 Explore P: 0.8191
Episode: 2402 Total reward: 27.0 Training loss: 10.9846 Explore P: 0.8190
Episode: 2403 Total reward: 12.0 Training loss: 3.0830 Explore P: 0.8190
Episode: 2404 Total reward: 10.0 Training loss: 20.3857 Explore P: 0.8190
Episode: 2405 Total reward: 10.0 Training loss: 0.1753 Explore P: 0.8190
Episode: 2406 Total reward: 58.0 Training loss: 15.7518 Explore P: 0.8189
Episode: 2407 Total reward: 14.0 Training loss: 44.7776 Explore P: 0.8188
Episode: 2408 Total reward: 30.0 Training loss: 53.9452 Explore P: 0.8188
Episode: 2409 Total reward: 44.0 Training loss: 12.2954 Explore P: 0.8187
Episode: 2410 Total reward: 50.0 Training loss: 48.0173 Explore P: 0.8186
Episode: 2411 Total reward: 17.0 Training loss: 0.9716 Explore P: 0.8186
Episode: 2412 Total reward: 61.0 Training loss: 3.2169 Explore P: 0.8185
Episode: 2413 Total reward: 11.0 Training loss: 40.5863 Explore P: 0.8185
Episode: 2414 Total reward: 11.0 Training loss: 0.3142 Explore P: 0.8185
Episode: 2415 Total reward: 11.0 Training loss: 1.0799 Explore P: 0.8185
Episode: 2416 Total reward: 17.0 Training loss: 1.1888 Explore P: 0.8184
Episode: 2417 Total reward: 15.0 Training loss: 1.2209 Explore P: 0.8184
Episode: 2418 Total reward: 11.0 Training loss: 28.8962 Explore P: 0.8184
Episode: 2419 Total reward: 57.0 Training loss: 1.1054 Explore P: 0.8183
Episode: 2420 Total reward: 12.0 Training loss: 0.1112 Explore P: 0.8183
Episode: 2421 Total reward: 43.0 Training loss: 7.9369 Explore P: 0.8182
Episode: 2422 Total reward: 44.0 Training loss: 26.5802 Explore P: 0.8181
Episode: 2423 Total reward: 17.0 Training loss: 8.1733 Explore P: 0.8181
Episode: 2424 Total reward: 45.0 Training loss: 28.1536 Explore P: 0.8180
Episode: 2425 Total reward: 21.0 Training loss: 16.1918 Explore P: 0.8180
Episode: 2426 Total reward: 19.0 Training loss: 35.5080 Explore P: 0.8180
Episode: 2427 Total reward: 11.0 Training loss: 0.1754 Explore P: 0.8180
Episode: 2428 Total reward: 35.0 Training loss: 40.3481 Explore P: 0.8179
Episode: 2429 Total reward: 15.0 Training loss: 0.1013 Explore P: 0.8179
Episode: 2430 Total reward: 14.0 Training loss: 3.0997 Explore P: 0.8179
Episode: 2431 Total reward: 11.0 Training loss: 0.1752 Explore P: 0.8178
Episode: 2432 Total reward: 9.0 Training loss: 0.9424 Explore P: 0.8178
Episode: 2433 Total reward: 12.0 Training loss: 66.7430 Explore P: 0.8178
Episode: 2434 Total reward: 11.0 Training loss: 5.5859 Explore P: 0.8178
Episode: 2435 Total reward: 9.0 Training loss: 73.5311 Explore P: 0.8178
Episode: 2436 Total reward: 27.0 Training loss: 3.7863 Explore P: 0.8177
Episode: 2437 Total reward: 19.0 Training loss: 10.7455 Explore P: 0.8177
Episode: 2438 Total reward: 44.0 Training loss: 20.5940 Explore P: 0.8176
Episode: 2439 Total reward: 17.0 Training loss: 0.6906 Explore P: 0.8176
Episode: 2440 Total reward: 31.0 Training loss: 0.3608 Explore P: 0.8175
Episode: 2441 Total reward: 20.0 Training loss: 2.5307 Explore P: 0.8175
Episode: 2442 Total reward: 15.0 Training loss: 1.8455 Explore P: 0.8175
Episode: 2443 Total reward: 26.0 Training loss: 108.6412 Explore P: 0.8174
Episode: 2444 Total reward: 39.0 Training loss: 4.5149 Explore P: 0.8174
Episode: 2445 Total reward: 12.0 Training loss: 36.0088 Explore P: 0.8174
Episode: 2446 Total reward: 33.0 Training loss: 27.4583 Explore P: 0.8173
Episode: 2447 Total reward: 14.0 Training loss: 0.8910 Explore P: 0.8173
Episode: 2448 Total reward: 10.0 Training loss: 39.8538 Explore P: 0.8173
Episode: 2449 Total reward: 14.0 Training loss: 11.9084 Explore P: 0.8173
Episode: 2450 Total reward: 18.0 Training loss: 19.5412 Explore P: 0.8172
Episode: 2451 Total reward: 11.0 Training loss: 26.4930 Explore P: 0.8172
Episode: 2452 Total reward: 26.0 Training loss: 60.1204 Explore P: 0.8172
Episode: 2453 Total reward: 11.0 Training loss: 0.0899 Explore P: 0.8171
Episode: 2454 Total reward: 49.0 Training loss: 0.4101 Explore P: 0.8171
Episode: 2455 Total reward: 10.0 Training loss: 0.1245 Explore P: 0.8170
Episode: 2456 Total reward: 13.0 Training loss: 13.3807 Explore P: 0.8170
Episode: 2457 Total reward: 15.0 Training loss: 15.1436 Explore P: 0.8170
Episode: 2458 Total reward: 17.0 Training loss: 69.8915 Explore P: 0.8170
Episode: 2459 Total reward: 22.0 Training loss: 739.8890 Explore P: 0.8169
Episode: 2460 Total reward: 17.0 Training loss: 0.1179 Explore P: 0.8169
Episode: 2461 Total reward: 17.0 Training loss: 45.7198 Explore P: 0.8169
Episode: 2462 Total reward: 17.0 Training loss: 0.2971 Explore P: 0.8169
Episode: 2463 Total reward: 13.0 Training loss: 16.6515 Explore P: 0.8168
Episode: 2464 Total reward: 16.0 Training loss: 107.5793 Explore P: 0.8168
Episode: 2465 Total reward: 11.0 Training loss: 0.2103 Explore P: 0.8168
Episode: 2466 Total reward: 15.0 Training loss: 31.9145 Explore P: 0.8168
Episode: 2467 Total reward: 30.0 Training loss: 27.7561 Explore P: 0.8167
Episode: 2468 Total reward: 12.0 Training loss: 0.6342 Explore P: 0.8167
Episode: 2469 Total reward: 24.0 Training loss: 23.4006 Explore P: 0.8167
Episode: 2470 Total reward: 13.0 Training loss: 60.4594 Explore P: 0.8166
Episode: 2471 Total reward: 9.0 Training loss: 0.1313 Explore P: 0.8166
Episode: 2472 Total reward: 11.0 Training loss: 0.2562 Explore P: 0.8166
Episode: 2473 Total reward: 10.0 Training loss: 1.5810 Explore P: 0.8166
Episode: 2474 Total reward: 23.0 Training loss: 1.7537 Explore P: 0.8166
Episode: 2475 Total reward: 7.0 Training loss: 37.3376 Explore P: 0.8165
Episode: 2476 Total reward: 37.0 Training loss: 65.8235 Explore P: 0.8165
Episode: 2477 Total reward: 15.0 Training loss: 19.3144 Explore P: 0.8165
Episode: 2478 Total reward: 27.0 Training loss: 0.2097 Explore P: 0.8164
Episode: 2479 Total reward: 18.0 Training loss: 10.9514 Explore P: 0.8164
Episode: 2480 Total reward: 14.0 Training loss: 116.3097 Explore P: 0.8164
Episode: 2481 Total reward: 16.0 Training loss: 0.2281 Explore P: 0.8163
Episode: 2482 Total reward: 16.0 Training loss: 37.6325 Explore P: 0.8163
Episode: 2483 Total reward: 17.0 Training loss: 1.2371 Explore P: 0.8163
Episode: 2484 Total reward: 13.0 Training loss: 74.9038 Explore P: 0.8163
Episode: 2485 Total reward: 18.0 Training loss: 8.7581 Explore P: 0.8162
Episode: 2486 Total reward: 49.0 Training loss: 3.0948 Explore P: 0.8162
Episode: 2487 Total reward: 25.0 Training loss: 28.1293 Explore P: 0.8161
Episode: 2488 Total reward: 25.0 Training loss: 28.6795 Explore P: 0.8161
Episode: 2489 Total reward: 30.0 Training loss: 0.8382 Explore P: 0.8160
Episode: 2490 Total reward: 13.0 Training loss: 0.4132 Explore P: 0.8160
Episode: 2491 Total reward: 20.0 Training loss: 19.0066 Explore P: 0.8160
Episode: 2492 Total reward: 23.0 Training loss: 0.4664 Explore P: 0.8159
Episode: 2493 Total reward: 52.0 Training loss: 48.9497 Explore P: 0.8159
Episode: 2494 Total reward: 56.0 Training loss: 48.2981 Explore P: 0.8158
Episode: 2495 Total reward: 32.0 Training loss: 0.0942 Explore P: 0.8157
Episode: 2496 Total reward: 23.0 Training loss: 2.4914 Explore P: 0.8157
Episode: 2497 Total reward: 11.0 Training loss: 0.4751 Explore P: 0.8157
Episode: 2498 Total reward: 14.0 Training loss: 4.6870 Explore P: 0.8156
Episode: 2499 Total reward: 50.0 Training loss: 11.8896 Explore P: 0.8156
Episode: 2500 Total reward: 13.0 Training loss: 6.3320 Explore P: 0.8155
Episode: 2501 Total reward: 29.0 Training loss: 32.2864 Explore P: 0.8155
Episode: 2502 Total reward: 13.0 Training loss: 8.3828 Explore P: 0.8155
Episode: 2503 Total reward: 16.0 Training loss: 11.1333 Explore P: 0.8154
Episode: 2504 Total reward: 11.0 Training loss: 17.9291 Explore P: 0.8154
Episode: 2505 Total reward: 27.0 Training loss: 10.5976 Explore P: 0.8154
Episode: 2506 Total reward: 9.0 Training loss: 13.2882 Explore P: 0.8154
Episode: 2507 Total reward: 14.0 Training loss: 3.2147 Explore P: 0.8153
Episode: 2508 Total reward: 17.0 Training loss: 3.8877 Explore P: 0.8153
Episode: 2509 Total reward: 27.0 Training loss: 14.8539 Explore P: 0.8153
Episode: 2510 Total reward: 8.0 Training loss: 0.2508 Explore P: 0.8153
Episode: 2511 Total reward: 18.0 Training loss: 10.3533 Explore P: 0.8152
Episode: 2512 Total reward: 14.0 Training loss: 0.2881 Explore P: 0.8152
Episode: 2513 Total reward: 30.0 Training loss: 37.7819 Explore P: 0.8152
Episode: 2514 Total reward: 17.0 Training loss: 6.6640 Explore P: 0.8151
Episode: 2515 Total reward: 8.0 Training loss: 9.7244 Explore P: 0.8151
Episode: 2516 Total reward: 17.0 Training loss: 1.4247 Explore P: 0.8151
Episode: 2517 Total reward: 24.0 Training loss: 13.4736 Explore P: 0.8151
Episode: 2518 Total reward: 12.0 Training loss: 14.0816 Explore P: 0.8150
Episode: 2519 Total reward: 16.0 Training loss: 31.4374 Explore P: 0.8150
Episode: 2520 Total reward: 11.0 Training loss: 10.8125 Explore P: 0.8150
Episode: 2521 Total reward: 27.0 Training loss: 3.2406 Explore P: 0.8149
Episode: 2522 Total reward: 18.0 Training loss: 31.1808 Explore P: 0.8149
Episode: 2523 Total reward: 12.0 Training loss: 0.1670 Explore P: 0.8149
Episode: 2524 Total reward: 17.0 Training loss: 0.3304 Explore P: 0.8149
Episode: 2525 Total reward: 15.0 Training loss: 60.6615 Explore P: 0.8148
Episode: 2526 Total reward: 12.0 Training loss: 11.1205 Explore P: 0.8148
Episode: 2527 Total reward: 11.0 Training loss: 23.0467 Explore P: 0.8148
Episode: 2528 Total reward: 19.0 Training loss: 17.3149 Explore P: 0.8148
Episode: 2529 Total reward: 12.0 Training loss: 0.3163 Explore P: 0.8148
Episode: 2530 Total reward: 22.0 Training loss: 13.0408 Explore P: 0.8147
Episode: 2531 Total reward: 16.0 Training loss: 8.0137 Explore P: 0.8147
Episode: 2532 Total reward: 21.0 Training loss: 10.1559 Explore P: 0.8147
Episode: 2533 Total reward: 18.0 Training loss: 1.5413 Explore P: 0.8146
Episode: 2534 Total reward: 28.0 Training loss: 0.3459 Explore P: 0.8146
Episode: 2535 Total reward: 15.0 Training loss: 5.7809 Explore P: 0.8146
Episode: 2536 Total reward: 10.0 Training loss: 1.6637 Explore P: 0.8146
Episode: 2537 Total reward: 11.0 Training loss: 0.3408 Explore P: 0.8145
Episode: 2538 Total reward: 19.0 Training loss: 182.8884 Explore P: 0.8145
Episode: 2539 Total reward: 16.0 Training loss: 0.9770 Explore P: 0.8145
Episode: 2540 Total reward: 9.0 Training loss: 26.2508 Explore P: 0.8145
Episode: 2541 Total reward: 32.0 Training loss: 0.2165 Explore P: 0.8144
Episode: 2542 Total reward: 9.0 Training loss: 0.2929 Explore P: 0.8144
Episode: 2543 Total reward: 21.0 Training loss: 3.7056 Explore P: 0.8144
Episode: 2544 Total reward: 16.0 Training loss: 0.5431 Explore P: 0.8143
Episode: 2545 Total reward: 17.0 Training loss: 0.0624 Explore P: 0.8143
Episode: 2546 Total reward: 14.0 Training loss: 74.3567 Explore P: 0.8143
Episode: 2547 Total reward: 22.0 Training loss: 8.4944 Explore P: 0.8143
Episode: 2548 Total reward: 11.0 Training loss: 34.9174 Explore P: 0.8142
Episode: 2549 Total reward: 9.0 Training loss: 2.6456 Explore P: 0.8142
Episode: 2550 Total reward: 41.0 Training loss: 0.9769 Explore P: 0.8142
Episode: 2551 Total reward: 27.0 Training loss: 0.1136 Explore P: 0.8141
Episode: 2552 Total reward: 15.0 Training loss: 27.4969 Explore P: 0.8141
Episode: 2553 Total reward: 13.0 Training loss: 1.3036 Explore P: 0.8141
Episode: 2554 Total reward: 20.0 Training loss: 19.7067 Explore P: 0.8140
Episode: 2555 Total reward: 13.0 Training loss: 17.0983 Explore P: 0.8140
Episode: 2556 Total reward: 9.0 Training loss: 11.6311 Explore P: 0.8140
Episode: 2557 Total reward: 10.0 Training loss: 0.2825 Explore P: 0.8140
Episode: 2558 Total reward: 19.0 Training loss: 31.4143 Explore P: 0.8140
Episode: 2559 Total reward: 11.0 Training loss: 4.8783 Explore P: 0.8139
Episode: 2560 Total reward: 12.0 Training loss: 3.8717 Explore P: 0.8139
Episode: 2561 Total reward: 22.0 Training loss: 4.0469 Explore P: 0.8139
Episode: 2562 Total reward: 12.0 Training loss: 24.1664 Explore P: 0.8139
Episode: 2563 Total reward: 13.0 Training loss: 23.3392 Explore P: 0.8138
Episode: 2564 Total reward: 13.0 Training loss: 45.0663 Explore P: 0.8138
Episode: 2565 Total reward: 18.0 Training loss: 23.4671 Explore P: 0.8138
Episode: 2566 Total reward: 9.0 Training loss: 71.1857 Explore P: 0.8138
Episode: 2567 Total reward: 21.0 Training loss: 12.3585 Explore P: 0.8137
Episode: 2568 Total reward: 20.0 Training loss: 29.5883 Explore P: 0.8137
Episode: 2569 Total reward: 41.0 Training loss: 2.2664 Explore P: 0.8136
Episode: 2570 Total reward: 18.0 Training loss: 4.6148 Explore P: 0.8136
Episode: 2571 Total reward: 21.0 Training loss: 5.6117 Explore P: 0.8136
Episode: 2572 Total reward: 14.0 Training loss: 0.5234 Explore P: 0.8136
Episode: 2573 Total reward: 16.0 Training loss: 0.1644 Explore P: 0.8135
Episode: 2574 Total reward: 13.0 Training loss: 0.2439 Explore P: 0.8135
Episode: 2575 Total reward: 11.0 Training loss: 22.2771 Explore P: 0.8135
Episode: 2576 Total reward: 11.0 Training loss: 10.4412 Explore P: 0.8135
Episode: 2577 Total reward: 26.0 Training loss: 4.9145 Explore P: 0.8134
Episode: 2578 Total reward: 15.0 Training loss: 16.0352 Explore P: 0.8134
Episode: 2579 Total reward: 10.0 Training loss: 18.7500 Explore P: 0.8134
Episode: 2580 Total reward: 20.0 Training loss: 0.7269 Explore P: 0.8134
Episode: 2581 Total reward: 10.0 Training loss: 1.5268 Explore P: 0.8133
Episode: 2582 Total reward: 46.0 Training loss: 0.7760 Explore P: 0.8133
Episode: 2583 Total reward: 14.0 Training loss: 0.2337 Explore P: 0.8132
Episode: 2584 Total reward: 13.0 Training loss: 6.0836 Explore P: 0.8132
Episode: 2585 Total reward: 13.0 Training loss: 2.2380 Explore P: 0.8132
Episode: 2586 Total reward: 39.0 Training loss: 4.4347 Explore P: 0.8131
Episode: 2587 Total reward: 11.0 Training loss: 14.9861 Explore P: 0.8131
Episode: 2588 Total reward: 13.0 Training loss: 1.0008 Explore P: 0.8131
Episode: 2589 Total reward: 27.0 Training loss: 0.7160 Explore P: 0.8131
Episode: 2590 Total reward: 18.0 Training loss: 2.1739 Explore P: 0.8130
Episode: 2591 Total reward: 9.0 Training loss: 17.9284 Explore P: 0.8130
Episode: 2592 Total reward: 15.0 Training loss: 14.5038 Explore P: 0.8130
Episode: 2593 Total reward: 30.0 Training loss: 0.3566 Explore P: 0.8129
Episode: 2594 Total reward: 30.0 Training loss: 4.3788 Explore P: 0.8129
Episode: 2595 Total reward: 20.0 Training loss: 86.0535 Explore P: 0.8129
Episode: 2596 Total reward: 11.0 Training loss: 0.8323 Explore P: 0.8128
Episode: 2597 Total reward: 11.0 Training loss: 0.3115 Explore P: 0.8128
Episode: 2598 Total reward: 18.0 Training loss: 0.1404 Explore P: 0.8128
Episode: 2599 Total reward: 19.0 Training loss: 4.2427 Explore P: 0.8128
Episode: 2600 Total reward: 16.0 Training loss: 10.3658 Explore P: 0.8127
Episode: 2601 Total reward: 9.0 Training loss: 3.5543 Explore P: 0.8127
Episode: 2602 Total reward: 40.0 Training loss: 32.6873 Explore P: 0.8127
Episode: 2603 Total reward: 10.0 Training loss: 0.1760 Explore P: 0.8127
Episode: 2604 Total reward: 14.0 Training loss: 31.1162 Explore P: 0.8126
Episode: 2605 Total reward: 44.0 Training loss: 0.9437 Explore P: 0.8126
Episode: 2606 Total reward: 13.0 Training loss: 0.1533 Explore P: 0.8125
Episode: 2607 Total reward: 29.0 Training loss: 19.2653 Explore P: 0.8125
Episode: 2608 Total reward: 39.0 Training loss: 1.0638 Explore P: 0.8124
Episode: 2609 Total reward: 28.0 Training loss: 0.8096 Explore P: 0.8124
Episode: 2610 Total reward: 10.0 Training loss: 0.1580 Explore P: 0.8124
Episode: 2611 Total reward: 42.0 Training loss: 0.1133 Explore P: 0.8123
Episode: 2612 Total reward: 33.0 Training loss: 2.3587 Explore P: 0.8122
Episode: 2613 Total reward: 44.0 Training loss: 36.3968 Explore P: 0.8122
Episode: 2614 Total reward: 8.0 Training loss: 20.4490 Explore P: 0.8122
Episode: 2615 Total reward: 45.0 Training loss: 65.5915 Explore P: 0.8121
Episode: 2616 Total reward: 12.0 Training loss: 1.4027 Explore P: 0.8121
Episode: 2617 Total reward: 57.0 Training loss: 11.0494 Explore P: 0.8120
Episode: 2618 Total reward: 16.0 Training loss: 5.6246 Explore P: 0.8120
Episode: 2619 Total reward: 11.0 Training loss: 53.1875 Explore P: 0.8119
Episode: 2620 Total reward: 36.0 Training loss: 3.3537 Explore P: 0.8119
Episode: 2621 Total reward: 23.0 Training loss: 0.1399 Explore P: 0.8118
Episode: 2622 Total reward: 16.0 Training loss: 2.8781 Explore P: 0.8118
Episode: 2623 Total reward: 17.0 Training loss: 22.8355 Explore P: 0.8118
Episode: 2624 Total reward: 10.0 Training loss: 1.5100 Explore P: 0.8118
Episode: 2625 Total reward: 42.0 Training loss: 42.4210 Explore P: 0.8117
Episode: 2626 Total reward: 13.0 Training loss: 6.1803 Explore P: 0.8117
Episode: 2627 Total reward: 15.0 Training loss: 38.5589 Explore P: 0.8117
Episode: 2628 Total reward: 13.0 Training loss: 0.1898 Explore P: 0.8116
Episode: 2629 Total reward: 9.0 Training loss: 8.7996 Explore P: 0.8116
Episode: 2630 Total reward: 14.0 Training loss: 0.2812 Explore P: 0.8116
Episode: 2631 Total reward: 16.0 Training loss: 56.0119 Explore P: 0.8116
Episode: 2632 Total reward: 19.0 Training loss: 0.1757 Explore P: 0.8115
Episode: 2633 Total reward: 13.0 Training loss: 39.5266 Explore P: 0.8115
Episode: 2634 Total reward: 10.0 Training loss: 4.2458 Explore P: 0.8115
Episode: 2635 Total reward: 21.0 Training loss: 4.3114 Explore P: 0.8115
Episode: 2636 Total reward: 16.0 Training loss: 0.9817 Explore P: 0.8115
Episode: 2637 Total reward: 12.0 Training loss: 0.5527 Explore P: 0.8114
Episode: 2638 Total reward: 13.0 Training loss: 10.4985 Explore P: 0.8114
Episode: 2639 Total reward: 21.0 Training loss: 13.4498 Explore P: 0.8114
Episode: 2640 Total reward: 10.0 Training loss: 0.1267 Explore P: 0.8114
Episode: 2641 Total reward: 95.0 Training loss: 0.0675 Explore P: 0.8112
Episode: 2642 Total reward: 10.0 Training loss: 0.5441 Explore P: 0.8112
Episode: 2643 Total reward: 10.0 Training loss: 146.5647 Explore P: 0.8112
Episode: 2644 Total reward: 7.0 Training loss: 2.6412 Explore P: 0.8112
Episode: 2645 Total reward: 16.0 Training loss: 32.3633 Explore P: 0.8111
Episode: 2646 Total reward: 37.0 Training loss: 1.6414 Explore P: 0.8111
Episode: 2647 Total reward: 9.0 Training loss: 0.3428 Explore P: 0.8111
Episode: 2648 Total reward: 16.0 Training loss: 5.6056 Explore P: 0.8110
Episode: 2649 Total reward: 17.0 Training loss: 7.8191 Explore P: 0.8110
Episode: 2650 Total reward: 14.0 Training loss: 0.1530 Explore P: 0.8110
Episode: 2651 Total reward: 11.0 Training loss: 0.1974 Explore P: 0.8110
Episode: 2652 Total reward: 20.0 Training loss: 140.4255 Explore P: 0.8109
Episode: 2653 Total reward: 18.0 Training loss: 1.6549 Explore P: 0.8109
Episode: 2654 Total reward: 16.0 Training loss: 0.1119 Explore P: 0.8109
Episode: 2655 Total reward: 18.0 Training loss: 17.4858 Explore P: 0.8109
Episode: 2656 Total reward: 22.0 Training loss: 1.4685 Explore P: 0.8108
Episode: 2657 Total reward: 12.0 Training loss: 3.6762 Explore P: 0.8108
Episode: 2658 Total reward: 16.0 Training loss: 3.8617 Explore P: 0.8108
Episode: 2659 Total reward: 46.0 Training loss: 6.5345 Explore P: 0.8107
Episode: 2660 Total reward: 12.0 Training loss: 3.2517 Explore P: 0.8107
Episode: 2661 Total reward: 30.0 Training loss: 21.2064 Explore P: 0.8106
Episode: 2662 Total reward: 9.0 Training loss: 0.1991 Explore P: 0.8106
Episode: 2663 Total reward: 39.0 Training loss: 3.2998 Explore P: 0.8106
Episode: 2664 Total reward: 22.0 Training loss: 0.1734 Explore P: 0.8105
Episode: 2665 Total reward: 13.0 Training loss: 0.1393 Explore P: 0.8105
Episode: 2666 Total reward: 34.0 Training loss: 15.6416 Explore P: 0.8105
Episode: 2667 Total reward: 10.0 Training loss: 31.5238 Explore P: 0.8104
Episode: 2668 Total reward: 21.0 Training loss: 116.1929 Explore P: 0.8104
Episode: 2669 Total reward: 10.0 Training loss: 36.4270 Explore P: 0.8104
Episode: 2670 Total reward: 16.0 Training loss: 40.6950 Explore P: 0.8104
Episode: 2671 Total reward: 12.0 Training loss: 29.8927 Explore P: 0.8103
Episode: 2672 Total reward: 8.0 Training loss: 73.7125 Explore P: 0.8103
Episode: 2673 Total reward: 13.0 Training loss: 68.3012 Explore P: 0.8103
Episode: 2674 Total reward: 30.0 Training loss: 0.2247 Explore P: 0.8103
Episode: 2675 Total reward: 13.0 Training loss: 481.7385 Explore P: 0.8102
Episode: 2676 Total reward: 10.0 Training loss: 0.6491 Explore P: 0.8102
Episode: 2677 Total reward: 14.0 Training loss: 0.3524 Explore P: 0.8102
Episode: 2678 Total reward: 19.0 Training loss: 0.2023 Explore P: 0.8102
Episode: 2679 Total reward: 26.0 Training loss: 15.3079 Explore P: 0.8101
Episode: 2680 Total reward: 10.0 Training loss: 90.5868 Explore P: 0.8101
Episode: 2681 Total reward: 24.0 Training loss: 1.5105 Explore P: 0.8101
Episode: 2682 Total reward: 12.0 Training loss: 1.5250 Explore P: 0.8101
Episode: 2683 Total reward: 34.0 Training loss: 0.1567 Explore P: 0.8100
Episode: 2684 Total reward: 18.0 Training loss: 11.4271 Explore P: 0.8100
Episode: 2685 Total reward: 23.0 Training loss: 8.6647 Explore P: 0.8099
Episode: 2686 Total reward: 15.0 Training loss: 3.4855 Explore P: 0.8099
Episode: 2687 Total reward: 13.0 Training loss: 24.1225 Explore P: 0.8099
Episode: 2688 Total reward: 15.0 Training loss: 31.3919 Explore P: 0.8099
Episode: 2689 Total reward: 24.0 Training loss: 0.8357 Explore P: 0.8098
Episode: 2690 Total reward: 12.0 Training loss: 0.0857 Explore P: 0.8098
Episode: 2691 Total reward: 15.0 Training loss: 0.6709 Explore P: 0.8098
Episode: 2692 Total reward: 15.0 Training loss: 13.9013 Explore P: 0.8098
Episode: 2693 Total reward: 11.0 Training loss: 0.1967 Explore P: 0.8097
Episode: 2694 Total reward: 11.0 Training loss: 0.2756 Explore P: 0.8097
Episode: 2695 Total reward: 21.0 Training loss: 0.5280 Explore P: 0.8097
Episode: 2696 Total reward: 29.0 Training loss: 6.4415 Explore P: 0.8096
Episode: 2697 Total reward: 10.0 Training loss: 0.1034 Explore P: 0.8096
Episode: 2698 Total reward: 22.0 Training loss: 3.0438 Explore P: 0.8096
Episode: 2699 Total reward: 19.0 Training loss: 21.3746 Explore P: 0.8096
Episode: 2700 Total reward: 17.0 Training loss: 62.8330 Explore P: 0.8095
Episode: 2701 Total reward: 12.0 Training loss: 11.8582 Explore P: 0.8095
Episode: 2702 Total reward: 14.0 Training loss: 56.7232 Explore P: 0.8095
Episode: 2703 Total reward: 15.0 Training loss: 16.6542 Explore P: 0.8095
Episode: 2704 Total reward: 24.0 Training loss: 187.9161 Explore P: 0.8094
Episode: 2705 Total reward: 25.0 Training loss: 29.8884 Explore P: 0.8094
Episode: 2706 Total reward: 14.0 Training loss: 0.2293 Explore P: 0.8094
Episode: 2707 Total reward: 26.0 Training loss: 9.7240 Explore P: 0.8093
Episode: 2708 Total reward: 17.0 Training loss: 6.3548 Explore P: 0.8093
Episode: 2709 Total reward: 15.0 Training loss: 22.3719 Explore P: 0.8093
Episode: 2710 Total reward: 38.0 Training loss: 2.1822 Explore P: 0.8092
Episode: 2711 Total reward: 15.0 Training loss: 52.6207 Explore P: 0.8092
Episode: 2712 Total reward: 19.0 Training loss: 0.1317 Explore P: 0.8092
Episode: 2713 Total reward: 36.0 Training loss: 0.8473 Explore P: 0.8091
Episode: 2714 Total reward: 11.0 Training loss: 22.7869 Explore P: 0.8091
Episode: 2715 Total reward: 16.0 Training loss: 0.1009 Explore P: 0.8091
Episode: 2716 Total reward: 13.0 Training loss: 1.2978 Explore P: 0.8090
Episode: 2717 Total reward: 26.0 Training loss: 38.0862 Explore P: 0.8090
Episode: 2718 Total reward: 25.0 Training loss: 17.4410 Explore P: 0.8090
Episode: 2719 Total reward: 34.0 Training loss: 3.0443 Explore P: 0.8089
Episode: 2720 Total reward: 26.0 Training loss: 51.7800 Explore P: 0.8089
Episode: 2721 Total reward: 18.0 Training loss: 519.1772 Explore P: 0.8088
Episode: 2722 Total reward: 16.0 Training loss: 13.1225 Explore P: 0.8088
Episode: 2723 Total reward: 12.0 Training loss: 48.4693 Explore P: 0.8088
Episode: 2724 Total reward: 40.0 Training loss: 0.3273 Explore P: 0.8087
Episode: 2725 Total reward: 24.0 Training loss: 17.5748 Explore P: 0.8087
Episode: 2726 Total reward: 41.0 Training loss: 5.2255 Explore P: 0.8086
Episode: 2727 Total reward: 16.0 Training loss: 2.7081 Explore P: 0.8086
Episode: 2728 Total reward: 21.0 Training loss: 67.9945 Explore P: 0.8086
Episode: 2729 Total reward: 13.0 Training loss: 14.0184 Explore P: 0.8085
Episode: 2730 Total reward: 12.0 Training loss: 14.3165 Explore P: 0.8085
Episode: 2731 Total reward: 19.0 Training loss: 13.7447 Explore P: 0.8085
Episode: 2732 Total reward: 15.0 Training loss: 0.1966 Explore P: 0.8085
Episode: 2733 Total reward: 10.0 Training loss: 15.9703 Explore P: 0.8085
Episode: 2734 Total reward: 11.0 Training loss: 20.6287 Explore P: 0.8084
Episode: 2735 Total reward: 37.0 Training loss: 0.1580 Explore P: 0.8084
Episode: 2736 Total reward: 12.0 Training loss: 0.5040 Explore P: 0.8084
Episode: 2737 Total reward: 29.0 Training loss: 0.4289 Explore P: 0.8083
Episode: 2738 Total reward: 15.0 Training loss: 6.4580 Explore P: 0.8083
Episode: 2739 Total reward: 16.0 Training loss: 225.1462 Explore P: 0.8083
Episode: 2740 Total reward: 48.0 Training loss: 9.5838 Explore P: 0.8082
Episode: 2741 Total reward: 13.0 Training loss: 1.4932 Explore P: 0.8082
Episode: 2742 Total reward: 11.0 Training loss: 22.2375 Explore P: 0.8081
Episode: 2743 Total reward: 42.0 Training loss: 3.1639 Explore P: 0.8081
Episode: 2744 Total reward: 25.0 Training loss: 44.8139 Explore P: 0.8080
Episode: 2745 Total reward: 30.0 Training loss: 0.2503 Explore P: 0.8080
Episode: 2746 Total reward: 14.0 Training loss: 0.4569 Explore P: 0.8080
Episode: 2747 Total reward: 21.0 Training loss: 0.4703 Explore P: 0.8079
Episode: 2748 Total reward: 16.0 Training loss: 0.1543 Explore P: 0.8079
Episode: 2749 Total reward: 10.0 Training loss: 0.2124 Explore P: 0.8079
Episode: 2750 Total reward: 13.0 Training loss: 0.0784 Explore P: 0.8079
Episode: 2751 Total reward: 12.0 Training loss: 93.5702 Explore P: 0.8079
Episode: 2752 Total reward: 15.0 Training loss: 94.9451 Explore P: 0.8078
Episode: 2753 Total reward: 15.0 Training loss: 0.2984 Explore P: 0.8078
Episode: 2754 Total reward: 17.0 Training loss: 14.5958 Explore P: 0.8078
Episode: 2755 Total reward: 14.0 Training loss: 65.9009 Explore P: 0.8078
Episode: 2756 Total reward: 9.0 Training loss: 0.2991 Explore P: 0.8077
Episode: 2757 Total reward: 18.0 Training loss: 0.1999 Explore P: 0.8077
Episode: 2758 Total reward: 13.0 Training loss: 3.9251 Explore P: 0.8077
Episode: 2759 Total reward: 14.0 Training loss: 0.3175 Explore P: 0.8077
Episode: 2760 Total reward: 8.0 Training loss: 6.7064 Explore P: 0.8077
Episode: 2761 Total reward: 34.0 Training loss: 151.3750 Explore P: 0.8076
Episode: 2762 Total reward: 12.0 Training loss: 0.1318 Explore P: 0.8076
Episode: 2763 Total reward: 10.0 Training loss: 1.7542 Explore P: 0.8076
Episode: 2764 Total reward: 9.0 Training loss: 1.5952 Explore P: 0.8076
Episode: 2765 Total reward: 16.0 Training loss: 0.2504 Explore P: 0.8075
Episode: 2766 Total reward: 13.0 Training loss: 2.9129 Explore P: 0.8075
Episode: 2767 Total reward: 10.0 Training loss: 16.6052 Explore P: 0.8075
Episode: 2768 Total reward: 13.0 Training loss: 0.3162 Explore P: 0.8075
Episode: 2769 Total reward: 19.0 Training loss: 8.6525 Explore P: 0.8074
Episode: 2770 Total reward: 10.0 Training loss: 10.6831 Explore P: 0.8074
Episode: 2771 Total reward: 10.0 Training loss: 0.1762 Explore P: 0.8074
Episode: 2772 Total reward: 8.0 Training loss: 0.2860 Explore P: 0.8074
Episode: 2773 Total reward: 12.0 Training loss: 54.8457 Explore P: 0.8074
Episode: 2774 Total reward: 20.0 Training loss: 17.2152 Explore P: 0.8073
Episode: 2775 Total reward: 9.0 Training loss: 1.5078 Explore P: 0.8073
Episode: 2776 Total reward: 37.0 Training loss: 32.6221 Explore P: 0.8073
Episode: 2777 Total reward: 54.0 Training loss: 7.5720 Explore P: 0.8072
Episode: 2778 Total reward: 16.0 Training loss: 4.6367 Explore P: 0.8072
Episode: 2779 Total reward: 10.0 Training loss: 3.4603 Explore P: 0.8071
Episode: 2780 Total reward: 12.0 Training loss: 27.5961 Explore P: 0.8071
Episode: 2781 Total reward: 21.0 Training loss: 28.0740 Explore P: 0.8071
Episode: 2782 Total reward: 21.0 Training loss: 12.5776 Explore P: 0.8071
Episode: 2783 Total reward: 17.0 Training loss: 73.6784 Explore P: 0.8070
Episode: 2784 Total reward: 14.0 Training loss: 420.5082 Explore P: 0.8070
Episode: 2785 Total reward: 16.0 Training loss: 44.6571 Explore P: 0.8070
Episode: 2786 Total reward: 11.0 Training loss: 0.3533 Explore P: 0.8070
Episode: 2787 Total reward: 14.0 Training loss: 14.9614 Explore P: 0.8069
Episode: 2788 Total reward: 60.0 Training loss: 16.3133 Explore P: 0.8068
Episode: 2789 Total reward: 17.0 Training loss: 4.1342 Explore P: 0.8068
Episode: 2790 Total reward: 31.0 Training loss: 41.6851 Explore P: 0.8068
Episode: 2791 Total reward: 12.0 Training loss: 30.8346 Explore P: 0.8068
Episode: 2792 Total reward: 12.0 Training loss: 54.3869 Explore P: 0.8067
Episode: 2793 Total reward: 19.0 Training loss: 6.5813 Explore P: 0.8067
Episode: 2794 Total reward: 15.0 Training loss: 9.4585 Explore P: 0.8067
Episode: 2795 Total reward: 11.0 Training loss: 0.1903 Explore P: 0.8067
Episode: 2796 Total reward: 25.0 Training loss: 4.3962 Explore P: 0.8066
Episode: 2797 Total reward: 13.0 Training loss: 0.1827 Explore P: 0.8066
Episode: 2798 Total reward: 31.0 Training loss: 4.7332 Explore P: 0.8066
Episode: 2799 Total reward: 15.0 Training loss: 27.9261 Explore P: 0.8065
Episode: 2800 Total reward: 13.0 Training loss: 2.0179 Explore P: 0.8065
Episode: 2801 Total reward: 17.0 Training loss: 0.0881 Explore P: 0.8065
Episode: 2802 Total reward: 21.0 Training loss: 0.2680 Explore P: 0.8064
Episode: 2803 Total reward: 38.0 Training loss: 5.5317 Explore P: 0.8064
Episode: 2804 Total reward: 20.0 Training loss: 92.7343 Explore P: 0.8064
Episode: 2805 Total reward: 15.0 Training loss: 0.5888 Explore P: 0.8063
Episode: 2806 Total reward: 13.0 Training loss: 0.2899 Explore P: 0.8063
Episode: 2807 Total reward: 25.0 Training loss: 14.7338 Explore P: 0.8063
Episode: 2808 Total reward: 13.0 Training loss: 9.7740 Explore P: 0.8062
Episode: 2809 Total reward: 12.0 Training loss: 0.2106 Explore P: 0.8062
Episode: 2810 Total reward: 26.0 Training loss: 6.6439 Explore P: 0.8062
Episode: 2811 Total reward: 33.0 Training loss: 0.4298 Explore P: 0.8061
Episode: 2812 Total reward: 15.0 Training loss: 0.2782 Explore P: 0.8061
Episode: 2813 Total reward: 11.0 Training loss: 2.9927 Explore P: 0.8061
Episode: 2814 Total reward: 30.0 Training loss: 26.4795 Explore P: 0.8060
Episode: 2815 Total reward: 12.0 Training loss: 0.4263 Explore P: 0.8060
Episode: 2816 Total reward: 49.0 Training loss: 30.6101 Explore P: 0.8059
Episode: 2817 Total reward: 13.0 Training loss: 0.4849 Explore P: 0.8059
Episode: 2818 Total reward: 16.0 Training loss: 0.1948 Explore P: 0.8059
Episode: 2819 Total reward: 14.0 Training loss: 0.1171 Explore P: 0.8059
Episode: 2820 Total reward: 19.0 Training loss: 0.6734 Explore P: 0.8059
Episode: 2821 Total reward: 57.0 Training loss: 0.1629 Explore P: 0.8058
Episode: 2822 Total reward: 11.0 Training loss: 187.7416 Explore P: 0.8057
Episode: 2823 Total reward: 10.0 Training loss: 0.1667 Explore P: 0.8057
Episode: 2824 Total reward: 9.0 Training loss: 1.7535 Explore P: 0.8057
Episode: 2825 Total reward: 12.0 Training loss: 46.1823 Explore P: 0.8057
Episode: 2826 Total reward: 35.0 Training loss: 11.7175 Explore P: 0.8056
Episode: 2827 Total reward: 17.0 Training loss: 14.3227 Explore P: 0.8056
Episode: 2828 Total reward: 10.0 Training loss: 1.9969 Explore P: 0.8056
Episode: 2829 Total reward: 17.0 Training loss: 1.4392 Explore P: 0.8056
Episode: 2830 Total reward: 11.0 Training loss: 13.8338 Explore P: 0.8055
Episode: 2831 Total reward: 29.0 Training loss: 1.9891 Explore P: 0.8055
Episode: 2832 Total reward: 10.0 Training loss: 49.9806 Explore P: 0.8055
Episode: 2833 Total reward: 28.0 Training loss: 0.0768 Explore P: 0.8054
Episode: 2834 Total reward: 29.0 Training loss: 0.5055 Explore P: 0.8054
Episode: 2835 Total reward: 15.0 Training loss: 0.0838 Explore P: 0.8054
Episode: 2836 Total reward: 69.0 Training loss: 1.4162 Explore P: 0.8053
Episode: 2837 Total reward: 23.0 Training loss: 14.2819 Explore P: 0.8052
Episode: 2838 Total reward: 17.0 Training loss: 10.8370 Explore P: 0.8052
Episode: 2839 Total reward: 17.0 Training loss: 0.1733 Explore P: 0.8052
Episode: 2840 Total reward: 19.0 Training loss: 139.4582 Explore P: 0.8051
Episode: 2841 Total reward: 102.0 Training loss: 1.2215 Explore P: 0.8050
Episode: 2842 Total reward: 19.0 Training loss: 7.6527 Explore P: 0.8050
Episode: 2843 Total reward: 19.0 Training loss: 10.0555 Explore P: 0.8049
Episode: 2844 Total reward: 14.0 Training loss: 5.0491 Explore P: 0.8049
Episode: 2845 Total reward: 15.0 Training loss: 4.6692 Explore P: 0.8049
Episode: 2846 Total reward: 18.0 Training loss: 49.0341 Explore P: 0.8048
Episode: 2847 Total reward: 14.0 Training loss: 0.1101 Explore P: 0.8048
Episode: 2848 Total reward: 18.0 Training loss: 32.5666 Explore P: 0.8048
Episode: 2849 Total reward: 19.0 Training loss: 73.6796 Explore P: 0.8048
Episode: 2850 Total reward: 20.0 Training loss: 2.9781 Explore P: 0.8047
Episode: 2851 Total reward: 30.0 Training loss: 38.9797 Explore P: 0.8047
Episode: 2852 Total reward: 9.0 Training loss: 0.5035 Explore P: 0.8047
Episode: 2853 Total reward: 30.0 Training loss: 22.5921 Explore P: 0.8046
Episode: 2854 Total reward: 43.0 Training loss: 65.3598 Explore P: 0.8046
Episode: 2855 Total reward: 13.0 Training loss: 4.6804 Explore P: 0.8045
Episode: 2856 Total reward: 17.0 Training loss: 5.2033 Explore P: 0.8045
Episode: 2857 Total reward: 15.0 Training loss: 7.3737 Explore P: 0.8045
Episode: 2858 Total reward: 14.0 Training loss: 26.3031 Explore P: 0.8045
Episode: 2859 Total reward: 9.0 Training loss: 0.1420 Explore P: 0.8044
Episode: 2860 Total reward: 22.0 Training loss: 3.5386 Explore P: 0.8044
Episode: 2861 Total reward: 13.0 Training loss: 5.8760 Explore P: 0.8044
Episode: 2862 Total reward: 16.0 Training loss: 18.4724 Explore P: 0.8044
Episode: 2863 Total reward: 9.0 Training loss: 0.5917 Explore P: 0.8044
Episode: 2864 Total reward: 32.0 Training loss: 0.2409 Explore P: 0.8043
Episode: 2865 Total reward: 25.0 Training loss: 0.1873 Explore P: 0.8043
Episode: 2866 Total reward: 15.0 Training loss: 3.3136 Explore P: 0.8042
Episode: 2867 Total reward: 23.0 Training loss: 3.3942 Explore P: 0.8042
Episode: 2868 Total reward: 15.0 Training loss: 0.2027 Explore P: 0.8042
Episode: 2869 Total reward: 26.0 Training loss: 29.8413 Explore P: 0.8041
Episode: 2870 Total reward: 18.0 Training loss: 49.7579 Explore P: 0.8041
Episode: 2871 Total reward: 15.0 Training loss: 0.1072 Explore P: 0.8041
Episode: 2872 Total reward: 41.0 Training loss: 0.1261 Explore P: 0.8040
Episode: 2873 Total reward: 11.0 Training loss: 0.8955 Explore P: 0.8040
Episode: 2874 Total reward: 13.0 Training loss: 0.3679 Explore P: 0.8040
Episode: 2875 Total reward: 17.0 Training loss: 122.7745 Explore P: 0.8040
Episode: 2876 Total reward: 25.0 Training loss: 1.3134 Explore P: 0.8039
Episode: 2877 Total reward: 14.0 Training loss: 10.8254 Explore P: 0.8039
Episode: 2878 Total reward: 10.0 Training loss: 27.9368 Explore P: 0.8039
Episode: 2879 Total reward: 37.0 Training loss: 0.7177 Explore P: 0.8038
Episode: 2880 Total reward: 13.0 Training loss: 19.1786 Explore P: 0.8038
Episode: 2881 Total reward: 15.0 Training loss: 0.1475 Explore P: 0.8038
Episode: 2882 Total reward: 32.0 Training loss: 20.3356 Explore P: 0.8037
Episode: 2883 Total reward: 22.0 Training loss: 0.8064 Explore P: 0.8037
Episode: 2884 Total reward: 12.0 Training loss: 6.3819 Explore P: 0.8037
Episode: 2885 Total reward: 18.0 Training loss: 9.3738 Explore P: 0.8036
Episode: 2886 Total reward: 12.0 Training loss: 5.8573 Explore P: 0.8036
Episode: 2887 Total reward: 23.0 Training loss: 21.2740 Explore P: 0.8036
Episode: 2888 Total reward: 13.0 Training loss: 13.1390 Explore P: 0.8036
Episode: 2889 Total reward: 19.0 Training loss: 0.2502 Explore P: 0.8035
Episode: 2890 Total reward: 53.0 Training loss: 0.2434 Explore P: 0.8034
Episode: 2891 Total reward: 33.0 Training loss: 0.2065 Explore P: 0.8034
Episode: 2892 Total reward: 32.0 Training loss: 59.4633 Explore P: 0.8033
Episode: 2893 Total reward: 21.0 Training loss: 6.8391 Explore P: 0.8033
Episode: 2894 Total reward: 21.0 Training loss: 0.2614 Explore P: 0.8033
Episode: 2895 Total reward: 13.0 Training loss: 47.3930 Explore P: 0.8033
Episode: 2896 Total reward: 16.0 Training loss: 39.0267 Explore P: 0.8032
Episode: 2897 Total reward: 12.0 Training loss: 8.0527 Explore P: 0.8032
Episode: 2898 Total reward: 11.0 Training loss: 4.4459 Explore P: 0.8032
Episode: 2899 Total reward: 18.0 Training loss: 4.3409 Explore P: 0.8032
Episode: 2900 Total reward: 15.0 Training loss: 51.8199 Explore P: 0.8031
Episode: 2901 Total reward: 8.0 Training loss: 0.1317 Explore P: 0.8031
Episode: 2902 Total reward: 11.0 Training loss: 13.7977 Explore P: 0.8031
Episode: 2903 Total reward: 34.0 Training loss: 2.9636 Explore P: 0.8031
Episode: 2904 Total reward: 16.0 Training loss: 0.1515 Explore P: 0.8030
Episode: 2905 Total reward: 15.0 Training loss: 0.1920 Explore P: 0.8030
Episode: 2906 Total reward: 23.0 Training loss: 0.9489 Explore P: 0.8030
Episode: 2907 Total reward: 12.0 Training loss: 23.1176 Explore P: 0.8030
Episode: 2908 Total reward: 15.0 Training loss: 7.4907 Explore P: 0.8029
Episode: 2909 Total reward: 38.0 Training loss: 0.1771 Explore P: 0.8029
Episode: 2910 Total reward: 19.0 Training loss: 1.1001 Explore P: 0.8028
Episode: 2911 Total reward: 9.0 Training loss: 0.2033 Explore P: 0.8028
Episode: 2912 Total reward: 11.0 Training loss: 51.8428 Explore P: 0.8028
Episode: 2913 Total reward: 55.0 Training loss: 0.2039 Explore P: 0.8027
Episode: 2914 Total reward: 30.0 Training loss: 28.7167 Explore P: 0.8027
Episode: 2915 Total reward: 45.0 Training loss: 1.8674 Explore P: 0.8026
Episode: 2916 Total reward: 11.0 Training loss: 0.2006 Explore P: 0.8026
Episode: 2917 Total reward: 13.0 Training loss: 9.0012 Explore P: 0.8026
Episode: 2918 Total reward: 20.0 Training loss: 15.6092 Explore P: 0.8025
Episode: 2919 Total reward: 11.0 Training loss: 0.2573 Explore P: 0.8025
Episode: 2920 Total reward: 43.0 Training loss: 20.5750 Explore P: 0.8024
Episode: 2921 Total reward: 12.0 Training loss: 0.1303 Explore P: 0.8024
Episode: 2922 Total reward: 12.0 Training loss: 55.0238 Explore P: 0.8024
Episode: 2923 Total reward: 11.0 Training loss: 47.2968 Explore P: 0.8024
Episode: 2924 Total reward: 12.0 Training loss: 41.8019 Explore P: 0.8024
Episode: 2925 Total reward: 19.0 Training loss: 11.6310 Explore P: 0.8023
Episode: 2926 Total reward: 14.0 Training loss: 13.3566 Explore P: 0.8023
Episode: 2927 Total reward: 11.0 Training loss: 3.0942 Explore P: 0.8023
Episode: 2928 Total reward: 25.0 Training loss: 0.2146 Explore P: 0.8023
Episode: 2929 Total reward: 12.0 Training loss: 7.0896 Explore P: 0.8022
Episode: 2930 Total reward: 8.0 Training loss: 13.5468 Explore P: 0.8022
Episode: 2931 Total reward: 23.0 Training loss: 44.6183 Explore P: 0.8022
Episode: 2932 Total reward: 11.0 Training loss: 28.4878 Explore P: 0.8022
Episode: 2933 Total reward: 12.0 Training loss: 13.6119 Explore P: 0.8022
Episode: 2934 Total reward: 11.0 Training loss: 122.5778 Explore P: 0.8021
Episode: 2935 Total reward: 27.0 Training loss: 3.4460 Explore P: 0.8021
Episode: 2936 Total reward: 34.0 Training loss: 5.8704 Explore P: 0.8020
Episode: 2937 Total reward: 22.0 Training loss: 8.8496 Explore P: 0.8020
Episode: 2938 Total reward: 8.0 Training loss: 26.3095 Explore P: 0.8020
Episode: 2939 Total reward: 14.0 Training loss: 13.6574 Explore P: 0.8020
Episode: 2940 Total reward: 16.0 Training loss: 0.0927 Explore P: 0.8019
Episode: 2941 Total reward: 11.0 Training loss: 0.2154 Explore P: 0.8019
Episode: 2942 Total reward: 11.0 Training loss: 1.1396 Explore P: 0.8019
Episode: 2943 Total reward: 16.0 Training loss: 0.2602 Explore P: 0.8019
Episode: 2944 Total reward: 13.0 Training loss: 1.9593 Explore P: 0.8019
Episode: 2945 Total reward: 21.0 Training loss: 31.1674 Explore P: 0.8018
Episode: 2946 Total reward: 11.0 Training loss: 1.5800 Explore P: 0.8018
Episode: 2947 Total reward: 14.0 Training loss: 0.3559 Explore P: 0.8018
Episode: 2948 Total reward: 22.0 Training loss: 2.6603 Explore P: 0.8018
Episode: 2949 Total reward: 21.0 Training loss: 52.8859 Explore P: 0.8017
Episode: 2950 Total reward: 16.0 Training loss: 12.2499 Explore P: 0.8017
Episode: 2951 Total reward: 19.0 Training loss: 3.5002 Explore P: 0.8017
Episode: 2952 Total reward: 19.0 Training loss: 0.1338 Explore P: 0.8016
Episode: 2953 Total reward: 14.0 Training loss: 4.4896 Explore P: 0.8016
Episode: 2954 Total reward: 13.0 Training loss: 3.0552 Explore P: 0.8016
Episode: 2955 Total reward: 16.0 Training loss: 0.2278 Explore P: 0.8016
Episode: 2956 Total reward: 11.0 Training loss: 0.1966 Explore P: 0.8016
Episode: 2957 Total reward: 22.0 Training loss: 0.2920 Explore P: 0.8015
Episode: 2958 Total reward: 12.0 Training loss: 0.1539 Explore P: 0.8015
Episode: 2959 Total reward: 42.0 Training loss: 4.6173 Explore P: 0.8014
Episode: 2960 Total reward: 24.0 Training loss: 0.2482 Explore P: 0.8014
Episode: 2961 Total reward: 15.0 Training loss: 0.2498 Explore P: 0.8014
Episode: 2962 Total reward: 33.0 Training loss: 20.7066 Explore P: 0.8013
Episode: 2963 Total reward: 38.0 Training loss: 0.2638 Explore P: 0.8013
Episode: 2964 Total reward: 21.0 Training loss: 14.0619 Explore P: 0.8012
Episode: 2965 Total reward: 26.0 Training loss: 48.4225 Explore P: 0.8012
Episode: 2966 Total reward: 10.0 Training loss: 260.2131 Explore P: 0.8012
Episode: 2967 Total reward: 14.0 Training loss: 0.1693 Explore P: 0.8011
Episode: 2968 Total reward: 28.0 Training loss: 3.0181 Explore P: 0.8011
Episode: 2969 Total reward: 14.0 Training loss: 0.7029 Explore P: 0.8011
Episode: 2970 Total reward: 16.0 Training loss: 2.3162 Explore P: 0.8011
Episode: 2971 Total reward: 28.0 Training loss: 0.1806 Explore P: 0.8010
Episode: 2972 Total reward: 10.0 Training loss: 3.3890 Explore P: 0.8010
Episode: 2973 Total reward: 20.0 Training loss: 0.0929 Explore P: 0.8010
Episode: 2974 Total reward: 23.0 Training loss: 0.1257 Explore P: 0.8009
Episode: 2975 Total reward: 32.0 Training loss: 19.2302 Explore P: 0.8009
Episode: 2976 Total reward: 9.0 Training loss: 2.1343 Explore P: 0.8009
Episode: 2977 Total reward: 9.0 Training loss: 2.6997 Explore P: 0.8009
Episode: 2978 Total reward: 28.0 Training loss: 0.2494 Explore P: 0.8008
Episode: 2979 Total reward: 22.0 Training loss: 3.3923 Explore P: 0.8008
Episode: 2980 Total reward: 19.0 Training loss: 18.1528 Explore P: 0.8007
Episode: 2981 Total reward: 17.0 Training loss: 0.4304 Explore P: 0.8007
Episode: 2982 Total reward: 22.0 Training loss: 1.8568 Explore P: 0.8007
Episode: 2983 Total reward: 18.0 Training loss: 45.6660 Explore P: 0.8007
Episode: 2984 Total reward: 33.0 Training loss: 15.1208 Explore P: 0.8006
Episode: 2985 Total reward: 26.0 Training loss: 9.3895 Explore P: 0.8006
Episode: 2986 Total reward: 23.0 Training loss: 0.3105 Explore P: 0.8005
Episode: 2987 Total reward: 12.0 Training loss: 37.0772 Explore P: 0.8005
Episode: 2988 Total reward: 17.0 Training loss: 0.9400 Explore P: 0.8005
Episode: 2989 Total reward: 15.0 Training loss: 12.3443 Explore P: 0.8005
Episode: 2990 Total reward: 18.0 Training loss: 0.1396 Explore P: 0.8004
Episode: 2991 Total reward: 9.0 Training loss: 0.2493 Explore P: 0.8004
Episode: 2992 Total reward: 10.0 Training loss: 5.1932 Explore P: 0.8004
Episode: 2993 Total reward: 23.0 Training loss: 35.4071 Explore P: 0.8004
Episode: 2994 Total reward: 17.0 Training loss: 25.1980 Explore P: 0.8003
Episode: 2995 Total reward: 22.0 Training loss: 0.7969 Explore P: 0.8003
Episode: 2996 Total reward: 17.0 Training loss: 56.1833 Explore P: 0.8003
Episode: 2997 Total reward: 10.0 Training loss: 1.6315 Explore P: 0.8003
Episode: 2998 Total reward: 10.0 Training loss: 0.0857 Explore P: 0.8002
Episode: 2999 Total reward: 18.0 Training loss: 6.9209 Explore P: 0.8002
Episode: 3000 Total reward: 10.0 Training loss: 0.2387 Explore P: 0.8002
Episode: 3001 Total reward: 9.0 Training loss: 0.5460 Explore P: 0.8002
Episode: 3002 Total reward: 16.0 Training loss: 0.8930 Explore P: 0.8002
Episode: 3003 Total reward: 27.0 Training loss: 28.9666 Explore P: 0.8001
Episode: 3004 Total reward: 19.0 Training loss: 4.7737 Explore P: 0.8001
Episode: 3005 Total reward: 21.0 Training loss: 5.1058 Explore P: 0.8000
Episode: 3006 Total reward: 13.0 Training loss: 7.9900 Explore P: 0.8000
Episode: 3007 Total reward: 10.0 Training loss: 5.8117 Explore P: 0.8000
Episode: 3008 Total reward: 15.0 Training loss: 0.0920 Explore P: 0.8000
Episode: 3009 Total reward: 39.0 Training loss: 1.5544 Explore P: 0.7999
Episode: 3010 Total reward: 17.0 Training loss: 1.7391 Explore P: 0.7999
Episode: 3011 Total reward: 29.0 Training loss: 17.4643 Explore P: 0.7999
Episode: 3012 Total reward: 14.0 Training loss: 12.2570 Explore P: 0.7998
Episode: 3013 Total reward: 55.0 Training loss: 28.8914 Explore P: 0.7997
Episode: 3014 Total reward: 10.0 Training loss: 21.4131 Explore P: 0.7997
Episode: 3015 Total reward: 14.0 Training loss: 0.1231 Explore P: 0.7997
Episode: 3016 Total reward: 22.0 Training loss: 12.1814 Explore P: 0.7997
Episode: 3017 Total reward: 23.0 Training loss: 0.3127 Explore P: 0.7996
Episode: 3018 Total reward: 17.0 Training loss: 3.8886 Explore P: 0.7996
Episode: 3019 Total reward: 13.0 Training loss: 5.2770 Explore P: 0.7996
Episode: 3020 Total reward: 19.0 Training loss: 9.2690 Explore P: 0.7996
Episode: 3021 Total reward: 9.0 Training loss: 12.0728 Explore P: 0.7995
Episode: 3022 Total reward: 12.0 Training loss: 12.3977 Explore P: 0.7995
Episode: 3023 Total reward: 17.0 Training loss: 4.3993 Explore P: 0.7995
Episode: 3024 Total reward: 10.0 Training loss: 81.2003 Explore P: 0.7995
Episode: 3025 Total reward: 12.0 Training loss: 34.8371 Explore P: 0.7995
Episode: 3026 Total reward: 27.0 Training loss: 13.5966 Explore P: 0.7994
Episode: 3027 Total reward: 11.0 Training loss: 9.3335 Explore P: 0.7994
Episode: 3028 Total reward: 18.0 Training loss: 21.9990 Explore P: 0.7994
Episode: 3029 Total reward: 17.0 Training loss: 0.3096 Explore P: 0.7993
Episode: 3030 Total reward: 29.0 Training loss: 0.2738 Explore P: 0.7993
Episode: 3031 Total reward: 21.0 Training loss: 10.5861 Explore P: 0.7993
Episode: 3032 Total reward: 23.0 Training loss: 17.6174 Explore P: 0.7992
Episode: 3033 Total reward: 18.0 Training loss: 2.6019 Explore P: 0.7992
Episode: 3034 Total reward: 14.0 Training loss: 72.3544 Explore P: 0.7992
Episode: 3035 Total reward: 7.0 Training loss: 13.5308 Explore P: 0.7992
Episode: 3036 Total reward: 18.0 Training loss: 93.3282 Explore P: 0.7991
Episode: 3037 Total reward: 16.0 Training loss: 0.3436 Explore P: 0.7991
Episode: 3038 Total reward: 8.0 Training loss: 3.2153 Explore P: 0.7991
Episode: 3039 Total reward: 20.0 Training loss: 7.1982 Explore P: 0.7991
Episode: 3040 Total reward: 10.0 Training loss: 95.0921 Explore P: 0.7991
Episode: 3041 Total reward: 9.0 Training loss: 0.1522 Explore P: 0.7990
Episode: 3042 Total reward: 17.0 Training loss: 9.7754 Explore P: 0.7990
Episode: 3043 Total reward: 10.0 Training loss: 40.8576 Explore P: 0.7990
Episode: 3044 Total reward: 16.0 Training loss: 0.1930 Explore P: 0.7990
Episode: 3045 Total reward: 12.0 Training loss: 6.6894 Explore P: 0.7990
Episode: 3046 Total reward: 11.0 Training loss: 0.1185 Explore P: 0.7989
Episode: 3047 Total reward: 11.0 Training loss: 0.1781 Explore P: 0.7989
Episode: 3048 Total reward: 35.0 Training loss: 7.1708 Explore P: 0.7989
Episode: 3049 Total reward: 14.0 Training loss: 0.1362 Explore P: 0.7988
Episode: 3050 Total reward: 10.0 Training loss: 43.3566 Explore P: 0.7988
Episode: 3051 Total reward: 14.0 Training loss: 0.4425 Explore P: 0.7988
Episode: 3052 Total reward: 15.0 Training loss: 254.4042 Explore P: 0.7988
Episode: 3053 Total reward: 15.0 Training loss: 0.1178 Explore P: 0.7988
Episode: 3054 Total reward: 21.0 Training loss: 0.1284 Explore P: 0.7987
Episode: 3055 Total reward: 43.0 Training loss: 2.3833 Explore P: 0.7987
Episode: 3056 Total reward: 10.0 Training loss: 0.1254 Explore P: 0.7986
Episode: 3057 Total reward: 13.0 Training loss: 0.2884 Explore P: 0.7986
Episode: 3058 Total reward: 22.0 Training loss: 10.8120 Explore P: 0.7986
Episode: 3059 Total reward: 13.0 Training loss: 0.0964 Explore P: 0.7986
Episode: 3060 Total reward: 10.0 Training loss: 0.2559 Explore P: 0.7986
Episode: 3061 Total reward: 30.0 Training loss: 0.5076 Explore P: 0.7985
Episode: 3062 Total reward: 12.0 Training loss: 0.2122 Explore P: 0.7985
Episode: 3063 Total reward: 47.0 Training loss: 0.1333 Explore P: 0.7984
Episode: 3064 Total reward: 37.0 Training loss: 0.0913 Explore P: 0.7984
Episode: 3065 Total reward: 8.0 Training loss: 3.0667 Explore P: 0.7983
Episode: 3066 Total reward: 28.0 Training loss: 9.7437 Explore P: 0.7983
Episode: 3067 Total reward: 18.0 Training loss: 1.9430 Explore P: 0.7983
Episode: 3068 Total reward: 21.0 Training loss: 1.7088 Explore P: 0.7982
Episode: 3069 Total reward: 26.0 Training loss: 1.6477 Explore P: 0.7982
Episode: 3070 Total reward: 10.0 Training loss: 1.5608 Explore P: 0.7982
Episode: 3071 Total reward: 56.0 Training loss: 0.1442 Explore P: 0.7981
Episode: 3072 Total reward: 30.0 Training loss: 2.3019 Explore P: 0.7980
Episode: 3073 Total reward: 23.0 Training loss: 0.2219 Explore P: 0.7980
Episode: 3074 Total reward: 11.0 Training loss: 1.6263 Explore P: 0.7980
Episode: 3075 Total reward: 17.0 Training loss: 0.3977 Explore P: 0.7980
Episode: 3076 Total reward: 16.0 Training loss: 0.1995 Explore P: 0.7979
Episode: 3077 Total reward: 8.0 Training loss: 3.9352 Explore P: 0.7979
Episode: 3078 Total reward: 23.0 Training loss: 0.1414 Explore P: 0.7979
Episode: 3079 Total reward: 26.0 Training loss: 0.0800 Explore P: 0.7978
Episode: 3080 Total reward: 18.0 Training loss: 2.0398 Explore P: 0.7978
Episode: 3081 Total reward: 10.0 Training loss: 5.4717 Explore P: 0.7978
Episode: 3082 Total reward: 14.0 Training loss: 12.7445 Explore P: 0.7978
Episode: 3083 Total reward: 22.0 Training loss: 0.6995 Explore P: 0.7977
Episode: 3084 Total reward: 27.0 Training loss: 0.3535 Explore P: 0.7977
Episode: 3085 Total reward: 14.0 Training loss: 35.7437 Explore P: 0.7977
Episode: 3086 Total reward: 58.0 Training loss: 1.6001 Explore P: 0.7976
Episode: 3087 Total reward: 15.0 Training loss: 16.6254 Explore P: 0.7976
Episode: 3088 Total reward: 29.0 Training loss: 7.0554 Explore P: 0.7975
Episode: 3089 Total reward: 18.0 Training loss: 24.4156 Explore P: 0.7975
Episode: 3090 Total reward: 21.0 Training loss: 1.0305 Explore P: 0.7975
Episode: 3091 Total reward: 15.0 Training loss: 111.1319 Explore P: 0.7974
Episode: 3092 Total reward: 15.0 Training loss: 1.2535 Explore P: 0.7974
Episode: 3093 Total reward: 9.0 Training loss: 138.4441 Explore P: 0.7974
Episode: 3094 Total reward: 14.0 Training loss: 19.4964 Explore P: 0.7974
Episode: 3095 Total reward: 13.0 Training loss: 16.5903 Explore P: 0.7974
Episode: 3096 Total reward: 17.0 Training loss: 8.7844 Explore P: 0.7973
Episode: 3097 Total reward: 16.0 Training loss: 8.8758 Explore P: 0.7973
Episode: 3098 Total reward: 11.0 Training loss: 5.2471 Explore P: 0.7973
Episode: 3099 Total reward: 21.0 Training loss: 0.2528 Explore P: 0.7973
Episode: 3100 Total reward: 12.0 Training loss: 2.2523 Explore P: 0.7972
Episode: 3101 Total reward: 12.0 Training loss: 1.0121 Explore P: 0.7972
Episode: 3102 Total reward: 31.0 Training loss: 5.1927 Explore P: 0.7972
Episode: 3103 Total reward: 14.0 Training loss: 0.1451 Explore P: 0.7971
Episode: 3104 Total reward: 43.0 Training loss: 26.4530 Explore P: 0.7971
Episode: 3105 Total reward: 15.0 Training loss: 0.1617 Explore P: 0.7971
Episode: 3106 Total reward: 9.0 Training loss: 0.0837 Explore P: 0.7970
Episode: 3107 Total reward: 18.0 Training loss: 1.8257 Explore P: 0.7970
Episode: 3108 Total reward: 12.0 Training loss: 36.0134 Explore P: 0.7970
Episode: 3109 Total reward: 13.0 Training loss: 0.1966 Explore P: 0.7970
Episode: 3110 Total reward: 11.0 Training loss: 0.1558 Explore P: 0.7970
Episode: 3111 Total reward: 13.0 Training loss: 32.7598 Explore P: 0.7969
Episode: 3112 Total reward: 10.0 Training loss: 3.9344 Explore P: 0.7969
Episode: 3113 Total reward: 14.0 Training loss: 16.5167 Explore P: 0.7969
Episode: 3114 Total reward: 11.0 Training loss: 5.2707 Explore P: 0.7969
Episode: 3115 Total reward: 10.0 Training loss: 1.0395 Explore P: 0.7969
Episode: 3116 Total reward: 14.0 Training loss: 11.0298 Explore P: 0.7968
Episode: 3117 Total reward: 27.0 Training loss: 1.4392 Explore P: 0.7968
Episode: 3118 Total reward: 30.0 Training loss: 0.3624 Explore P: 0.7968
Episode: 3119 Total reward: 13.0 Training loss: 41.9909 Explore P: 0.7967
Episode: 3120 Total reward: 18.0 Training loss: 1.5821 Explore P: 0.7967
Episode: 3121 Total reward: 16.0 Training loss: 0.2279 Explore P: 0.7967
Episode: 3122 Total reward: 14.0 Training loss: 0.2537 Explore P: 0.7967
Episode: 3123 Total reward: 31.0 Training loss: 3.8022 Explore P: 0.7966
Episode: 3124 Total reward: 29.0 Training loss: 1.3966 Explore P: 0.7966
Episode: 3125 Total reward: 9.0 Training loss: 18.2246 Explore P: 0.7965
Episode: 3126 Total reward: 12.0 Training loss: 8.0300 Explore P: 0.7965
Episode: 3127 Total reward: 18.0 Training loss: 35.1905 Explore P: 0.7965
Episode: 3128 Total reward: 11.0 Training loss: 4.8701 Explore P: 0.7965
Episode: 3129 Total reward: 7.0 Training loss: 3.9070 Explore P: 0.7965
Episode: 3130 Total reward: 41.0 Training loss: 2.1350 Explore P: 0.7964
Episode: 3131 Total reward: 16.0 Training loss: 14.3255 Explore P: 0.7964
Episode: 3132 Total reward: 45.0 Training loss: 2.0803 Explore P: 0.7963
Episode: 3133 Total reward: 10.0 Training loss: 17.2069 Explore P: 0.7963
Episode: 3134 Total reward: 14.0 Training loss: 9.6267 Explore P: 0.7963
Episode: 3135 Total reward: 11.0 Training loss: 17.3544 Explore P: 0.7963
Episode: 3136 Total reward: 14.0 Training loss: 48.7353 Explore P: 0.7962
Episode: 3137 Total reward: 19.0 Training loss: 8.6243 Explore P: 0.7962
Episode: 3138 Total reward: 20.0 Training loss: 2.9542 Explore P: 0.7962
Episode: 3139 Total reward: 16.0 Training loss: 1.5738 Explore P: 0.7961
Episode: 3140 Total reward: 20.0 Training loss: 6.2261 Explore P: 0.7961
Episode: 3141 Total reward: 14.0 Training loss: 20.1538 Explore P: 0.7961
Episode: 3142 Total reward: 12.0 Training loss: 20.0055 Explore P: 0.7961
Episode: 3143 Total reward: 17.0 Training loss: 0.1366 Explore P: 0.7960
Episode: 3144 Total reward: 33.0 Training loss: 0.1474 Explore P: 0.7960
Episode: 3145 Total reward: 26.0 Training loss: 21.6388 Explore P: 0.7960
Episode: 3146 Total reward: 12.0 Training loss: 4.9118 Explore P: 0.7959
Episode: 3147 Total reward: 13.0 Training loss: 0.2903 Explore P: 0.7959
Episode: 3148 Total reward: 28.0 Training loss: 1.9174 Explore P: 0.7959
Episode: 3149 Total reward: 40.0 Training loss: 4.2563 Explore P: 0.7958
Episode: 3150 Total reward: 31.0 Training loss: 0.3514 Explore P: 0.7958
Episode: 3151 Total reward: 12.0 Training loss: 0.2497 Explore P: 0.7957
Episode: 3152 Total reward: 12.0 Training loss: 6.1108 Explore P: 0.7957
Episode: 3153 Total reward: 10.0 Training loss: 2.8774 Explore P: 0.7957
Episode: 3154 Total reward: 27.0 Training loss: 39.0045 Explore P: 0.7957
Episode: 3155 Total reward: 15.0 Training loss: 11.1197 Explore P: 0.7956
Episode: 3156 Total reward: 12.0 Training loss: 0.0999 Explore P: 0.7956
Episode: 3157 Total reward: 21.0 Training loss: 1.8882 Explore P: 0.7956
Episode: 3158 Total reward: 27.0 Training loss: 2.9397 Explore P: 0.7955
Episode: 3159 Total reward: 32.0 Training loss: 8.5777 Explore P: 0.7955
Episode: 3160 Total reward: 34.0 Training loss: 4.2249 Explore P: 0.7954
Episode: 3161 Total reward: 9.0 Training loss: 28.0089 Explore P: 0.7954
Episode: 3162 Total reward: 38.0 Training loss: 1.0373 Explore P: 0.7954
Episode: 3163 Total reward: 14.0 Training loss: 0.1821 Explore P: 0.7953
Episode: 3164 Total reward: 14.0 Training loss: 0.1438 Explore P: 0.7953
Episode: 3165 Total reward: 16.0 Training loss: 0.0781 Explore P: 0.7953
Episode: 3166 Total reward: 58.0 Training loss: 0.0700 Explore P: 0.7952
Episode: 3167 Total reward: 38.0 Training loss: 0.7886 Explore P: 0.7951
Episode: 3168 Total reward: 13.0 Training loss: 1.2798 Explore P: 0.7951
Episode: 3169 Total reward: 23.0 Training loss: 2.9116 Explore P: 0.7951
Episode: 3170 Total reward: 12.0 Training loss: 1.2150 Explore P: 0.7951
Episode: 3171 Total reward: 11.0 Training loss: 38.7688 Explore P: 0.7951
Episode: 3172 Total reward: 9.0 Training loss: 7.7337 Explore P: 0.7950
Episode: 3173 Total reward: 18.0 Training loss: 8.6419 Explore P: 0.7950
Episode: 3174 Total reward: 9.0 Training loss: 2.3737 Explore P: 0.7950
Episode: 3175 Total reward: 47.0 Training loss: 7.8521 Explore P: 0.7949
Episode: 3176 Total reward: 14.0 Training loss: 0.4135 Explore P: 0.7949
Episode: 3177 Total reward: 25.0 Training loss: 0.4134 Explore P: 0.7949
Episode: 3178 Total reward: 9.0 Training loss: 11.9767 Explore P: 0.7949
Episode: 3179 Total reward: 12.0 Training loss: 2.8036 Explore P: 0.7948
Episode: 3180 Total reward: 27.0 Training loss: 0.1618 Explore P: 0.7948
Episode: 3181 Total reward: 7.0 Training loss: 0.4896 Explore P: 0.7948
Episode: 3182 Total reward: 17.0 Training loss: 4.7490 Explore P: 0.7948
Episode: 3183 Total reward: 17.0 Training loss: 11.8466 Explore P: 0.7947
Episode: 3184 Total reward: 14.0 Training loss: 0.1383 Explore P: 0.7947
Episode: 3185 Total reward: 9.0 Training loss: 2.5444 Explore P: 0.7947
Episode: 3186 Total reward: 61.0 Training loss: 0.1337 Explore P: 0.7946
Episode: 3187 Total reward: 48.0 Training loss: 2.5486 Explore P: 0.7945
Episode: 3188 Total reward: 30.0 Training loss: 10.4232 Explore P: 0.7945
Episode: 3189 Total reward: 10.0 Training loss: 71.2151 Explore P: 0.7945
Episode: 3190 Total reward: 37.0 Training loss: 2.5391 Explore P: 0.7944
Episode: 3191 Total reward: 11.0 Training loss: 12.8900 Explore P: 0.7944
Episode: 3192 Total reward: 8.0 Training loss: 22.6630 Explore P: 0.7944
Episode: 3193 Total reward: 14.0 Training loss: 11.8430 Explore P: 0.7943
Episode: 3194 Total reward: 14.0 Training loss: 26.7894 Explore P: 0.7943
Episode: 3195 Total reward: 16.0 Training loss: 19.2746 Explore P: 0.7943
Episode: 3196 Total reward: 12.0 Training loss: 20.8462 Explore P: 0.7943
Episode: 3197 Total reward: 21.0 Training loss: 26.1592 Explore P: 0.7942
Episode: 3198 Total reward: 11.0 Training loss: 0.0834 Explore P: 0.7942
Episode: 3199 Total reward: 33.0 Training loss: 7.3350 Explore P: 0.7942
Episode: 3200 Total reward: 14.0 Training loss: 29.0382 Explore P: 0.7942
Episode: 3201 Total reward: 51.0 Training loss: 19.2680 Explore P: 0.7941
Episode: 3202 Total reward: 20.0 Training loss: 1.2210 Explore P: 0.7940
Episode: 3203 Total reward: 16.0 Training loss: 5.0910 Explore P: 0.7940
Episode: 3204 Total reward: 14.0 Training loss: 12.1345 Explore P: 0.7940
Episode: 3205 Total reward: 13.0 Training loss: 0.1136 Explore P: 0.7940
Episode: 3206 Total reward: 20.0 Training loss: 12.9734 Explore P: 0.7939
Episode: 3207 Total reward: 12.0 Training loss: 1.6886 Explore P: 0.7939
Episode: 3208 Total reward: 29.0 Training loss: 10.3610 Explore P: 0.7939
Episode: 3209 Total reward: 19.0 Training loss: 7.3423 Explore P: 0.7939
Episode: 3210 Total reward: 19.0 Training loss: 23.7597 Explore P: 0.7938
Episode: 3211 Total reward: 41.0 Training loss: 26.7415 Explore P: 0.7938
Episode: 3212 Total reward: 25.0 Training loss: 40.8760 Explore P: 0.7937
Episode: 3213 Total reward: 24.0 Training loss: 8.4621 Explore P: 0.7937
Episode: 3214 Total reward: 13.0 Training loss: 0.6467 Explore P: 0.7937
Episode: 3215 Total reward: 13.0 Training loss: 40.7807 Explore P: 0.7936
Episode: 3216 Total reward: 26.0 Training loss: 3.3426 Explore P: 0.7936
Episode: 3217 Total reward: 9.0 Training loss: 0.1412 Explore P: 0.7936
Episode: 3218 Total reward: 12.0 Training loss: 7.3067 Explore P: 0.7936
Episode: 3219 Total reward: 23.0 Training loss: 7.5181 Explore P: 0.7935
Episode: 3220 Total reward: 11.0 Training loss: 15.5130 Explore P: 0.7935
Episode: 3221 Total reward: 16.0 Training loss: 0.2516 Explore P: 0.7935
Episode: 3222 Total reward: 37.0 Training loss: 9.8489 Explore P: 0.7934
Episode: 3223 Total reward: 14.0 Training loss: 250.6538 Explore P: 0.7934
Episode: 3224 Total reward: 14.0 Training loss: 27.9398 Explore P: 0.7934
Episode: 3225 Total reward: 23.0 Training loss: 2.1822 Explore P: 0.7933
Episode: 3226 Total reward: 27.0 Training loss: 2.5751 Explore P: 0.7933
Episode: 3227 Total reward: 16.0 Training loss: 0.1948 Explore P: 0.7933
Episode: 3228 Total reward: 17.0 Training loss: 0.1136 Explore P: 0.7933
Episode: 3229 Total reward: 15.0 Training loss: 0.3773 Explore P: 0.7932
Episode: 3230 Total reward: 24.0 Training loss: 1.5528 Explore P: 0.7932
Episode: 3231 Total reward: 14.0 Training loss: 2.8856 Explore P: 0.7932
Episode: 3232 Total reward: 10.0 Training loss: 0.1836 Explore P: 0.7932
Episode: 3233 Total reward: 15.0 Training loss: 0.0650 Explore P: 0.7931
Episode: 3234 Total reward: 7.0 Training loss: 115.2909 Explore P: 0.7931
Episode: 3235 Total reward: 15.0 Training loss: 14.1174 Explore P: 0.7931
Episode: 3236 Total reward: 12.0 Training loss: 18.1827 Explore P: 0.7931
Episode: 3237 Total reward: 25.0 Training loss: 23.5324 Explore P: 0.7930
Episode: 3238 Total reward: 19.0 Training loss: 0.2720 Explore P: 0.7930
Episode: 3239 Total reward: 16.0 Training loss: 2.5402 Explore P: 0.7930
Episode: 3240 Total reward: 47.0 Training loss: 13.9775 Explore P: 0.7929
Episode: 3241 Total reward: 10.0 Training loss: 255.6066 Explore P: 0.7929
Episode: 3242 Total reward: 27.0 Training loss: 0.2174 Explore P: 0.7929
Episode: 3243 Total reward: 16.0 Training loss: 0.0350 Explore P: 0.7928
Episode: 3244 Total reward: 13.0 Training loss: 0.3131 Explore P: 0.7928
Episode: 3245 Total reward: 36.0 Training loss: 5.0447 Explore P: 0.7928
Episode: 3246 Total reward: 27.0 Training loss: 0.2619 Explore P: 0.7927
Episode: 3247 Total reward: 13.0 Training loss: 1.2789 Explore P: 0.7927
Episode: 3248 Total reward: 22.0 Training loss: 8.2721 Explore P: 0.7927
Episode: 3249 Total reward: 13.0 Training loss: 0.1153 Explore P: 0.7926
Episode: 3250 Total reward: 19.0 Training loss: 52.2332 Explore P: 0.7926
Episode: 3251 Total reward: 69.0 Training loss: 46.6888 Explore P: 0.7925
Episode: 3252 Total reward: 27.0 Training loss: 0.1869 Explore P: 0.7925
Episode: 3253 Total reward: 40.0 Training loss: 0.7098 Explore P: 0.7924
Episode: 3254 Total reward: 11.0 Training loss: 147.3662 Explore P: 0.7924
Episode: 3255 Total reward: 15.0 Training loss: 12.9523 Explore P: 0.7924
Episode: 3256 Total reward: 10.0 Training loss: 5.4921 Explore P: 0.7923
Episode: 3257 Total reward: 12.0 Training loss: 0.2264 Explore P: 0.7923
Episode: 3258 Total reward: 48.0 Training loss: 0.1082 Explore P: 0.7922
Episode: 3259 Total reward: 21.0 Training loss: 14.4258 Explore P: 0.7922
Episode: 3260 Total reward: 13.0 Training loss: 0.0885 Explore P: 0.7922
Episode: 3261 Total reward: 19.0 Training loss: 0.0786 Explore P: 0.7922
Episode: 3262 Total reward: 30.0 Training loss: 17.7850 Explore P: 0.7921
Episode: 3263 Total reward: 11.0 Training loss: 8.9587 Explore P: 0.7921
Episode: 3264 Total reward: 35.0 Training loss: 56.7635 Explore P: 0.7920
Episode: 3265 Total reward: 12.0 Training loss: 20.3841 Explore P: 0.7920
Episode: 3266 Total reward: 22.0 Training loss: 12.7634 Explore P: 0.7920
Episode: 3267 Total reward: 22.0 Training loss: 26.1093 Explore P: 0.7920
Episode: 3268 Total reward: 10.0 Training loss: 8.5155 Explore P: 0.7919
Episode: 3269 Total reward: 36.0 Training loss: 0.1630 Explore P: 0.7919
Episode: 3270 Total reward: 24.0 Training loss: 3.7452 Explore P: 0.7918
Episode: 3271 Total reward: 34.0 Training loss: 16.5908 Explore P: 0.7918
Episode: 3272 Total reward: 13.0 Training loss: 3.7144 Explore P: 0.7918
Episode: 3273 Total reward: 13.0 Training loss: 27.5606 Explore P: 0.7918
Episode: 3274 Total reward: 36.0 Training loss: 5.1464 Explore P: 0.7917
Episode: 3275 Total reward: 10.0 Training loss: 18.7049 Explore P: 0.7917
Episode: 3276 Total reward: 24.0 Training loss: 0.2236 Explore P: 0.7916
Episode: 3277 Total reward: 20.0 Training loss: 0.0656 Explore P: 0.7916
Episode: 3278 Total reward: 7.0 Training loss: 12.6578 Explore P: 0.7916
Episode: 3279 Total reward: 15.0 Training loss: 8.4331 Explore P: 0.7916
Episode: 3280 Total reward: 10.0 Training loss: 63.5413 Explore P: 0.7916
Episode: 3281 Total reward: 14.0 Training loss: 0.0926 Explore P: 0.7915
Episode: 3282 Total reward: 21.0 Training loss: 11.9208 Explore P: 0.7915
Episode: 3283 Total reward: 12.0 Training loss: 8.6968 Explore P: 0.7915
Episode: 3284 Total reward: 18.0 Training loss: 0.1074 Explore P: 0.7915
Episode: 3285 Total reward: 13.0 Training loss: 0.2373 Explore P: 0.7914
Episode: 3286 Total reward: 15.0 Training loss: 1.3279 Explore P: 0.7914
Episode: 3287 Total reward: 25.0 Training loss: 0.3880 Explore P: 0.7914
Episode: 3288 Total reward: 12.0 Training loss: 7.7362 Explore P: 0.7914
Episode: 3289 Total reward: 11.0 Training loss: 0.1357 Explore P: 0.7913
Episode: 3290 Total reward: 57.0 Training loss: 0.2156 Explore P: 0.7913
Episode: 3291 Total reward: 24.0 Training loss: 4.4007 Explore P: 0.7912
Episode: 3292 Total reward: 8.0 Training loss: 28.9195 Explore P: 0.7912
Episode: 3293 Total reward: 10.0 Training loss: 39.8992 Explore P: 0.7912
Episode: 3294 Total reward: 25.0 Training loss: 30.9527 Explore P: 0.7911
Episode: 3295 Total reward: 18.0 Training loss: 0.0994 Explore P: 0.7911
Episode: 3296 Total reward: 13.0 Training loss: 20.6776 Explore P: 0.7911
Episode: 3297 Total reward: 12.0 Training loss: 6.0580 Explore P: 0.7911
Episode: 3298 Total reward: 14.0 Training loss: 1.5306 Explore P: 0.7911
Episode: 3299 Total reward: 21.0 Training loss: 13.6130 Explore P: 0.7910
Episode: 3300 Total reward: 17.0 Training loss: 48.6049 Explore P: 0.7910
Episode: 3301 Total reward: 8.0 Training loss: 4.5620 Explore P: 0.7910
Episode: 3302 Total reward: 10.0 Training loss: 3.2787 Explore P: 0.7910
Episode: 3303 Total reward: 14.0 Training loss: 0.1325 Explore P: 0.7909
Episode: 3304 Total reward: 23.0 Training loss: 6.6674 Explore P: 0.7909
Episode: 3305 Total reward: 25.0 Training loss: 2.5558 Explore P: 0.7909
Episode: 3306 Total reward: 12.0 Training loss: 11.6467 Explore P: 0.7909
Episode: 3307 Total reward: 29.0 Training loss: 1.1580 Explore P: 0.7908
Episode: 3308 Total reward: 13.0 Training loss: 0.2727 Explore P: 0.7908
Episode: 3309 Total reward: 11.0 Training loss: 6.9943 Explore P: 0.7908
Episode: 3310 Total reward: 26.0 Training loss: 49.3451 Explore P: 0.7907
Episode: 3311 Total reward: 10.0 Training loss: 19.6407 Explore P: 0.7907
Episode: 3312 Total reward: 12.0 Training loss: 0.1222 Explore P: 0.7907
Episode: 3313 Total reward: 18.0 Training loss: 22.3818 Explore P: 0.7907
Episode: 3314 Total reward: 23.0 Training loss: 33.6562 Explore P: 0.7906
Episode: 3315 Total reward: 10.0 Training loss: 88.0404 Explore P: 0.7906
Episode: 3316 Total reward: 34.0 Training loss: 1.5056 Explore P: 0.7906
Episode: 3317 Total reward: 10.0 Training loss: 33.6118 Explore P: 0.7905
Episode: 3318 Total reward: 9.0 Training loss: 0.1105 Explore P: 0.7905
Episode: 3319 Total reward: 7.0 Training loss: 0.1398 Explore P: 0.7905
Episode: 3320 Total reward: 24.0 Training loss: 8.1829 Explore P: 0.7905
Episode: 3321 Total reward: 22.0 Training loss: 3.1068 Explore P: 0.7905
Episode: 3322 Total reward: 27.0 Training loss: 0.0547 Explore P: 0.7904
Episode: 3323 Total reward: 22.0 Training loss: 0.2828 Explore P: 0.7904
Episode: 3324 Total reward: 30.0 Training loss: 2.1855 Explore P: 0.7903
Episode: 3325 Total reward: 21.0 Training loss: 4.6928 Explore P: 0.7903
Episode: 3326 Total reward: 16.0 Training loss: 0.2325 Explore P: 0.7903
Episode: 3327 Total reward: 29.0 Training loss: 41.1837 Explore P: 0.7902
Episode: 3328 Total reward: 15.0 Training loss: 14.7238 Explore P: 0.7902
Episode: 3329 Total reward: 10.0 Training loss: 1.0596 Explore P: 0.7902
Episode: 3330 Total reward: 15.0 Training loss: 0.0665 Explore P: 0.7902
Episode: 3331 Total reward: 25.0 Training loss: 0.1133 Explore P: 0.7901
Episode: 3332 Total reward: 24.0 Training loss: 2.8174 Explore P: 0.7901
Episode: 3333 Total reward: 24.0 Training loss: 0.0819 Explore P: 0.7900
Episode: 3334 Total reward: 17.0 Training loss: 3.7536 Explore P: 0.7900
Episode: 3335 Total reward: 10.0 Training loss: 0.1729 Explore P: 0.7900
Episode: 3336 Total reward: 35.0 Training loss: 17.2876 Explore P: 0.7900
Episode: 3337 Total reward: 14.0 Training loss: 0.2293 Explore P: 0.7899
Episode: 3338 Total reward: 16.0 Training loss: 25.0522 Explore P: 0.7899
Episode: 3339 Total reward: 15.0 Training loss: 0.1703 Explore P: 0.7899
Episode: 3340 Total reward: 14.0 Training loss: 0.4051 Explore P: 0.7899
Episode: 3341 Total reward: 10.0 Training loss: 1.8878 Explore P: 0.7898
Episode: 3342 Total reward: 11.0 Training loss: 0.1176 Explore P: 0.7898
Episode: 3343 Total reward: 12.0 Training loss: 1.6101 Explore P: 0.7898
Episode: 3344 Total reward: 12.0 Training loss: 4.4518 Explore P: 0.7898
Episode: 3345 Total reward: 35.0 Training loss: 2.5203 Explore P: 0.7897
Episode: 3346 Total reward: 15.0 Training loss: 1.4807 Explore P: 0.7897
Episode: 3347 Total reward: 12.0 Training loss: 0.0419 Explore P: 0.7897
Episode: 3348 Total reward: 12.0 Training loss: 22.0560 Explore P: 0.7897
Episode: 3349 Total reward: 17.0 Training loss: 0.1991 Explore P: 0.7896
Episode: 3350 Total reward: 35.0 Training loss: 0.1733 Explore P: 0.7896
Episode: 3351 Total reward: 16.0 Training loss: 23.5708 Explore P: 0.7896
Episode: 3352 Total reward: 16.0 Training loss: 0.1312 Explore P: 0.7895
Episode: 3353 Total reward: 18.0 Training loss: 8.3399 Explore P: 0.7895
Episode: 3354 Total reward: 33.0 Training loss: 0.1592 Explore P: 0.7895
Episode: 3355 Total reward: 27.0 Training loss: 1.7340 Explore P: 0.7894
Episode: 3356 Total reward: 8.0 Training loss: 35.6111 Explore P: 0.7894
Episode: 3357 Total reward: 16.0 Training loss: 80.0826 Explore P: 0.7894
Episode: 3358 Total reward: 16.0 Training loss: 0.9130 Explore P: 0.7894
Episode: 3359 Total reward: 22.0 Training loss: 1.7020 Explore P: 0.7893
Episode: 3360 Total reward: 17.0 Training loss: 4.0158 Explore P: 0.7893
Episode: 3361 Total reward: 11.0 Training loss: 0.1443 Explore P: 0.7893
Episode: 3362 Total reward: 13.0 Training loss: 1.1517 Explore P: 0.7893
Episode: 3363 Total reward: 12.0 Training loss: 0.0178 Explore P: 0.7892
Episode: 3364 Total reward: 8.0 Training loss: 0.1205 Explore P: 0.7892
Episode: 3365 Total reward: 21.0 Training loss: 18.5481 Explore P: 0.7892
Episode: 3366 Total reward: 17.0 Training loss: 3.1989 Explore P: 0.7892
Episode: 3367 Total reward: 33.0 Training loss: 0.1097 Explore P: 0.7891
Episode: 3368 Total reward: 16.0 Training loss: 3.5989 Explore P: 0.7891
Episode: 3369 Total reward: 13.0 Training loss: 0.1468 Explore P: 0.7891
Episode: 3370 Total reward: 11.0 Training loss: 0.4132 Explore P: 0.7891
Episode: 3371 Total reward: 10.0 Training loss: 1.8895 Explore P: 0.7890
Episode: 3372 Total reward: 10.0 Training loss: 30.4281 Explore P: 0.7890
Episode: 3373 Total reward: 22.0 Training loss: 9.1838 Explore P: 0.7890
Episode: 3374 Total reward: 38.0 Training loss: 8.1559 Explore P: 0.7889
Episode: 3375 Total reward: 9.0 Training loss: 0.4451 Explore P: 0.7889
Episode: 3376 Total reward: 10.0 Training loss: 0.2391 Explore P: 0.7889
Episode: 3377 Total reward: 9.0 Training loss: 2.4403 Explore P: 0.7889
Episode: 3378 Total reward: 29.0 Training loss: 0.3073 Explore P: 0.7888
Episode: 3379 Total reward: 17.0 Training loss: 0.5820 Explore P: 0.7888
Episode: 3380 Total reward: 44.0 Training loss: 3.8436 Explore P: 0.7887
Episode: 3381 Total reward: 11.0 Training loss: 6.8250 Explore P: 0.7887
Episode: 3382 Total reward: 13.0 Training loss: 15.2968 Explore P: 0.7887
Episode: 3383 Total reward: 17.0 Training loss: 0.1668 Explore P: 0.7887
Episode: 3384 Total reward: 11.0 Training loss: 0.1554 Explore P: 0.7887
Episode: 3385 Total reward: 25.0 Training loss: 57.7936 Explore P: 0.7886
Episode: 3386 Total reward: 10.0 Training loss: 31.9712 Explore P: 0.7886
Episode: 3387 Total reward: 12.0 Training loss: 60.2814 Explore P: 0.7886
Episode: 3388 Total reward: 13.0 Training loss: 0.1283 Explore P: 0.7886
Episode: 3389 Total reward: 12.0 Training loss: 22.1138 Explore P: 0.7886
Episode: 3390 Total reward: 10.0 Training loss: 9.7096 Explore P: 0.7885
Episode: 3391 Total reward: 32.0 Training loss: 4.8438 Explore P: 0.7885
Episode: 3392 Total reward: 34.0 Training loss: 28.1040 Explore P: 0.7884
Episode: 3393 Total reward: 24.0 Training loss: 0.0897 Explore P: 0.7884
Episode: 3394 Total reward: 10.0 Training loss: 11.1814 Explore P: 0.7884
Episode: 3395 Total reward: 12.0 Training loss: 37.6771 Explore P: 0.7884
Episode: 3396 Total reward: 17.0 Training loss: 96.8865 Explore P: 0.7883
Episode: 3397 Total reward: 25.0 Training loss: 0.0869 Explore P: 0.7883
Episode: 3398 Total reward: 35.0 Training loss: 1.9532 Explore P: 0.7882
Episode: 3399 Total reward: 11.0 Training loss: 4.3909 Explore P: 0.7882
Episode: 3400 Total reward: 22.0 Training loss: 5.1157 Explore P: 0.7882
Episode: 3401 Total reward: 46.0 Training loss: 2.4282 Explore P: 0.7881
Episode: 3402 Total reward: 30.0 Training loss: 0.2081 Explore P: 0.7881
Episode: 3403 Total reward: 22.0 Training loss: 0.1042 Explore P: 0.7880
Episode: 3404 Total reward: 14.0 Training loss: 3.4476 Explore P: 0.7880
Episode: 3405 Total reward: 12.0 Training loss: 30.4983 Explore P: 0.7880
Episode: 3406 Total reward: 14.0 Training loss: 37.1654 Explore P: 0.7880
Episode: 3407 Total reward: 24.0 Training loss: 6.8863 Explore P: 0.7879
Episode: 3408 Total reward: 48.0 Training loss: 2.3341 Explore P: 0.7879
Episode: 3409 Total reward: 11.0 Training loss: 28.7076 Explore P: 0.7878
Episode: 3410 Total reward: 24.0 Training loss: 10.0394 Explore P: 0.7878
Episode: 3411 Total reward: 26.0 Training loss: 11.4088 Explore P: 0.7878
Episode: 3412 Total reward: 12.0 Training loss: 11.6888 Explore P: 0.7878
Episode: 3413 Total reward: 11.0 Training loss: 6.5968 Explore P: 0.7877
Episode: 3414 Total reward: 13.0 Training loss: 0.2517 Explore P: 0.7877
Episode: 3415 Total reward: 33.0 Training loss: 0.5231 Explore P: 0.7877
Episode: 3416 Total reward: 9.0 Training loss: 0.3016 Explore P: 0.7877
Episode: 3417 Total reward: 26.0 Training loss: 0.0832 Explore P: 0.7876
Episode: 3418 Total reward: 15.0 Training loss: 23.8962 Explore P: 0.7876
Episode: 3419 Total reward: 26.0 Training loss: 0.0927 Explore P: 0.7875
Episode: 3420 Total reward: 29.0 Training loss: 4.0089 Explore P: 0.7875
Episode: 3421 Total reward: 12.0 Training loss: 3.0269 Explore P: 0.7875
Episode: 3422 Total reward: 37.0 Training loss: 4.0860 Explore P: 0.7874
Episode: 3423 Total reward: 15.0 Training loss: 4.1851 Explore P: 0.7874
Episode: 3424 Total reward: 33.0 Training loss: 0.2809 Explore P: 0.7874
Episode: 3425 Total reward: 18.0 Training loss: 0.1539 Explore P: 0.7873
Episode: 3426 Total reward: 37.0 Training loss: 0.1796 Explore P: 0.7873
Episode: 3427 Total reward: 14.0 Training loss: 0.1805 Explore P: 0.7872
Episode: 3428 Total reward: 21.0 Training loss: 0.1271 Explore P: 0.7872
Episode: 3429 Total reward: 12.0 Training loss: 0.1304 Explore P: 0.7872
Episode: 3430 Total reward: 52.0 Training loss: 0.2895 Explore P: 0.7871
Episode: 3431 Total reward: 11.0 Training loss: 0.7608 Explore P: 0.7871
Episode: 3432 Total reward: 16.0 Training loss: 11.0552 Explore P: 0.7871
Episode: 3433 Total reward: 14.0 Training loss: 1.6660 Explore P: 0.7870
Episode: 3434 Total reward: 8.0 Training loss: 15.1153 Explore P: 0.7870
Episode: 3435 Total reward: 10.0 Training loss: 0.0850 Explore P: 0.7870
Episode: 3436 Total reward: 14.0 Training loss: 15.2263 Explore P: 0.7870
Episode: 3437 Total reward: 14.0 Training loss: 2.2526 Explore P: 0.7870
Episode: 3438 Total reward: 15.0 Training loss: 10.1862 Explore P: 0.7870
Episode: 3439 Total reward: 11.0 Training loss: 10.2767 Explore P: 0.7869
Episode: 3440 Total reward: 19.0 Training loss: 9.2111 Explore P: 0.7869
Episode: 3441 Total reward: 15.0 Training loss: 0.3279 Explore P: 0.7869
Episode: 3442 Total reward: 56.0 Training loss: 19.4877 Explore P: 0.7868
Episode: 3443 Total reward: 8.0 Training loss: 0.1007 Explore P: 0.7868
Episode: 3444 Total reward: 37.0 Training loss: 0.0563 Explore P: 0.7867
Episode: 3445 Total reward: 12.0 Training loss: 25.4143 Explore P: 0.7867
Episode: 3446 Total reward: 13.0 Training loss: 14.1852 Explore P: 0.7867
Episode: 3447 Total reward: 14.0 Training loss: 5.6207 Explore P: 0.7867
Episode: 3448 Total reward: 19.0 Training loss: 3.7625 Explore P: 0.7866
Episode: 3449 Total reward: 19.0 Training loss: 5.5395 Explore P: 0.7866
Episode: 3450 Total reward: 12.0 Training loss: 4.2212 Explore P: 0.7866
Episode: 3451 Total reward: 50.0 Training loss: 36.5969 Explore P: 0.7865
Episode: 3452 Total reward: 15.0 Training loss: 1.2398 Explore P: 0.7865
Episode: 3453 Total reward: 15.0 Training loss: 7.6437 Explore P: 0.7865
Episode: 3454 Total reward: 22.0 Training loss: 234.6072 Explore P: 0.7864
Episode: 3455 Total reward: 12.0 Training loss: 21.7729 Explore P: 0.7864
Episode: 3456 Total reward: 14.0 Training loss: 7.6815 Explore P: 0.7864
Episode: 3457 Total reward: 11.0 Training loss: 2.8589 Explore P: 0.7864
Episode: 3458 Total reward: 18.0 Training loss: 4.1107 Explore P: 0.7863
Episode: 3459 Total reward: 57.0 Training loss: 0.1367 Explore P: 0.7863
Episode: 3460 Total reward: 30.0 Training loss: 6.9482 Explore P: 0.7862
Episode: 3461 Total reward: 10.0 Training loss: 0.1149 Explore P: 0.7862
Episode: 3462 Total reward: 13.0 Training loss: 0.0928 Explore P: 0.7862
Episode: 3463 Total reward: 16.0 Training loss: 0.7081 Explore P: 0.7861
Episode: 3464 Total reward: 13.0 Training loss: 3.7126 Explore P: 0.7861
Episode: 3465 Total reward: 12.0 Training loss: 11.3955 Explore P: 0.7861
Episode: 3466 Total reward: 12.0 Training loss: 4.7027 Explore P: 0.7861
Episode: 3467 Total reward: 16.0 Training loss: 0.2722 Explore P: 0.7861
Episode: 3468 Total reward: 11.0 Training loss: 3.9391 Explore P: 0.7860
Episode: 3469 Total reward: 28.0 Training loss: 27.5561 Explore P: 0.7860
Episode: 3470 Total reward: 30.0 Training loss: 0.1955 Explore P: 0.7860
Episode: 3471 Total reward: 29.0 Training loss: 0.1318 Explore P: 0.7859
Episode: 3472 Total reward: 17.0 Training loss: 15.0302 Explore P: 0.7859
Episode: 3473 Total reward: 20.0 Training loss: 4.1612 Explore P: 0.7859
Episode: 3474 Total reward: 21.0 Training loss: 0.1532 Explore P: 0.7858
Episode: 3475 Total reward: 14.0 Training loss: 6.8776 Explore P: 0.7858
Episode: 3476 Total reward: 14.0 Training loss: 3.8834 Explore P: 0.7858
Episode: 3477 Total reward: 9.0 Training loss: 49.2305 Explore P: 0.7858
Episode: 3478 Total reward: 19.0 Training loss: 0.2078 Explore P: 0.7857
Episode: 3479 Total reward: 13.0 Training loss: 0.7174 Explore P: 0.7857
Episode: 3480 Total reward: 29.0 Training loss: 0.3968 Explore P: 0.7857
Episode: 3481 Total reward: 45.0 Training loss: 13.5654 Explore P: 0.7856
Episode: 3482 Total reward: 30.0 Training loss: 0.6401 Explore P: 0.7856
Episode: 3483 Total reward: 24.0 Training loss: 1.8775 Explore P: 0.7855
Episode: 3484 Total reward: 11.0 Training loss: 20.7885 Explore P: 0.7855
Episode: 3485 Total reward: 29.0 Training loss: 0.1301 Explore P: 0.7855
Episode: 3486 Total reward: 12.0 Training loss: 0.2585 Explore P: 0.7854
Episode: 3487 Total reward: 11.0 Training loss: 44.6691 Explore P: 0.7854
Episode: 3488 Total reward: 10.0 Training loss: 17.7738 Explore P: 0.7854
Episode: 3489 Total reward: 12.0 Training loss: 0.1249 Explore P: 0.7854
Episode: 3490 Total reward: 13.0 Training loss: 0.1979 Explore P: 0.7854
Episode: 3491 Total reward: 33.0 Training loss: 3.6803 Explore P: 0.7853
Episode: 3492 Total reward: 16.0 Training loss: 1.1250 Explore P: 0.7853
Episode: 3493 Total reward: 9.0 Training loss: 10.8781 Explore P: 0.7853
Episode: 3494 Total reward: 13.0 Training loss: 0.1661 Explore P: 0.7853
Episode: 3495 Total reward: 24.0 Training loss: 0.9527 Explore P: 0.7852
Episode: 3496 Total reward: 17.0 Training loss: 4.0573 Explore P: 0.7852
Episode: 3497 Total reward: 15.0 Training loss: 27.4107 Explore P: 0.7852
Episode: 3498 Total reward: 10.0 Training loss: 0.6766 Explore P: 0.7852
Episode: 3499 Total reward: 9.0 Training loss: 11.0133 Explore P: 0.7851
Episode: 3500 Total reward: 18.0 Training loss: 9.6070 Explore P: 0.7851
Episode: 3501 Total reward: 12.0 Training loss: 0.7373 Explore P: 0.7851
Episode: 3502 Total reward: 10.0 Training loss: 7.9210 Explore P: 0.7851
Episode: 3503 Total reward: 11.0 Training loss: 0.5231 Explore P: 0.7851
Episode: 3504 Total reward: 14.0 Training loss: 0.0533 Explore P: 0.7850
Episode: 3505 Total reward: 14.0 Training loss: 4.9443 Explore P: 0.7850
Episode: 3506 Total reward: 8.0 Training loss: 0.1810 Explore P: 0.7850
Episode: 3507 Total reward: 14.0 Training loss: 4.4690 Explore P: 0.7850
Episode: 3508 Total reward: 62.0 Training loss: 6.8656 Explore P: 0.7849
Episode: 3509 Total reward: 12.0 Training loss: 3.4425 Explore P: 0.7849
Episode: 3510 Total reward: 18.0 Training loss: 0.0833 Explore P: 0.7848
Episode: 3511 Total reward: 27.0 Training loss: 0.2175 Explore P: 0.7848
Episode: 3512 Total reward: 14.0 Training loss: 1.4089 Explore P: 0.7848
Episode: 3513 Total reward: 41.0 Training loss: 4.0593 Explore P: 0.7847
Episode: 3514 Total reward: 27.0 Training loss: 9.6178 Explore P: 0.7847
Episode: 3515 Total reward: 11.0 Training loss: 28.5376 Explore P: 0.7847
Episode: 3516 Total reward: 29.0 Training loss: 4.3743 Explore P: 0.7846
Episode: 3517 Total reward: 7.0 Training loss: 8.4077 Explore P: 0.7846
Episode: 3518 Total reward: 32.0 Training loss: 16.9814 Explore P: 0.7845
Episode: 3519 Total reward: 12.0 Training loss: 15.1498 Explore P: 0.7845
Episode: 3520 Total reward: 13.0 Training loss: 0.3084 Explore P: 0.7845
Episode: 3521 Total reward: 22.0 Training loss: 14.2055 Explore P: 0.7845
Episode: 3522 Total reward: 25.0 Training loss: 15.4048 Explore P: 0.7844
Episode: 3523 Total reward: 79.0 Training loss: 0.0740 Explore P: 0.7843
Episode: 3524 Total reward: 15.0 Training loss: 5.4485 Explore P: 0.7843
Episode: 3525 Total reward: 39.0 Training loss: 3.8780 Explore P: 0.7842
Episode: 3526 Total reward: 14.0 Training loss: 2.9086 Explore P: 0.7842
Episode: 3527 Total reward: 18.0 Training loss: 0.0731 Explore P: 0.7842
Episode: 3528 Total reward: 17.0 Training loss: 0.8257 Explore P: 0.7842
Episode: 3529 Total reward: 24.0 Training loss: 2.4416 Explore P: 0.7841
Episode: 3530 Total reward: 19.0 Training loss: 0.3970 Explore P: 0.7841
Episode: 3531 Total reward: 14.0 Training loss: 0.8135 Explore P: 0.7841
Episode: 3532 Total reward: 38.0 Training loss: 14.3372 Explore P: 0.7840
Episode: 3533 Total reward: 36.0 Training loss: 0.1074 Explore P: 0.7840
Episode: 3534 Total reward: 17.0 Training loss: 45.8343 Explore P: 0.7839
Episode: 3535 Total reward: 22.0 Training loss: 0.3309 Explore P: 0.7839
Episode: 3536 Total reward: 9.0 Training loss: 1.0142 Explore P: 0.7839
Episode: 3537 Total reward: 9.0 Training loss: 426.6924 Explore P: 0.7839
Episode: 3538 Total reward: 9.0 Training loss: 0.2390 Explore P: 0.7839
Episode: 3539 Total reward: 12.0 Training loss: 19.5441 Explore P: 0.7838
Episode: 3540 Total reward: 19.0 Training loss: 0.1327 Explore P: 0.7838
Episode: 3541 Total reward: 14.0 Training loss: 2.0316 Explore P: 0.7838
Episode: 3542 Total reward: 20.0 Training loss: 12.2538 Explore P: 0.7838
Episode: 3543 Total reward: 14.0 Training loss: 14.4599 Explore P: 0.7837
Episode: 3544 Total reward: 18.0 Training loss: 2.3200 Explore P: 0.7837
Episode: 3545 Total reward: 18.0 Training loss: 8.3143 Explore P: 0.7837
Episode: 3546 Total reward: 28.0 Training loss: 0.0679 Explore P: 0.7836
Episode: 3547 Total reward: 11.0 Training loss: 0.6857 Explore P: 0.7836
Episode: 3548 Total reward: 29.0 Training loss: 0.1065 Explore P: 0.7836
Episode: 3549 Total reward: 39.0 Training loss: 26.9331 Explore P: 0.7835
Episode: 3550 Total reward: 12.0 Training loss: 46.2577 Explore P: 0.7835
Episode: 3551 Total reward: 15.0 Training loss: 0.5087 Explore P: 0.7835
Episode: 3552 Total reward: 15.0 Training loss: 0.2063 Explore P: 0.7834
Episode: 3553 Total reward: 66.0 Training loss: 0.1405 Explore P: 0.7833
Episode: 3554 Total reward: 18.0 Training loss: 2.4590 Explore P: 0.7833
Episode: 3555 Total reward: 17.0 Training loss: 2.8125 Explore P: 0.7833
Episode: 3556 Total reward: 30.0 Training loss: 4.0910 Explore P: 0.7832
Episode: 3557 Total reward: 27.0 Training loss: 7.1812 Explore P: 0.7832
Episode: 3558 Total reward: 13.0 Training loss: 1.4487 Explore P: 0.7832
Episode: 3559 Total reward: 11.0 Training loss: 11.3270 Explore P: 0.7832
Episode: 3560 Total reward: 17.0 Training loss: 0.1833 Explore P: 0.7831
Episode: 3561 Total reward: 12.0 Training loss: 3.8569 Explore P: 0.7831
Episode: 3562 Total reward: 16.0 Training loss: 9.8952 Explore P: 0.7831
Episode: 3563 Total reward: 9.0 Training loss: 2.3553 Explore P: 0.7831
Episode: 3564 Total reward: 11.0 Training loss: 5.1724 Explore P: 0.7831
Episode: 3565 Total reward: 30.0 Training loss: 0.0832 Explore P: 0.7830
Episode: 3566 Total reward: 33.0 Training loss: 25.7800 Explore P: 0.7830
Episode: 3567 Total reward: 29.0 Training loss: 0.0819 Explore P: 0.7829
Episode: 3568 Total reward: 13.0 Training loss: 52.7645 Explore P: 0.7829
Episode: 3569 Total reward: 9.0 Training loss: 0.2612 Explore P: 0.7829
Episode: 3570 Total reward: 10.0 Training loss: 21.1556 Explore P: 0.7829
Episode: 3571 Total reward: 8.0 Training loss: 22.4832 Explore P: 0.7829
Episode: 3572 Total reward: 14.0 Training loss: 0.1523 Explore P: 0.7828
Episode: 3573 Total reward: 10.0 Training loss: 8.3436 Explore P: 0.7828
Episode: 3574 Total reward: 49.0 Training loss: 2.8906 Explore P: 0.7827
Episode: 3575 Total reward: 68.0 Training loss: 13.9967 Explore P: 0.7826
Episode: 3576 Total reward: 14.0 Training loss: 0.0553 Explore P: 0.7826
Episode: 3577 Total reward: 17.0 Training loss: 2.6016 Explore P: 0.7826
Episode: 3578 Total reward: 23.0 Training loss: 44.4874 Explore P: 0.7826
Episode: 3579 Total reward: 30.0 Training loss: 5.2388 Explore P: 0.7825
Episode: 3580 Total reward: 30.0 Training loss: 3.5396 Explore P: 0.7825
Episode: 3581 Total reward: 19.0 Training loss: 50.2340 Explore P: 0.7824
Episode: 3582 Total reward: 26.0 Training loss: 2.7746 Explore P: 0.7824
Episode: 3583 Total reward: 11.0 Training loss: 2.5260 Explore P: 0.7824
Episode: 3584 Total reward: 14.0 Training loss: 1.4619 Explore P: 0.7824
Episode: 3585 Total reward: 18.0 Training loss: 625.0002 Explore P: 0.7823
Episode: 3586 Total reward: 23.0 Training loss: 0.1143 Explore P: 0.7823
Episode: 3587 Total reward: 13.0 Training loss: 18.5040 Explore P: 0.7823
Episode: 3588 Total reward: 43.0 Training loss: 5.7263 Explore P: 0.7822
Episode: 3589 Total reward: 11.0 Training loss: 0.2360 Explore P: 0.7822
Episode: 3590 Total reward: 14.0 Training loss: 2.1503 Explore P: 0.7822
Episode: 3591 Total reward: 22.0 Training loss: 3.4806 Explore P: 0.7821
Episode: 3592 Total reward: 25.0 Training loss: 16.7774 Explore P: 0.7821
Episode: 3593 Total reward: 20.0 Training loss: 0.1397 Explore P: 0.7821
Episode: 3594 Total reward: 57.0 Training loss: 12.1154 Explore P: 0.7820
Episode: 3595 Total reward: 11.0 Training loss: 0.0877 Explore P: 0.7820
Episode: 3596 Total reward: 16.0 Training loss: 0.0206 Explore P: 0.7819
Episode: 3597 Total reward: 18.0 Training loss: 15.0197 Explore P: 0.7819
Episode: 3598 Total reward: 11.0 Training loss: 31.0037 Explore P: 0.7819
Episode: 3599 Total reward: 20.0 Training loss: 0.1104 Explore P: 0.7819
Episode: 3600 Total reward: 18.0 Training loss: 12.7813 Explore P: 0.7818
Episode: 3601 Total reward: 34.0 Training loss: 0.3380 Explore P: 0.7818
Episode: 3602 Total reward: 8.0 Training loss: 0.2415 Explore P: 0.7818
Episode: 3603 Total reward: 10.0 Training loss: 9.2433 Explore P: 0.7817
Episode: 3604 Total reward: 23.0 Training loss: 0.2790 Explore P: 0.7817
Episode: 3605 Total reward: 12.0 Training loss: 3.1607 Explore P: 0.7817
Episode: 3606 Total reward: 44.0 Training loss: 0.1142 Explore P: 0.7816
Episode: 3607 Total reward: 24.0 Training loss: 1.7442 Explore P: 0.7816
Episode: 3608 Total reward: 16.0 Training loss: 0.1702 Explore P: 0.7816
Episode: 3609 Total reward: 12.0 Training loss: 12.3312 Explore P: 0.7815
Episode: 3610 Total reward: 20.0 Training loss: 5.8359 Explore P: 0.7815
Episode: 3611 Total reward: 25.0 Training loss: 11.4108 Explore P: 0.7815
Episode: 3612 Total reward: 16.0 Training loss: 11.4859 Explore P: 0.7815
Episode: 3613 Total reward: 30.0 Training loss: 0.1298 Explore P: 0.7814
Episode: 3614 Total reward: 23.0 Training loss: 7.1984 Explore P: 0.7814
Episode: 3615 Total reward: 16.0 Training loss: 1.6204 Explore P: 0.7813
Episode: 3616 Total reward: 20.0 Training loss: 23.2499 Explore P: 0.7813
Episode: 3617 Total reward: 19.0 Training loss: 18.7099 Explore P: 0.7813
Episode: 3618 Total reward: 28.0 Training loss: 0.1001 Explore P: 0.7812
Episode: 3619 Total reward: 62.0 Training loss: 66.7570 Explore P: 0.7811
Episode: 3620 Total reward: 33.0 Training loss: 375.1791 Explore P: 0.7811
Episode: 3621 Total reward: 15.0 Training loss: 0.3954 Explore P: 0.7811
Episode: 3622 Total reward: 12.0 Training loss: 10.1106 Explore P: 0.7811
Episode: 3623 Total reward: 9.0 Training loss: 0.0931 Explore P: 0.7810
Episode: 3624 Total reward: 13.0 Training loss: 3.2622 Explore P: 0.7810
Episode: 3625 Total reward: 8.0 Training loss: 0.1460 Explore P: 0.7810
Episode: 3626 Total reward: 18.0 Training loss: 0.0700 Explore P: 0.7810
Episode: 3627 Total reward: 25.0 Training loss: 5.8175 Explore P: 0.7809
Episode: 3628 Total reward: 48.0 Training loss: 2.9928 Explore P: 0.7809
Episode: 3629 Total reward: 10.0 Training loss: 0.1149 Explore P: 0.7809
Episode: 3630 Total reward: 10.0 Training loss: 31.2563 Explore P: 0.7808
Episode: 3631 Total reward: 21.0 Training loss: 1.6308 Explore P: 0.7808
Episode: 3632 Total reward: 11.0 Training loss: 0.3085 Explore P: 0.7808
Episode: 3633 Total reward: 14.0 Training loss: 0.9737 Explore P: 0.7808
Episode: 3634 Total reward: 19.0 Training loss: 11.1050 Explore P: 0.7807
Episode: 3635 Total reward: 25.0 Training loss: 4.7291 Explore P: 0.7807
Episode: 3636 Total reward: 12.0 Training loss: 0.3212 Explore P: 0.7807
Episode: 3637 Total reward: 30.0 Training loss: 1.1704 Explore P: 0.7806
Episode: 3638 Total reward: 16.0 Training loss: 5.5143 Explore P: 0.7806
Episode: 3639 Total reward: 11.0 Training loss: 6.8159 Explore P: 0.7806
Episode: 3640 Total reward: 12.0 Training loss: 0.7991 Explore P: 0.7806
Episode: 3641 Total reward: 10.0 Training loss: 2.0843 Explore P: 0.7806
Episode: 3642 Total reward: 21.0 Training loss: 2.7176 Explore P: 0.7805
Episode: 3643 Total reward: 12.0 Training loss: 4.6897 Explore P: 0.7805
Episode: 3644 Total reward: 15.0 Training loss: 5.4930 Explore P: 0.7805
Episode: 3645 Total reward: 11.0 Training loss: 0.1151 Explore P: 0.7805
Episode: 3646 Total reward: 12.0 Training loss: 0.6517 Explore P: 0.7804
Episode: 3647 Total reward: 10.0 Training loss: 0.1495 Explore P: 0.7804
Episode: 3648 Total reward: 17.0 Training loss: 10.4680 Explore P: 0.7804
Episode: 3649 Total reward: 21.0 Training loss: 0.2287 Explore P: 0.7804
Episode: 3650 Total reward: 15.0 Training loss: 0.0209 Explore P: 0.7804
Episode: 3651 Total reward: 12.0 Training loss: 0.2523 Explore P: 0.7803
Episode: 3652 Total reward: 25.0 Training loss: 2.0691 Explore P: 0.7803
Episode: 3653 Total reward: 27.0 Training loss: 0.4349 Explore P: 0.7803
Episode: 3654 Total reward: 21.0 Training loss: 7.3320 Explore P: 0.7802
Episode: 3655 Total reward: 17.0 Training loss: 3.0614 Explore P: 0.7802
Episode: 3656 Total reward: 18.0 Training loss: 26.2045 Explore P: 0.7802
Episode: 3657 Total reward: 21.0 Training loss: 0.0727 Explore P: 0.7801
Episode: 3658 Total reward: 9.0 Training loss: 1.0474 Explore P: 0.7801
Episode: 3659 Total reward: 8.0 Training loss: 0.1235 Explore P: 0.7801
Episode: 3660 Total reward: 13.0 Training loss: 4.6960 Explore P: 0.7801
Episode: 3661 Total reward: 14.0 Training loss: 6.8833 Explore P: 0.7801
Episode: 3662 Total reward: 21.0 Training loss: 0.2113 Explore P: 0.7800
Episode: 3663 Total reward: 13.0 Training loss: 9.7371 Explore P: 0.7800
Episode: 3664 Total reward: 19.0 Training loss: 5.1405 Explore P: 0.7800
Episode: 3665 Total reward: 9.0 Training loss: 12.6820 Explore P: 0.7800
Episode: 3666 Total reward: 14.0 Training loss: 0.2052 Explore P: 0.7799
Episode: 3667 Total reward: 37.0 Training loss: 0.1323 Explore P: 0.7799
Episode: 3668 Total reward: 11.0 Training loss: 0.8154 Explore P: 0.7799
Episode: 3669 Total reward: 12.0 Training loss: 0.5663 Explore P: 0.7799
Episode: 3670 Total reward: 20.0 Training loss: 13.5064 Explore P: 0.7798
Episode: 3671 Total reward: 26.0 Training loss: 5.5467 Explore P: 0.7798
Episode: 3672 Total reward: 34.0 Training loss: 4.1150 Explore P: 0.7797
Episode: 3673 Total reward: 15.0 Training loss: 0.4955 Explore P: 0.7797
Episode: 3674 Total reward: 18.0 Training loss: 0.2256 Explore P: 0.7797
Episode: 3675 Total reward: 12.0 Training loss: 10.9623 Explore P: 0.7797
Episode: 3676 Total reward: 11.0 Training loss: 9.4977 Explore P: 0.7796
Episode: 3677 Total reward: 10.0 Training loss: 28.2600 Explore P: 0.7796
Episode: 3678 Total reward: 14.0 Training loss: 17.5823 Explore P: 0.7796
Episode: 3679 Total reward: 22.0 Training loss: 30.6337 Explore P: 0.7796
Episode: 3680 Total reward: 10.0 Training loss: 5.5032 Explore P: 0.7796
Episode: 3681 Total reward: 33.0 Training loss: 23.8648 Explore P: 0.7795
Episode: 3682 Total reward: 18.0 Training loss: 1.8402 Explore P: 0.7795
Episode: 3683 Total reward: 10.0 Training loss: 0.1901 Explore P: 0.7795
Episode: 3684 Total reward: 14.0 Training loss: 7.4908 Explore P: 0.7794
Episode: 3685 Total reward: 24.0 Training loss: 5.3622 Explore P: 0.7794
Episode: 3686 Total reward: 24.0 Training loss: 162.6020 Explore P: 0.7794
Episode: 3687 Total reward: 15.0 Training loss: 0.5600 Explore P: 0.7793
Episode: 3688 Total reward: 18.0 Training loss: 4.9001 Explore P: 0.7793
Episode: 3689 Total reward: 15.0 Training loss: 0.0774 Explore P: 0.7793
Episode: 3690 Total reward: 18.0 Training loss: 0.2700 Explore P: 0.7793
Episode: 3691 Total reward: 22.0 Training loss: 7.6339 Explore P: 0.7792
Episode: 3692 Total reward: 18.0 Training loss: 0.0683 Explore P: 0.7792
Episode: 3693 Total reward: 26.0 Training loss: 0.6264 Explore P: 0.7792
Episode: 3694 Total reward: 57.0 Training loss: 0.1187 Explore P: 0.7791
Episode: 3695 Total reward: 11.0 Training loss: 0.1740 Explore P: 0.7791
Episode: 3696 Total reward: 57.0 Training loss: 59.9995 Explore P: 0.7790
Episode: 3697 Total reward: 15.0 Training loss: 0.3262 Explore P: 0.7790
Episode: 3698 Total reward: 18.0 Training loss: 3.2464 Explore P: 0.7789
Episode: 3699 Total reward: 37.0 Training loss: 0.5488 Explore P: 0.7789
Episode: 3700 Total reward: 26.0 Training loss: 40.8606 Explore P: 0.7788
Episode: 3701 Total reward: 9.0 Training loss: 55.9100 Explore P: 0.7788
Episode: 3702 Total reward: 19.0 Training loss: 2.1482 Explore P: 0.7788
Episode: 3703 Total reward: 20.0 Training loss: 6.5239 Explore P: 0.7788
Episode: 3704 Total reward: 11.0 Training loss: 19.5900 Explore P: 0.7787
Episode: 3705 Total reward: 12.0 Training loss: 0.0913 Explore P: 0.7787
Episode: 3706 Total reward: 10.0 Training loss: 0.1830 Explore P: 0.7787
Episode: 3707 Total reward: 21.0 Training loss: 0.0195 Explore P: 0.7787
Episode: 3708 Total reward: 10.0 Training loss: 12.2665 Explore P: 0.7787
Episode: 3709 Total reward: 41.0 Training loss: 1.9700 Explore P: 0.7786
Episode: 3710 Total reward: 24.0 Training loss: 18.5213 Explore P: 0.7786
Episode: 3711 Total reward: 17.0 Training loss: 0.1064 Explore P: 0.7785
Episode: 3712 Total reward: 10.0 Training loss: 0.5606 Explore P: 0.7785
Episode: 3713 Total reward: 21.0 Training loss: 3.0214 Explore P: 0.7785
Episode: 3714 Total reward: 17.0 Training loss: 35.8117 Explore P: 0.7785
Episode: 3715 Total reward: 25.0 Training loss: 20.8924 Explore P: 0.7784
Episode: 3716 Total reward: 13.0 Training loss: 3.7610 Explore P: 0.7784
Episode: 3717 Total reward: 11.0 Training loss: 0.1883 Explore P: 0.7784
Episode: 3718 Total reward: 12.0 Training loss: 0.5148 Explore P: 0.7784
Episode: 3719 Total reward: 9.0 Training loss: 15.6485 Explore P: 0.7784
Episode: 3720 Total reward: 25.0 Training loss: 34.1257 Explore P: 0.7783
Episode: 3721 Total reward: 16.0 Training loss: 0.3577 Explore P: 0.7783
Episode: 3722 Total reward: 36.0 Training loss: 44.2953 Explore P: 0.7782
Episode: 3723 Total reward: 42.0 Training loss: 43.1595 Explore P: 0.7782
Episode: 3724 Total reward: 11.0 Training loss: 0.6793 Explore P: 0.7782
Episode: 3725 Total reward: 11.0 Training loss: 81.9777 Explore P: 0.7781
Episode: 3726 Total reward: 17.0 Training loss: 0.1313 Explore P: 0.7781
Episode: 3727 Total reward: 9.0 Training loss: 0.2452 Explore P: 0.7781
Episode: 3728 Total reward: 24.0 Training loss: 6.3647 Explore P: 0.7781
Episode: 3729 Total reward: 29.0 Training loss: 0.1219 Explore P: 0.7780
Episode: 3730 Total reward: 14.0 Training loss: 1.1456 Explore P: 0.7780
Episode: 3731 Total reward: 13.0 Training loss: 10.5791 Explore P: 0.7780
Episode: 3732 Total reward: 43.0 Training loss: 0.1333 Explore P: 0.7779
Episode: 3733 Total reward: 15.0 Training loss: 0.1897 Explore P: 0.7779
Episode: 3734 Total reward: 9.0 Training loss: 1.7363 Explore P: 0.7779
Episode: 3735 Total reward: 9.0 Training loss: 0.0664 Explore P: 0.7779
Episode: 3736 Total reward: 26.0 Training loss: 0.0528 Explore P: 0.7778
Episode: 3737 Total reward: 15.0 Training loss: 10.5413 Explore P: 0.7778
Episode: 3738 Total reward: 16.0 Training loss: 0.2131 Explore P: 0.7778
Episode: 3739 Total reward: 14.0 Training loss: 9.8981 Explore P: 0.7777
Episode: 3740 Total reward: 11.0 Training loss: 0.0869 Explore P: 0.7777
Episode: 3741 Total reward: 17.0 Training loss: 3.5103 Explore P: 0.7777
Episode: 3742 Total reward: 14.0 Training loss: 0.0733 Explore P: 0.7777
Episode: 3743 Total reward: 10.0 Training loss: 8.1581 Explore P: 0.7777
Episode: 3744 Total reward: 21.0 Training loss: 6.1047 Explore P: 0.7776
Episode: 3745 Total reward: 8.0 Training loss: 35.0404 Explore P: 0.7776
Episode: 3746 Total reward: 18.0 Training loss: 4.7970 Explore P: 0.7776
Episode: 3747 Total reward: 9.0 Training loss: 9.4765 Explore P: 0.7776
Episode: 3748 Total reward: 14.0 Training loss: 2.7869 Explore P: 0.7776
Episode: 3749 Total reward: 12.0 Training loss: 0.0259 Explore P: 0.7775
Episode: 3750 Total reward: 22.0 Training loss: 0.0859 Explore P: 0.7775
Episode: 3751 Total reward: 12.0 Training loss: 0.0908 Explore P: 0.7775
Episode: 3752 Total reward: 15.0 Training loss: 0.0756 Explore P: 0.7775
Episode: 3753 Total reward: 17.0 Training loss: 0.0776 Explore P: 0.7774
Episode: 3754 Total reward: 30.0 Training loss: 0.1753 Explore P: 0.7774
Episode: 3755 Total reward: 14.0 Training loss: 0.1957 Explore P: 0.7774
Episode: 3756 Total reward: 29.0 Training loss: 64.9921 Explore P: 0.7773
Episode: 3757 Total reward: 14.0 Training loss: 8.3900 Explore P: 0.7773
Episode: 3758 Total reward: 13.0 Training loss: 7.8719 Explore P: 0.7773
Episode: 3759 Total reward: 27.0 Training loss: 5.1637 Explore P: 0.7772
Episode: 3760 Total reward: 13.0 Training loss: 0.0681 Explore P: 0.7772
Episode: 3761 Total reward: 17.0 Training loss: 4.4160 Explore P: 0.7772
Episode: 3762 Total reward: 9.0 Training loss: 29.2714 Explore P: 0.7772
Episode: 3763 Total reward: 15.0 Training loss: 4.0648 Explore P: 0.7772
Episode: 3764 Total reward: 14.0 Training loss: 0.1839 Explore P: 0.7771
Episode: 3765 Total reward: 23.0 Training loss: 1.0249 Explore P: 0.7771
Episode: 3766 Total reward: 12.0 Training loss: 6.1460 Explore P: 0.7771
Episode: 3767 Total reward: 12.0 Training loss: 0.1279 Explore P: 0.7771
Episode: 3768 Total reward: 14.0 Training loss: 0.1698 Explore P: 0.7770
Episode: 3769 Total reward: 15.0 Training loss: 0.1347 Explore P: 0.7770
Episode: 3770 Total reward: 8.0 Training loss: 2.0449 Explore P: 0.7770
Episode: 3771 Total reward: 15.0 Training loss: 7.6615 Explore P: 0.7770
Episode: 3772 Total reward: 12.0 Training loss: 6.5078 Explore P: 0.7770
Episode: 3773 Total reward: 22.0 Training loss: 1.5240 Explore P: 0.7769
Episode: 3774 Total reward: 11.0 Training loss: 26.6207 Explore P: 0.7769
Episode: 3775 Total reward: 10.0 Training loss: 0.1373 Explore P: 0.7769
Episode: 3776 Total reward: 17.0 Training loss: 0.2606 Explore P: 0.7769
Episode: 3777 Total reward: 21.0 Training loss: 4.6966 Explore P: 0.7768
Episode: 3778 Total reward: 10.0 Training loss: 0.3496 Explore P: 0.7768
Episode: 3779 Total reward: 10.0 Training loss: 1.7671 Explore P: 0.7768
Episode: 3780 Total reward: 20.0 Training loss: 0.4960 Explore P: 0.7768
Episode: 3781 Total reward: 10.0 Training loss: 38.0262 Explore P: 0.7768
Episode: 3782 Total reward: 25.0 Training loss: 2.0432 Explore P: 0.7767
Episode: 3783 Total reward: 13.0 Training loss: 0.0942 Explore P: 0.7767
Episode: 3784 Total reward: 36.0 Training loss: 7.6104 Explore P: 0.7767
Episode: 3785 Total reward: 11.0 Training loss: 0.0526 Explore P: 0.7766
Episode: 3786 Total reward: 22.0 Training loss: 10.8414 Explore P: 0.7766
Episode: 3787 Total reward: 27.0 Training loss: 6.0181 Explore P: 0.7766
Episode: 3788 Total reward: 10.0 Training loss: 4.4404 Explore P: 0.7765
Episode: 3789 Total reward: 13.0 Training loss: 0.7528 Explore P: 0.7765
Episode: 3790 Total reward: 18.0 Training loss: 46.3247 Explore P: 0.7765
Episode: 3791 Total reward: 17.0 Training loss: 20.4193 Explore P: 0.7765
Episode: 3792 Total reward: 27.0 Training loss: 26.9497 Explore P: 0.7764
Episode: 3793 Total reward: 31.0 Training loss: 1.3838 Explore P: 0.7764
Episode: 3794 Total reward: 40.0 Training loss: 0.9480 Explore P: 0.7763
Episode: 3795 Total reward: 31.0 Training loss: 8.8377 Explore P: 0.7763
Episode: 3796 Total reward: 9.0 Training loss: 13.3580 Explore P: 0.7763
Episode: 3797 Total reward: 15.0 Training loss: 0.0786 Explore P: 0.7762
Episode: 3798 Total reward: 11.0 Training loss: 3.0331 Explore P: 0.7762
Episode: 3799 Total reward: 9.0 Training loss: 41.6245 Explore P: 0.7762
Episode: 3800 Total reward: 38.0 Training loss: 7.6206 Explore P: 0.7761
Episode: 3801 Total reward: 14.0 Training loss: 0.2371 Explore P: 0.7761
Episode: 3802 Total reward: 44.0 Training loss: 0.9649 Explore P: 0.7761
Episode: 3803 Total reward: 11.0 Training loss: 9.3297 Explore P: 0.7760
Episode: 3804 Total reward: 23.0 Training loss: 2.8030 Explore P: 0.7760
Episode: 3805 Total reward: 27.0 Training loss: 21.6009 Explore P: 0.7760
Episode: 3806 Total reward: 16.0 Training loss: 4.0424 Explore P: 0.7759
Episode: 3807 Total reward: 10.0 Training loss: 6.2829 Explore P: 0.7759
Episode: 3808 Total reward: 34.0 Training loss: 1.6069 Explore P: 0.7759
Episode: 3809 Total reward: 9.0 Training loss: 0.0740 Explore P: 0.7759
Episode: 3810 Total reward: 14.0 Training loss: 16.2934 Explore P: 0.7758
Episode: 3811 Total reward: 19.0 Training loss: 12.1368 Explore P: 0.7758
Episode: 3812 Total reward: 13.0 Training loss: 9.8585 Explore P: 0.7758
Episode: 3813 Total reward: 27.0 Training loss: 3.4976 Explore P: 0.7757
Episode: 3814 Total reward: 23.0 Training loss: 4.7555 Explore P: 0.7757
Episode: 3815 Total reward: 16.0 Training loss: 0.2674 Explore P: 0.7757
Episode: 3816 Total reward: 28.0 Training loss: 2.0788 Explore P: 0.7756
Episode: 3817 Total reward: 14.0 Training loss: 0.1957 Explore P: 0.7756
Episode: 3818 Total reward: 12.0 Training loss: 5.1062 Explore P: 0.7756
Episode: 3819 Total reward: 74.0 Training loss: 4.5795 Explore P: 0.7755
Episode: 3820 Total reward: 25.0 Training loss: 0.4522 Explore P: 0.7755
Episode: 3821 Total reward: 11.0 Training loss: 0.0684 Explore P: 0.7754
Episode: 3822 Total reward: 10.0 Training loss: 0.0651 Explore P: 0.7754
Episode: 3823 Total reward: 22.0 Training loss: 6.8759 Explore P: 0.7754
Episode: 3824 Total reward: 11.0 Training loss: 1.7124 Explore P: 0.7754
Episode: 3825 Total reward: 17.0 Training loss: 0.0825 Explore P: 0.7753
Episode: 3826 Total reward: 12.0 Training loss: 18.0540 Explore P: 0.7753
Episode: 3827 Total reward: 9.0 Training loss: 12.2406 Explore P: 0.7753
Episode: 3828 Total reward: 16.0 Training loss: 11.6496 Explore P: 0.7753
Episode: 3829 Total reward: 15.0 Training loss: 0.0392 Explore P: 0.7753
Episode: 3830 Total reward: 20.0 Training loss: 0.0816 Explore P: 0.7752
Episode: 3831 Total reward: 20.0 Training loss: 4.6030 Explore P: 0.7752
Episode: 3832 Total reward: 57.0 Training loss: 81.7854 Explore P: 0.7751
Episode: 3833 Total reward: 18.0 Training loss: 0.1297 Explore P: 0.7751
Episode: 3834 Total reward: 18.0 Training loss: 0.0978 Explore P: 0.7751
Episode: 3835 Total reward: 13.0 Training loss: 15.5733 Explore P: 0.7750
Episode: 3836 Total reward: 12.0 Training loss: 0.2708 Explore P: 0.7750
Episode: 3837 Total reward: 20.0 Training loss: 2.0023 Explore P: 0.7750
Episode: 3838 Total reward: 20.0 Training loss: 0.0401 Explore P: 0.7750
Episode: 3839 Total reward: 36.0 Training loss: 0.1471 Explore P: 0.7749
Episode: 3840 Total reward: 22.0 Training loss: 2.1114 Explore P: 0.7749
Episode: 3841 Total reward: 21.0 Training loss: 5.3532 Explore P: 0.7748
Episode: 3842 Total reward: 16.0 Training loss: 0.4049 Explore P: 0.7748
Episode: 3843 Total reward: 13.0 Training loss: 0.1303 Explore P: 0.7748
Episode: 3844 Total reward: 28.0 Training loss: 0.1106 Explore P: 0.7748
Episode: 3845 Total reward: 21.0 Training loss: 0.1958 Explore P: 0.7747
Episode: 3846 Total reward: 32.0 Training loss: 0.2248 Explore P: 0.7747
Episode: 3847 Total reward: 12.0 Training loss: 9.5770 Explore P: 0.7747
Episode: 3848 Total reward: 7.0 Training loss: 33.6825 Explore P: 0.7746
Episode: 3849 Total reward: 30.0 Training loss: 47.5807 Explore P: 0.7746
Episode: 3850 Total reward: 12.0 Training loss: 0.1047 Explore P: 0.7746
Episode: 3851 Total reward: 31.0 Training loss: 0.0512 Explore P: 0.7745
Episode: 3852 Total reward: 24.0 Training loss: 7.5228 Explore P: 0.7745
Episode: 3853 Total reward: 19.0 Training loss: 1.2669 Explore P: 0.7745
Episode: 3854 Total reward: 32.0 Training loss: 0.0745 Explore P: 0.7744
Episode: 3855 Total reward: 8.0 Training loss: 0.1073 Explore P: 0.7744
Episode: 3856 Total reward: 38.0 Training loss: 2.6297 Explore P: 0.7743
Episode: 3857 Total reward: 28.0 Training loss: 0.1010 Explore P: 0.7743
Episode: 3858 Total reward: 18.0 Training loss: 47.1823 Explore P: 0.7743
Episode: 3859 Total reward: 11.0 Training loss: 22.4802 Explore P: 0.7743
Episode: 3860 Total reward: 15.0 Training loss: 31.9133 Explore P: 0.7742
Episode: 3861 Total reward: 16.0 Training loss: 0.0418 Explore P: 0.7742
Episode: 3862 Total reward: 36.0 Training loss: 28.6614 Explore P: 0.7742
Episode: 3863 Total reward: 10.0 Training loss: 0.0491 Explore P: 0.7741
Episode: 3864 Total reward: 23.0 Training loss: 6.9091 Explore P: 0.7741
Episode: 3865 Total reward: 11.0 Training loss: 167.5822 Explore P: 0.7741
Episode: 3866 Total reward: 20.0 Training loss: 0.1469 Explore P: 0.7741
Episode: 3867 Total reward: 12.0 Training loss: 4.9273 Explore P: 0.7740
Episode: 3868 Total reward: 14.0 Training loss: 3.5621 Explore P: 0.7740
Episode: 3869 Total reward: 19.0 Training loss: 0.1616 Explore P: 0.7740
Episode: 3870 Total reward: 19.0 Training loss: 5.3924 Explore P: 0.7740
Episode: 3871 Total reward: 19.0 Training loss: 49.4329 Explore P: 0.7739
Episode: 3872 Total reward: 24.0 Training loss: 27.8029 Explore P: 0.7739
Episode: 3873 Total reward: 14.0 Training loss: 0.1799 Explore P: 0.7739
Episode: 3874 Total reward: 28.0 Training loss: 4.9252 Explore P: 0.7738
Episode: 3875 Total reward: 13.0 Training loss: 1.4296 Explore P: 0.7738
Episode: 3876 Total reward: 20.0 Training loss: 0.0668 Explore P: 0.7738
Episode: 3877 Total reward: 37.0 Training loss: 3.8787 Explore P: 0.7737
Episode: 3878 Total reward: 11.0 Training loss: 2.3417 Explore P: 0.7737
Episode: 3879 Total reward: 40.0 Training loss: 6.5396 Explore P: 0.7736
Episode: 3880 Total reward: 10.0 Training loss: 0.9038 Explore P: 0.7736
Episode: 3881 Total reward: 12.0 Training loss: 12.7642 Explore P: 0.7736
Episode: 3882 Total reward: 13.0 Training loss: 8.1568 Explore P: 0.7736
Episode: 3883 Total reward: 17.0 Training loss: 0.1330 Explore P: 0.7736
Episode: 3884 Total reward: 29.0 Training loss: 0.1008 Explore P: 0.7735
Episode: 3885 Total reward: 28.0 Training loss: 0.0584 Explore P: 0.7735
Episode: 3886 Total reward: 37.0 Training loss: 6.3405 Explore P: 0.7734
Episode: 3887 Total reward: 30.0 Training loss: 1.2245 Explore P: 0.7734
Episode: 3888 Total reward: 15.0 Training loss: 0.1363 Explore P: 0.7734
Episode: 3889 Total reward: 12.0 Training loss: 3.4770 Explore P: 0.7733
Episode: 3890 Total reward: 23.0 Training loss: 3.8229 Explore P: 0.7733
Episode: 3891 Total reward: 16.0 Training loss: 8.1787 Explore P: 0.7733
Episode: 3892 Total reward: 13.0 Training loss: 0.1263 Explore P: 0.7733
Episode: 3893 Total reward: 14.0 Training loss: 1.3002 Explore P: 0.7732
Episode: 3894 Total reward: 13.0 Training loss: 0.4870 Explore P: 0.7732
Episode: 3895 Total reward: 43.0 Training loss: 1.5306 Explore P: 0.7732
Episode: 3896 Total reward: 27.0 Training loss: 0.1768 Explore P: 0.7731
Episode: 3897 Total reward: 24.0 Training loss: 0.1241 Explore P: 0.7731
Episode: 3898 Total reward: 13.0 Training loss: 0.1266 Explore P: 0.7731
Episode: 3899 Total reward: 38.0 Training loss: 0.0947 Explore P: 0.7730
Episode: 3900 Total reward: 9.0 Training loss: 1.0873 Explore P: 0.7730
Episode: 3901 Total reward: 27.0 Training loss: 0.1475 Explore P: 0.7729
Episode: 3902 Total reward: 24.0 Training loss: 0.8427 Explore P: 0.7729
Episode: 3903 Total reward: 9.0 Training loss: 10.0107 Explore P: 0.7729
Episode: 3904 Total reward: 25.0 Training loss: 1.4623 Explore P: 0.7729
Episode: 3905 Total reward: 40.0 Training loss: 20.9789 Explore P: 0.7728
Episode: 3906 Total reward: 24.0 Training loss: 10.8156 Explore P: 0.7728
Episode: 3907 Total reward: 10.0 Training loss: 0.8750 Explore P: 0.7727
Episode: 3908 Total reward: 13.0 Training loss: 2.3831 Explore P: 0.7727
Episode: 3909 Total reward: 15.0 Training loss: 0.6034 Explore P: 0.7727
Episode: 3910 Total reward: 10.0 Training loss: 32.1767 Explore P: 0.7727
Episode: 3911 Total reward: 10.0 Training loss: 1.0141 Explore P: 0.7727
Episode: 3912 Total reward: 30.0 Training loss: 1.4463 Explore P: 0.7726
Episode: 3913 Total reward: 9.0 Training loss: 0.8273 Explore P: 0.7726
Episode: 3914 Total reward: 15.0 Training loss: 5.2338 Explore P: 0.7726
Episode: 3915 Total reward: 12.0 Training loss: 9.7231 Explore P: 0.7726
Episode: 3916 Total reward: 21.0 Training loss: 15.1950 Explore P: 0.7725
Episode: 3917 Total reward: 16.0 Training loss: 49.3365 Explore P: 0.7725
Episode: 3918 Total reward: 45.0 Training loss: 0.1891 Explore P: 0.7724
Episode: 3919 Total reward: 18.0 Training loss: 2.6820 Explore P: 0.7724
Episode: 3920 Total reward: 24.0 Training loss: 0.3180 Explore P: 0.7724
Episode: 3921 Total reward: 11.0 Training loss: 0.8816 Explore P: 0.7724
Episode: 3922 Total reward: 19.0 Training loss: 0.6263 Explore P: 0.7723
Episode: 3923 Total reward: 28.0 Training loss: 6.7367 Explore P: 0.7723
Episode: 3924 Total reward: 27.0 Training loss: 0.0909 Explore P: 0.7722
Episode: 3925 Total reward: 11.0 Training loss: 0.1581 Explore P: 0.7722
Episode: 3926 Total reward: 12.0 Training loss: 0.0675 Explore P: 0.7722
Episode: 3927 Total reward: 41.0 Training loss: 0.0858 Explore P: 0.7722
Episode: 3928 Total reward: 16.0 Training loss: 17.3318 Explore P: 0.7721
Episode: 3929 Total reward: 62.0 Training loss: 13.4697 Explore P: 0.7720
Episode: 3930 Total reward: 59.0 Training loss: 2.4898 Explore P: 0.7719
Episode: 3931 Total reward: 12.0 Training loss: 2.0547 Explore P: 0.7719
Episode: 3932 Total reward: 15.0 Training loss: 1.1760 Explore P: 0.7719
Episode: 3933 Total reward: 10.0 Training loss: 10.7402 Explore P: 0.7719
Episode: 3934 Total reward: 10.0 Training loss: 15.6962 Explore P: 0.7719
Episode: 3935 Total reward: 17.0 Training loss: 2.6366 Explore P: 0.7718
Episode: 3936 Total reward: 17.0 Training loss: 6.8680 Explore P: 0.7718
Episode: 3937 Total reward: 20.0 Training loss: 0.5980 Explore P: 0.7718
Episode: 3938 Total reward: 24.0 Training loss: 35.9448 Explore P: 0.7718
Episode: 3939 Total reward: 12.0 Training loss: 6.6582 Explore P: 0.7717
Episode: 3940 Total reward: 14.0 Training loss: 4.4103 Explore P: 0.7717
Episode: 3941 Total reward: 11.0 Training loss: 0.0758 Explore P: 0.7717
Episode: 3942 Total reward: 12.0 Training loss: 1.5189 Explore P: 0.7717
Episode: 3943 Total reward: 9.0 Training loss: 12.3330 Explore P: 0.7717
Episode: 3944 Total reward: 13.0 Training loss: 6.4298 Explore P: 0.7716
Episode: 3945 Total reward: 16.0 Training loss: 3.0663 Explore P: 0.7716
Episode: 3946 Total reward: 20.0 Training loss: 21.4744 Explore P: 0.7716
Episode: 3947 Total reward: 17.0 Training loss: 4.6004 Explore P: 0.7716
Episode: 3948 Total reward: 24.0 Training loss: 0.1787 Explore P: 0.7715
Episode: 3949 Total reward: 20.0 Training loss: 5.7688 Explore P: 0.7715
Episode: 3950 Total reward: 9.0 Training loss: 1.0266 Explore P: 0.7715
Episode: 3951 Total reward: 22.0 Training loss: 0.1521 Explore P: 0.7714
Episode: 3952 Total reward: 29.0 Training loss: 0.0872 Explore P: 0.7714
Episode: 3953 Total reward: 26.0 Training loss: 0.4031 Explore P: 0.7714
Episode: 3954 Total reward: 15.0 Training loss: 1.6884 Explore P: 0.7713
Episode: 3955 Total reward: 14.0 Training loss: 8.3280 Explore P: 0.7713
Episode: 3956 Total reward: 40.0 Training loss: 6.2718 Explore P: 0.7713
Episode: 3957 Total reward: 15.0 Training loss: 0.1163 Explore P: 0.7712
Episode: 3958 Total reward: 9.0 Training loss: 0.1676 Explore P: 0.7712
Episode: 3959 Total reward: 11.0 Training loss: 0.0634 Explore P: 0.7712
Episode: 3960 Total reward: 33.0 Training loss: 2.5294 Explore P: 0.7712
Episode: 3961 Total reward: 17.0 Training loss: 3.5894 Explore P: 0.7711
Episode: 3962 Total reward: 23.0 Training loss: 1.7378 Explore P: 0.7711
Episode: 3963 Total reward: 10.0 Training loss: 3.3224 Explore P: 0.7711
Episode: 3964 Total reward: 11.0 Training loss: 5.9911 Explore P: 0.7711
Episode: 3965 Total reward: 14.0 Training loss: 10.6317 Explore P: 0.7710
Episode: 3966 Total reward: 13.0 Training loss: 6.8833 Explore P: 0.7710
Episode: 3967 Total reward: 12.0 Training loss: 19.4622 Explore P: 0.7710
Episode: 3968 Total reward: 9.0 Training loss: 0.4917 Explore P: 0.7710
Episode: 3969 Total reward: 8.0 Training loss: 2.5502 Explore P: 0.7710
Episode: 3970 Total reward: 14.0 Training loss: 0.1325 Explore P: 0.7710
Episode: 3971 Total reward: 10.0 Training loss: 0.0847 Explore P: 0.7709
Episode: 3972 Total reward: 10.0 Training loss: 0.0720 Explore P: 0.7709
Episode: 3973 Total reward: 20.0 Training loss: 14.2118 Explore P: 0.7709
Episode: 3974 Total reward: 25.0 Training loss: 1.2768 Explore P: 0.7709
Episode: 3975 Total reward: 14.0 Training loss: 5.7064 Explore P: 0.7708
Episode: 3976 Total reward: 11.0 Training loss: 5.5094 Explore P: 0.7708
Episode: 3977 Total reward: 13.0 Training loss: 0.0890 Explore P: 0.7708
Episode: 3978 Total reward: 11.0 Training loss: 3.5422 Explore P: 0.7708
Episode: 3979 Total reward: 12.0 Training loss: 1.7632 Explore P: 0.7708
Episode: 3980 Total reward: 52.0 Training loss: 0.0514 Explore P: 0.7707
Episode: 3981 Total reward: 12.0 Training loss: 4.7966 Explore P: 0.7707
Episode: 3982 Total reward: 41.0 Training loss: 28.1637 Explore P: 0.7706
Episode: 3983 Total reward: 20.0 Training loss: 0.1072 Explore P: 0.7706
Episode: 3984 Total reward: 17.0 Training loss: 11.0407 Explore P: 0.7705
Episode: 3985 Total reward: 26.0 Training loss: 32.2486 Explore P: 0.7705
Episode: 3986 Total reward: 12.0 Training loss: 0.1876 Explore P: 0.7705
Episode: 3987 Total reward: 31.0 Training loss: 0.0268 Explore P: 0.7704
Episode: 3988 Total reward: 13.0 Training loss: 3.0486 Explore P: 0.7704
Episode: 3989 Total reward: 9.0 Training loss: 2.8528 Explore P: 0.7704
Episode: 3990 Total reward: 19.0 Training loss: 1.2840 Explore P: 0.7704
Episode: 3991 Total reward: 20.0 Training loss: 13.5887 Explore P: 0.7704
Episode: 3992 Total reward: 11.0 Training loss: 1.6229 Explore P: 0.7703
Episode: 3993 Total reward: 15.0 Training loss: 24.6447 Explore P: 0.7703
Episode: 3994 Total reward: 26.0 Training loss: 0.8272 Explore P: 0.7703
Episode: 3995 Total reward: 28.0 Training loss: 2.6715 Explore P: 0.7702
Episode: 3996 Total reward: 21.0 Training loss: 8.3886 Explore P: 0.7702
Episode: 3997 Total reward: 16.0 Training loss: 6.4419 Explore P: 0.7702
Episode: 3998 Total reward: 22.0 Training loss: 0.0872 Explore P: 0.7701
Episode: 3999 Total reward: 24.0 Training loss: 2.0489 Explore P: 0.7701
Episode: 4000 Total reward: 14.0 Training loss: 0.1421 Explore P: 0.7701
Episode: 4001 Total reward: 10.0 Training loss: 2.6827 Explore P: 0.7701
Episode: 4002 Total reward: 23.0 Training loss: 1.6109 Explore P: 0.7700
Episode: 4003 Total reward: 14.0 Training loss: 0.0362 Explore P: 0.7700
Episode: 4004 Total reward: 25.0 Training loss: 6.4083 Explore P: 0.7700
Episode: 4005 Total reward: 27.0 Training loss: 0.6861 Explore P: 0.7699
Episode: 4006 Total reward: 12.0 Training loss: 2.4265 Explore P: 0.7699
Episode: 4007 Total reward: 17.0 Training loss: 8.1961 Explore P: 0.7699
Episode: 4008 Total reward: 49.0 Training loss: 27.7325 Explore P: 0.7698
Episode: 4009 Total reward: 11.0 Training loss: 2.4439 Explore P: 0.7698
Episode: 4010 Total reward: 43.0 Training loss: 2.0271 Explore P: 0.7697
Episode: 4011 Total reward: 31.0 Training loss: 1.0481 Explore P: 0.7697
Episode: 4012 Total reward: 13.0 Training loss: 0.2030 Explore P: 0.7697
Episode: 4013 Total reward: 28.0 Training loss: 38.0919 Explore P: 0.7696
Episode: 4014 Total reward: 31.0 Training loss: 6.2391 Explore P: 0.7696
Episode: 4015 Total reward: 15.0 Training loss: 22.7727 Explore P: 0.7696
Episode: 4016 Total reward: 8.0 Training loss: 21.3924 Explore P: 0.7695
Episode: 4017 Total reward: 14.0 Training loss: 5.3446 Explore P: 0.7695
Episode: 4018 Total reward: 27.0 Training loss: 0.1023 Explore P: 0.7695
Episode: 4019 Total reward: 16.0 Training loss: 0.3044 Explore P: 0.7695
Episode: 4020 Total reward: 28.0 Training loss: 21.5814 Explore P: 0.7694
Episode: 4021 Total reward: 11.0 Training loss: 5.0637 Explore P: 0.7694
Episode: 4022 Total reward: 11.0 Training loss: 3.1563 Explore P: 0.7694
Episode: 4023 Total reward: 14.0 Training loss: 1.5453 Explore P: 0.7694
Episode: 4024 Total reward: 25.0 Training loss: 8.2685 Explore P: 0.7693
Episode: 4025 Total reward: 12.0 Training loss: 25.3622 Explore P: 0.7693
Episode: 4026 Total reward: 36.0 Training loss: 1.0415 Explore P: 0.7692
Episode: 4027 Total reward: 25.0 Training loss: 3.4148 Explore P: 0.7692
Episode: 4028 Total reward: 16.0 Training loss: 10.1403 Explore P: 0.7692
Episode: 4029 Total reward: 18.0 Training loss: 0.0731 Explore P: 0.7692
Episode: 4030 Total reward: 22.0 Training loss: 1.5578 Explore P: 0.7691
Episode: 4031 Total reward: 13.0 Training loss: 0.1322 Explore P: 0.7691
Episode: 4032 Total reward: 10.0 Training loss: 6.1964 Explore P: 0.7691
Episode: 4033 Total reward: 47.0 Training loss: 3.6202 Explore P: 0.7690
Episode: 4034 Total reward: 24.0 Training loss: 13.9349 Explore P: 0.7690
Episode: 4035 Total reward: 17.0 Training loss: 19.8048 Explore P: 0.7690
Episode: 4036 Total reward: 14.0 Training loss: 0.1655 Explore P: 0.7689
Episode: 4037 Total reward: 28.0 Training loss: 17.6146 Explore P: 0.7689
Episode: 4038 Total reward: 8.0 Training loss: 0.1702 Explore P: 0.7689
Episode: 4039 Total reward: 18.0 Training loss: 3.4573 Explore P: 0.7689
Episode: 4040 Total reward: 22.0 Training loss: 0.1119 Explore P: 0.7688
Episode: 4041 Total reward: 14.0 Training loss: 16.6620 Explore P: 0.7688
Episode: 4042 Total reward: 20.0 Training loss: 0.5029 Explore P: 0.7688
Episode: 4043 Total reward: 13.0 Training loss: 0.0744 Explore P: 0.7687
Episode: 4044 Total reward: 18.0 Training loss: 5.4500 Explore P: 0.7687
Episode: 4045 Total reward: 29.0 Training loss: 22.2107 Explore P: 0.7687
Episode: 4046 Total reward: 11.0 Training loss: 12.8591 Explore P: 0.7687
Episode: 4047 Total reward: 15.0 Training loss: 0.2655 Explore P: 0.7686
Episode: 4048 Total reward: 27.0 Training loss: 0.0835 Explore P: 0.7686
Episode: 4049 Total reward: 9.0 Training loss: 0.0880 Explore P: 0.7686
Episode: 4050 Total reward: 22.0 Training loss: 2.0047 Explore P: 0.7685
Episode: 4051 Total reward: 8.0 Training loss: 5.6085 Explore P: 0.7685
Episode: 4052 Total reward: 12.0 Training loss: 13.5315 Explore P: 0.7685
Episode: 4053 Total reward: 16.0 Training loss: 5.0791 Explore P: 0.7685
Episode: 4054 Total reward: 23.0 Training loss: 0.0504 Explore P: 0.7685
Episode: 4055 Total reward: 34.0 Training loss: 12.9498 Explore P: 0.7684
Episode: 4056 Total reward: 51.0 Training loss: 0.2441 Explore P: 0.7683
Episode: 4057 Total reward: 13.0 Training loss: 6.6546 Explore P: 0.7683
Episode: 4058 Total reward: 22.0 Training loss: 5.4834 Explore P: 0.7683
Episode: 4059 Total reward: 17.0 Training loss: 15.2489 Explore P: 0.7683
Episode: 4060 Total reward: 32.0 Training loss: 0.1521 Explore P: 0.7682
Episode: 4061 Total reward: 14.0 Training loss: 1.2779 Explore P: 0.7682
Episode: 4062 Total reward: 25.0 Training loss: 1.0343 Explore P: 0.7681
Episode: 4063 Total reward: 12.0 Training loss: 0.0786 Explore P: 0.7681
Episode: 4064 Total reward: 10.0 Training loss: 4.5002 Explore P: 0.7681
Episode: 4065 Total reward: 27.0 Training loss: 4.3472 Explore P: 0.7681
Episode: 4066 Total reward: 54.0 Training loss: 11.8405 Explore P: 0.7680
Episode: 4067 Total reward: 9.0 Training loss: 1.9091 Explore P: 0.7680
Episode: 4068 Total reward: 14.0 Training loss: 0.0332 Explore P: 0.7680
Episode: 4069 Total reward: 17.0 Training loss: 0.0697 Explore P: 0.7679
Episode: 4070 Total reward: 20.0 Training loss: 56.0176 Explore P: 0.7679
Episode: 4071 Total reward: 14.0 Training loss: 9.4978 Explore P: 0.7679
Episode: 4072 Total reward: 15.0 Training loss: 0.0885 Explore P: 0.7679
Episode: 4073 Total reward: 45.0 Training loss: 7.7515 Explore P: 0.7678
Episode: 4074 Total reward: 18.0 Training loss: 0.2612 Explore P: 0.7678
Episode: 4075 Total reward: 12.0 Training loss: 0.4078 Explore P: 0.7677
Episode: 4076 Total reward: 58.0 Training loss: 8.1041 Explore P: 0.7676
Episode: 4077 Total reward: 63.0 Training loss: 6.0686 Explore P: 0.7676
Episode: 4078 Total reward: 14.0 Training loss: 0.4029 Explore P: 0.7675
Episode: 4079 Total reward: 23.0 Training loss: 3.0079 Explore P: 0.7675
Episode: 4080 Total reward: 29.0 Training loss: 1.1694 Explore P: 0.7675
Episode: 4081 Total reward: 37.0 Training loss: 16.1491 Explore P: 0.7674
Episode: 4082 Total reward: 13.0 Training loss: 2.9049 Explore P: 0.7674
Episode: 4083 Total reward: 11.0 Training loss: 24.2968 Explore P: 0.7674
Episode: 4084 Total reward: 17.0 Training loss: 0.0490 Explore P: 0.7673
Episode: 4085 Total reward: 10.0 Training loss: 9.9008 Explore P: 0.7673
Episode: 4086 Total reward: 17.0 Training loss: 0.1060 Explore P: 0.7673
Episode: 4087 Total reward: 18.0 Training loss: 15.6624 Explore P: 0.7673
Episode: 4088 Total reward: 36.0 Training loss: 11.6119 Explore P: 0.7672
Episode: 4089 Total reward: 17.0 Training loss: 0.1157 Explore P: 0.7672
Episode: 4090 Total reward: 20.0 Training loss: 15.9862 Explore P: 0.7672
Episode: 4091 Total reward: 34.0 Training loss: 4.9873 Explore P: 0.7671
Episode: 4092 Total reward: 30.0 Training loss: 39.3872 Explore P: 0.7671
Episode: 4093 Total reward: 14.0 Training loss: 0.4725 Explore P: 0.7670
Episode: 4094 Total reward: 23.0 Training loss: 9.6148 Explore P: 0.7670
Episode: 4095 Total reward: 30.0 Training loss: 21.1894 Explore P: 0.7670
Episode: 4096 Total reward: 15.0 Training loss: 0.0743 Explore P: 0.7669
Episode: 4097 Total reward: 23.0 Training loss: 2.2638 Explore P: 0.7669
Episode: 4098 Total reward: 12.0 Training loss: 40.0991 Explore P: 0.7669
Episode: 4099 Total reward: 22.0 Training loss: 4.8255 Explore P: 0.7669
Episode: 4100 Total reward: 17.0 Training loss: 0.1463 Explore P: 0.7668
Episode: 4101 Total reward: 15.0 Training loss: 0.0703 Explore P: 0.7668
Episode: 4102 Total reward: 15.0 Training loss: 2.1693 Explore P: 0.7668
Episode: 4103 Total reward: 27.0 Training loss: 1.5932 Explore P: 0.7667
Episode: 4104 Total reward: 13.0 Training loss: 8.9457 Explore P: 0.7667
Episode: 4105 Total reward: 7.0 Training loss: 7.7799 Explore P: 0.7667
Episode: 4106 Total reward: 73.0 Training loss: 17.8023 Explore P: 0.7666
Episode: 4107 Total reward: 19.0 Training loss: 0.4363 Explore P: 0.7666
Episode: 4108 Total reward: 24.0 Training loss: 0.0786 Explore P: 0.7665
Episode: 4109 Total reward: 10.0 Training loss: 7.0389 Explore P: 0.7665
Episode: 4110 Total reward: 12.0 Training loss: 1.7549 Explore P: 0.7665
Episode: 4111 Total reward: 14.0 Training loss: 0.1233 Explore P: 0.7665
Episode: 4112 Total reward: 19.0 Training loss: 0.3566 Explore P: 0.7664
Episode: 4113 Total reward: 10.0 Training loss: 0.2142 Explore P: 0.7664
Episode: 4114 Total reward: 54.0 Training loss: 0.8475 Explore P: 0.7664
Episode: 4115 Total reward: 12.0 Training loss: 0.4465 Explore P: 0.7663
Episode: 4116 Total reward: 22.0 Training loss: 0.6445 Explore P: 0.7663
Episode: 4117 Total reward: 13.0 Training loss: 14.1654 Explore P: 0.7663
Episode: 4118 Total reward: 29.0 Training loss: 0.0946 Explore P: 0.7662
Episode: 4119 Total reward: 9.0 Training loss: 2.8370 Explore P: 0.7662
Episode: 4120 Total reward: 10.0 Training loss: 24.5958 Explore P: 0.7662
Episode: 4121 Total reward: 16.0 Training loss: 1.3736 Explore P: 0.7662
Episode: 4122 Total reward: 44.0 Training loss: 11.0728 Explore P: 0.7661
Episode: 4123 Total reward: 13.0 Training loss: 0.1336 Explore P: 0.7661
Episode: 4124 Total reward: 14.0 Training loss: 4.8955 Explore P: 0.7661
Episode: 4125 Total reward: 9.0 Training loss: 0.1048 Explore P: 0.7661
Episode: 4126 Total reward: 34.0 Training loss: 0.0964 Explore P: 0.7660
Episode: 4127 Total reward: 34.0 Training loss: 0.5548 Explore P: 0.7660
Episode: 4128 Total reward: 12.0 Training loss: 11.6442 Explore P: 0.7659
Episode: 4129 Total reward: 17.0 Training loss: 0.1397 Explore P: 0.7659
Episode: 4130 Total reward: 15.0 Training loss: 7.8417 Explore P: 0.7659
Episode: 4131 Total reward: 9.0 Training loss: 1.5705 Explore P: 0.7659
Episode: 4132 Total reward: 10.0 Training loss: 2.3235 Explore P: 0.7659
Episode: 4133 Total reward: 27.0 Training loss: 3.6485 Explore P: 0.7658
Episode: 4134 Total reward: 10.0 Training loss: 33.5453 Explore P: 0.7658
Episode: 4135 Total reward: 14.0 Training loss: 2.1206 Explore P: 0.7658
Episode: 4136 Total reward: 30.0 Training loss: 1.3627 Explore P: 0.7657
Episode: 4137 Total reward: 8.0 Training loss: 0.2417 Explore P: 0.7657
Episode: 4138 Total reward: 26.0 Training loss: 0.0968 Explore P: 0.7657
Episode: 4139 Total reward: 21.0 Training loss: 0.1957 Explore P: 0.7657
Episode: 4140 Total reward: 23.0 Training loss: 0.0469 Explore P: 0.7656
Episode: 4141 Total reward: 34.0 Training loss: 4.8748 Explore P: 0.7656
Episode: 4142 Total reward: 11.0 Training loss: 0.0780 Explore P: 0.7656
Episode: 4143 Total reward: 21.0 Training loss: 2.7599 Explore P: 0.7655
Episode: 4144 Total reward: 9.0 Training loss: 7.9547 Explore P: 0.7655
Episode: 4145 Total reward: 20.0 Training loss: 5.6903 Explore P: 0.7655
Episode: 4146 Total reward: 12.0 Training loss: 0.0783 Explore P: 0.7655
Episode: 4147 Total reward: 20.0 Training loss: 34.1310 Explore P: 0.7654
Episode: 4148 Total reward: 11.0 Training loss: 0.0799 Explore P: 0.7654
Episode: 4149 Total reward: 21.0 Training loss: 0.1002 Explore P: 0.7654
Episode: 4150 Total reward: 9.0 Training loss: 2.0067 Explore P: 0.7654
Episode: 4151 Total reward: 18.0 Training loss: 0.1512 Explore P: 0.7653
Episode: 4152 Total reward: 10.0 Training loss: 4.2482 Explore P: 0.7653
Episode: 4153 Total reward: 19.0 Training loss: 3.1368 Explore P: 0.7653
Episode: 4154 Total reward: 12.0 Training loss: 1.9784 Explore P: 0.7653
Episode: 4155 Total reward: 9.0 Training loss: 8.1517 Explore P: 0.7653
Episode: 4156 Total reward: 36.0 Training loss: 0.0591 Explore P: 0.7652
Episode: 4157 Total reward: 13.0 Training loss: 0.0880 Explore P: 0.7652
Episode: 4158 Total reward: 10.0 Training loss: 0.3571 Explore P: 0.7652
Episode: 4159 Total reward: 15.0 Training loss: 0.3195 Explore P: 0.7652
Episode: 4160 Total reward: 13.0 Training loss: 0.2982 Explore P: 0.7651
Episode: 4161 Total reward: 14.0 Training loss: 0.0976 Explore P: 0.7651
Episode: 4162 Total reward: 13.0 Training loss: 0.0806 Explore P: 0.7651
Episode: 4163 Total reward: 11.0 Training loss: 12.9912 Explore P: 0.7651
Episode: 4164 Total reward: 28.0 Training loss: 18.8131 Explore P: 0.7650
Episode: 4165 Total reward: 16.0 Training loss: 12.8595 Explore P: 0.7650
Episode: 4166 Total reward: 8.0 Training loss: 3.7791 Explore P: 0.7650
Episode: 4167 Total reward: 12.0 Training loss: 2.1271 Explore P: 0.7650
Episode: 4168 Total reward: 18.0 Training loss: 0.0504 Explore P: 0.7650
Episode: 4169 Total reward: 33.0 Training loss: 0.0624 Explore P: 0.7649
Episode: 4170 Total reward: 25.0 Training loss: 13.9615 Explore P: 0.7649
Episode: 4171 Total reward: 28.0 Training loss: 6.7656 Explore P: 0.7648
Episode: 4172 Total reward: 20.0 Training loss: 24.2278 Explore P: 0.7648
Episode: 4173 Total reward: 42.0 Training loss: 0.1748 Explore P: 0.7647
Episode: 4174 Total reward: 11.0 Training loss: 1.2669 Explore P: 0.7647
Episode: 4175 Total reward: 28.0 Training loss: 20.3314 Explore P: 0.7647
Episode: 4176 Total reward: 14.0 Training loss: 3.5203 Explore P: 0.7647
Episode: 4177 Total reward: 18.0 Training loss: 0.5653 Explore P: 0.7646
Episode: 4178 Total reward: 48.0 Training loss: 21.5189 Explore P: 0.7646
Episode: 4179 Total reward: 22.0 Training loss: 2.2019 Explore P: 0.7645
Episode: 4180 Total reward: 22.0 Training loss: 3.9438 Explore P: 0.7645
Episode: 4181 Total reward: 14.0 Training loss: 2.3599 Explore P: 0.7645
Episode: 4182 Total reward: 18.0 Training loss: 0.0639 Explore P: 0.7644
Episode: 4183 Total reward: 23.0 Training loss: 0.8381 Explore P: 0.7644
Episode: 4184 Total reward: 24.0 Training loss: 21.3138 Explore P: 0.7644
Episode: 4185 Total reward: 20.0 Training loss: 17.7758 Explore P: 0.7643
Episode: 4186 Total reward: 28.0 Training loss: 13.7711 Explore P: 0.7643
Episode: 4187 Total reward: 11.0 Training loss: 5.5946 Explore P: 0.7643
Episode: 4188 Total reward: 10.0 Training loss: 0.4090 Explore P: 0.7643
Episode: 4189 Total reward: 30.0 Training loss: 6.2380 Explore P: 0.7642
Episode: 4190 Total reward: 22.0 Training loss: 16.8132 Explore P: 0.7642
Episode: 4191 Total reward: 14.0 Training loss: 0.0189 Explore P: 0.7642
Episode: 4192 Total reward: 22.0 Training loss: 1.6852 Explore P: 0.7641
Episode: 4193 Total reward: 21.0 Training loss: 0.5769 Explore P: 0.7641
Episode: 4194 Total reward: 16.0 Training loss: 1.8644 Explore P: 0.7641
Episode: 4195 Total reward: 12.0 Training loss: 0.0404 Explore P: 0.7641
Episode: 4196 Total reward: 25.0 Training loss: 1.0039 Explore P: 0.7640
Episode: 4197 Total reward: 85.0 Training loss: 0.1164 Explore P: 0.7639
Episode: 4198 Total reward: 10.0 Training loss: 15.1523 Explore P: 0.7639
Episode: 4199 Total reward: 21.0 Training loss: 0.2352 Explore P: 0.7638
Episode: 4200 Total reward: 13.0 Training loss: 13.2505 Explore P: 0.7638
Episode: 4201 Total reward: 36.0 Training loss: 55.3660 Explore P: 0.7638
Episode: 4202 Total reward: 10.0 Training loss: 0.1086 Explore P: 0.7638
Episode: 4203 Total reward: 29.0 Training loss: 2.6919 Explore P: 0.7637
Episode: 4204 Total reward: 17.0 Training loss: 0.1003 Explore P: 0.7637
Episode: 4205 Total reward: 26.0 Training loss: 1.0245 Explore P: 0.7636
Episode: 4206 Total reward: 10.0 Training loss: 3.7528 Explore P: 0.7636
Episode: 4207 Total reward: 11.0 Training loss: 22.2954 Explore P: 0.7636
Episode: 4208 Total reward: 21.0 Training loss: 1.7062 Explore P: 0.7636
Episode: 4209 Total reward: 15.0 Training loss: 15.5242 Explore P: 0.7636
Episode: 4210 Total reward: 27.0 Training loss: 1.5110 Explore P: 0.7635
Episode: 4211 Total reward: 10.0 Training loss: 17.7955 Explore P: 0.7635
Episode: 4212 Total reward: 14.0 Training loss: 31.3795 Explore P: 0.7635
Episode: 4213 Total reward: 16.0 Training loss: 43.0399 Explore P: 0.7635
Episode: 4214 Total reward: 8.0 Training loss: 0.2225 Explore P: 0.7634
Episode: 4215 Total reward: 59.0 Training loss: 24.6525 Explore P: 0.7634
Episode: 4216 Total reward: 13.0 Training loss: 0.1168 Explore P: 0.7633
Episode: 4217 Total reward: 16.0 Training loss: 1.6361 Explore P: 0.7633
Episode: 4218 Total reward: 15.0 Training loss: 8.0703 Explore P: 0.7633
Episode: 4219 Total reward: 20.0 Training loss: 1.6091 Explore P: 0.7633
Episode: 4220 Total reward: 16.0 Training loss: 10.4378 Explore P: 0.7632
Episode: 4221 Total reward: 23.0 Training loss: 0.7501 Explore P: 0.7632
Episode: 4222 Total reward: 14.0 Training loss: 0.6087 Explore P: 0.7632
Episode: 4223 Total reward: 66.0 Training loss: 0.6321 Explore P: 0.7631
Episode: 4224 Total reward: 26.0 Training loss: 2.2542 Explore P: 0.7630
Episode: 4225 Total reward: 15.0 Training loss: 13.1601 Explore P: 0.7630
Episode: 4226 Total reward: 13.0 Training loss: 0.5873 Explore P: 0.7630
Episode: 4227 Total reward: 17.0 Training loss: 0.8281 Explore P: 0.7630
Episode: 4228 Total reward: 22.0 Training loss: 11.6899 Explore P: 0.7629
Episode: 4229 Total reward: 42.0 Training loss: 0.2686 Explore P: 0.7629
Episode: 4230 Total reward: 63.0 Training loss: 0.8133 Explore P: 0.7628
Episode: 4231 Total reward: 20.0 Training loss: 0.1103 Explore P: 0.7628
Episode: 4232 Total reward: 16.0 Training loss: 8.8405 Explore P: 0.7627
Episode: 4233 Total reward: 21.0 Training loss: 0.1239 Explore P: 0.7627
Episode: 4234 Total reward: 24.0 Training loss: 0.1137 Explore P: 0.7627
Episode: 4235 Total reward: 8.0 Training loss: 1.9739 Explore P: 0.7627
Episode: 4236 Total reward: 10.0 Training loss: 10.6832 Explore P: 0.7626
Episode: 4237 Total reward: 10.0 Training loss: 0.1711 Explore P: 0.7626
Episode: 4238 Total reward: 19.0 Training loss: 0.7742 Explore P: 0.7626
Episode: 4239 Total reward: 21.0 Training loss: 2.9821 Explore P: 0.7626
Episode: 4240 Total reward: 16.0 Training loss: 31.4390 Explore P: 0.7625
Episode: 4241 Total reward: 10.0 Training loss: 1.4841 Explore P: 0.7625
Episode: 4242 Total reward: 13.0 Training loss: 0.1179 Explore P: 0.7625
Episode: 4243 Total reward: 45.0 Training loss: 74.6536 Explore P: 0.7624
Episode: 4244 Total reward: 12.0 Training loss: 0.0717 Explore P: 0.7624
Episode: 4245 Total reward: 21.0 Training loss: 0.0412 Explore P: 0.7624
Episode: 4246 Total reward: 34.0 Training loss: 1.7339 Explore P: 0.7623
Episode: 4247 Total reward: 13.0 Training loss: 9.2865 Explore P: 0.7623
Episode: 4248 Total reward: 14.0 Training loss: 14.7484 Explore P: 0.7623
Episode: 4249 Total reward: 22.0 Training loss: 4.3558 Explore P: 0.7623
Episode: 4250 Total reward: 12.0 Training loss: 5.0596 Explore P: 0.7622
Episode: 4251 Total reward: 17.0 Training loss: 1.8296 Explore P: 0.7622
Episode: 4252 Total reward: 13.0 Training loss: 7.5507 Explore P: 0.7622
Episode: 4253 Total reward: 34.0 Training loss: 10.3526 Explore P: 0.7621
Episode: 4254 Total reward: 22.0 Training loss: 10.2157 Explore P: 0.7621
Episode: 4255 Total reward: 12.0 Training loss: 0.2926 Explore P: 0.7621
Episode: 4256 Total reward: 12.0 Training loss: 4.3618 Explore P: 0.7621
Episode: 4257 Total reward: 12.0 Training loss: 0.1514 Explore P: 0.7621
Episode: 4258 Total reward: 17.0 Training loss: 0.1146 Explore P: 0.7620
Episode: 4259 Total reward: 8.0 Training loss: 7.0439 Explore P: 0.7620
Episode: 4260 Total reward: 28.0 Training loss: 36.1919 Explore P: 0.7620
Episode: 4261 Total reward: 19.0 Training loss: 0.4787 Explore P: 0.7619
Episode: 4262 Total reward: 11.0 Training loss: 10.1325 Explore P: 0.7619
Episode: 4263 Total reward: 42.0 Training loss: 0.8484 Explore P: 0.7619
Episode: 4264 Total reward: 12.0 Training loss: 10.1235 Explore P: 0.7619
Episode: 4265 Total reward: 15.0 Training loss: 13.7887 Explore P: 0.7618
Episode: 4266 Total reward: 16.0 Training loss: 6.8770 Explore P: 0.7618
Episode: 4267 Total reward: 15.0 Training loss: 3.3241 Explore P: 0.7618
Episode: 4268 Total reward: 24.0 Training loss: 1.6403 Explore P: 0.7617
Episode: 4269 Total reward: 26.0 Training loss: 3.8648 Explore P: 0.7617
Episode: 4270 Total reward: 14.0 Training loss: 0.8300 Explore P: 0.7617
Episode: 4271 Total reward: 14.0 Training loss: 1.0767 Explore P: 0.7617
Episode: 4272 Total reward: 12.0 Training loss: 0.0980 Explore P: 0.7616
Episode: 4273 Total reward: 15.0 Training loss: 0.0838 Explore P: 0.7616
Episode: 4274 Total reward: 19.0 Training loss: 1.7494 Explore P: 0.7616
Episode: 4275 Total reward: 28.0 Training loss: 16.2716 Explore P: 0.7616
Episode: 4276 Total reward: 65.0 Training loss: 0.1160 Explore P: 0.7615
Episode: 4277 Total reward: 15.0 Training loss: 0.1164 Explore P: 0.7614
Episode: 4278 Total reward: 8.0 Training loss: 1.5275 Explore P: 0.7614
Episode: 4279 Total reward: 12.0 Training loss: 0.5537 Explore P: 0.7614
Episode: 4280 Total reward: 8.0 Training loss: 0.8107 Explore P: 0.7614
Episode: 4281 Total reward: 14.0 Training loss: 11.3082 Explore P: 0.7614
Episode: 4282 Total reward: 11.0 Training loss: 1.8370 Explore P: 0.7614
Episode: 4283 Total reward: 36.0 Training loss: 0.1150 Explore P: 0.7613
Episode: 4284 Total reward: 18.0 Training loss: 7.6477 Explore P: 0.7613
Episode: 4285 Total reward: 45.0 Training loss: 8.9706 Explore P: 0.7612
Episode: 4286 Total reward: 8.0 Training loss: 3.7485 Explore P: 0.7612
Episode: 4287 Total reward: 45.0 Training loss: 0.1217 Explore P: 0.7611
Episode: 4288 Total reward: 7.0 Training loss: 0.9430 Explore P: 0.7611
Episode: 4289 Total reward: 27.0 Training loss: 0.0556 Explore P: 0.7611
Episode: 4290 Total reward: 7.0 Training loss: 1.2866 Explore P: 0.7611
Episode: 4291 Total reward: 15.0 Training loss: 3.6984 Explore P: 0.7610
Episode: 4292 Total reward: 16.0 Training loss: 0.0987 Explore P: 0.7610
Episode: 4293 Total reward: 12.0 Training loss: 2.4276 Explore P: 0.7610
Episode: 4294 Total reward: 11.0 Training loss: 5.7547 Explore P: 0.7610
Episode: 4295 Total reward: 10.0 Training loss: 8.8185 Explore P: 0.7610
Episode: 4296 Total reward: 14.0 Training loss: 4.7400 Explore P: 0.7609
Episode: 4297 Total reward: 8.0 Training loss: 0.0818 Explore P: 0.7609
Episode: 4298 Total reward: 19.0 Training loss: 6.0650 Explore P: 0.7609
Episode: 4299 Total reward: 16.0 Training loss: 7.9937 Explore P: 0.7609
Episode: 4300 Total reward: 24.0 Training loss: 1.4591 Explore P: 0.7608
Episode: 4301 Total reward: 43.0 Training loss: 0.6325 Explore P: 0.7608
Episode: 4302 Total reward: 14.0 Training loss: 21.0942 Explore P: 0.7608
Episode: 4303 Total reward: 22.0 Training loss: 12.3504 Explore P: 0.7607
Episode: 4304 Total reward: 25.0 Training loss: 21.4585 Explore P: 0.7607
Episode: 4305 Total reward: 43.0 Training loss: 0.4935 Explore P: 0.7606
Episode: 4306 Total reward: 19.0 Training loss: 7.7173 Explore P: 0.7606
Episode: 4307 Total reward: 10.0 Training loss: 8.1899 Explore P: 0.7606
Episode: 4308 Total reward: 15.0 Training loss: 0.1861 Explore P: 0.7606
Episode: 4309 Total reward: 10.0 Training loss: 106.5747 Explore P: 0.7605
Episode: 4310 Total reward: 15.0 Training loss: 0.8455 Explore P: 0.7605
Episode: 4311 Total reward: 8.0 Training loss: 79.6812 Explore P: 0.7605
Episode: 4312 Total reward: 12.0 Training loss: 0.0451 Explore P: 0.7605
Episode: 4313 Total reward: 9.0 Training loss: 4.4918 Explore P: 0.7605
Episode: 4314 Total reward: 10.0 Training loss: 0.5444 Explore P: 0.7605
Episode: 4315 Total reward: 10.0 Training loss: 0.0753 Explore P: 0.7604
Episode: 4316 Total reward: 29.0 Training loss: 0.2835 Explore P: 0.7604
Episode: 4317 Total reward: 13.0 Training loss: 25.3477 Explore P: 0.7604
Episode: 4318 Total reward: 11.0 Training loss: 14.0152 Explore P: 0.7604
Episode: 4319 Total reward: 14.0 Training loss: 4.5360 Explore P: 0.7603
Episode: 4320 Total reward: 19.0 Training loss: 0.8291 Explore P: 0.7603
Episode: 4321 Total reward: 19.0 Training loss: 81.8839 Explore P: 0.7603
Episode: 4322 Total reward: 19.0 Training loss: 9.3682 Explore P: 0.7603
Episode: 4323 Total reward: 24.0 Training loss: 1.7426 Explore P: 0.7602
Episode: 4324 Total reward: 24.0 Training loss: 1.0761 Explore P: 0.7602
Episode: 4325 Total reward: 12.0 Training loss: 0.1238 Explore P: 0.7602
Episode: 4326 Total reward: 31.0 Training loss: 10.8878 Explore P: 0.7601
Episode: 4327 Total reward: 24.0 Training loss: 10.2941 Explore P: 0.7601
Episode: 4328 Total reward: 17.0 Training loss: 3.6096 Explore P: 0.7601
Episode: 4329 Total reward: 25.0 Training loss: 14.6709 Explore P: 0.7600
Episode: 4330 Total reward: 21.0 Training loss: 6.9596 Explore P: 0.7600
Episode: 4331 Total reward: 8.0 Training loss: 0.0466 Explore P: 0.7600
Episode: 4332 Total reward: 15.0 Training loss: 4.1003 Explore P: 0.7600
Episode: 4333 Total reward: 9.0 Training loss: 20.1571 Explore P: 0.7599
Episode: 4334 Total reward: 28.0 Training loss: 13.5560 Explore P: 0.7599
Episode: 4335 Total reward: 23.0 Training loss: 3.6553 Explore P: 0.7599
Episode: 4336 Total reward: 18.0 Training loss: 0.3878 Explore P: 0.7598
Episode: 4337 Total reward: 11.0 Training loss: 58.2131 Explore P: 0.7598
Episode: 4338 Total reward: 20.0 Training loss: 5.7692 Explore P: 0.7598
Episode: 4339 Total reward: 10.0 Training loss: 4.3979 Explore P: 0.7598
Episode: 4340 Total reward: 19.0 Training loss: 0.3411 Explore P: 0.7598
Episode: 4341 Total reward: 21.0 Training loss: 12.7309 Explore P: 0.7597
Episode: 4342 Total reward: 10.0 Training loss: 0.2830 Explore P: 0.7597
Episode: 4343 Total reward: 15.0 Training loss: 0.5036 Explore P: 0.7597
Episode: 4344 Total reward: 9.0 Training loss: 9.4579 Explore P: 0.7597
Episode: 4345 Total reward: 37.0 Training loss: 17.6925 Explore P: 0.7596
Episode: 4346 Total reward: 28.0 Training loss: 0.0380 Explore P: 0.7596
Episode: 4347 Total reward: 14.0 Training loss: 22.6658 Explore P: 0.7596
Episode: 4348 Total reward: 13.0 Training loss: 1.1417 Explore P: 0.7595
Episode: 4349 Total reward: 15.0 Training loss: 1.3526 Explore P: 0.7595
Episode: 4350 Total reward: 9.0 Training loss: 4.0044 Explore P: 0.7595
Episode: 4351 Total reward: 24.0 Training loss: 0.1335 Explore P: 0.7595
Episode: 4352 Total reward: 19.0 Training loss: 9.8646 Explore P: 0.7594
Episode: 4353 Total reward: 29.0 Training loss: 1.7924 Explore P: 0.7594
Episode: 4354 Total reward: 17.0 Training loss: 0.0346 Explore P: 0.7594
Episode: 4355 Total reward: 16.0 Training loss: 5.6939 Explore P: 0.7593
Episode: 4356 Total reward: 21.0 Training loss: 3.0487 Explore P: 0.7593
Episode: 4357 Total reward: 9.0 Training loss: 7.4240 Explore P: 0.7593
Episode: 4358 Total reward: 7.0 Training loss: 4.0512 Explore P: 0.7593
Episode: 4359 Total reward: 52.0 Training loss: 1.1919 Explore P: 0.7592
Episode: 4360 Total reward: 18.0 Training loss: 3.3485 Explore P: 0.7592
Episode: 4361 Total reward: 12.0 Training loss: 0.8379 Explore P: 0.7592
Episode: 4362 Total reward: 9.0 Training loss: 0.0973 Explore P: 0.7591
Episode: 4363 Total reward: 16.0 Training loss: 30.5684 Explore P: 0.7591
Episode: 4364 Total reward: 18.0 Training loss: 0.1983 Explore P: 0.7591
Episode: 4365 Total reward: 18.0 Training loss: 4.1644 Explore P: 0.7591
Episode: 4366 Total reward: 9.0 Training loss: 4.7520 Explore P: 0.7591
Episode: 4367 Total reward: 11.0 Training loss: 0.0840 Explore P: 0.7590
Episode: 4368 Total reward: 13.0 Training loss: 25.5217 Explore P: 0.7590
Episode: 4369 Total reward: 13.0 Training loss: 0.4936 Explore P: 0.7590
Episode: 4370 Total reward: 22.0 Training loss: 1.4458 Explore P: 0.7590
Episode: 4371 Total reward: 12.0 Training loss: 0.1435 Explore P: 0.7590
Episode: 4372 Total reward: 18.0 Training loss: 4.0202 Explore P: 0.7589
Episode: 4373 Total reward: 11.0 Training loss: 0.1486 Explore P: 0.7589
Episode: 4374 Total reward: 16.0 Training loss: 2.8155 Explore P: 0.7589
Episode: 4375 Total reward: 19.0 Training loss: 17.3461 Explore P: 0.7589
Episode: 4376 Total reward: 22.0 Training loss: 1.5844 Explore P: 0.7588
Episode: 4377 Total reward: 8.0 Training loss: 0.2492 Explore P: 0.7588
Episode: 4378 Total reward: 12.0 Training loss: 3.8408 Explore P: 0.7588
Episode: 4379 Total reward: 27.0 Training loss: 2.6684 Explore P: 0.7588
Episode: 4380 Total reward: 10.0 Training loss: 2.1963 Explore P: 0.7587
Episode: 4381 Total reward: 17.0 Training loss: 0.1556 Explore P: 0.7587
Episode: 4382 Total reward: 28.0 Training loss: 18.0041 Explore P: 0.7587
Episode: 4383 Total reward: 14.0 Training loss: 2.5784 Explore P: 0.7586
Episode: 4384 Total reward: 19.0 Training loss: 1.6499 Explore P: 0.7586
Episode: 4385 Total reward: 24.0 Training loss: 23.0427 Explore P: 0.7586
Episode: 4386 Total reward: 36.0 Training loss: 1.6573 Explore P: 0.7585
Episode: 4387 Total reward: 8.0 Training loss: 5.9515 Explore P: 0.7585
Episode: 4388 Total reward: 23.0 Training loss: 0.0350 Explore P: 0.7585
Episode: 4389 Total reward: 19.0 Training loss: 0.2727 Explore P: 0.7585
Episode: 4390 Total reward: 21.0 Training loss: 0.1886 Explore P: 0.7584
Episode: 4391 Total reward: 23.0 Training loss: 18.3112 Explore P: 0.7584
Episode: 4392 Total reward: 10.0 Training loss: 0.0929 Explore P: 0.7584
Episode: 4393 Total reward: 15.0 Training loss: 0.8575 Explore P: 0.7584
Episode: 4394 Total reward: 38.0 Training loss: 0.7235 Explore P: 0.7583
Episode: 4395 Total reward: 26.0 Training loss: 1.7860 Explore P: 0.7583
Episode: 4396 Total reward: 19.0 Training loss: 4.2390 Explore P: 0.7582
Episode: 4397 Total reward: 13.0 Training loss: 3.5360 Explore P: 0.7582
Episode: 4398 Total reward: 36.0 Training loss: 52.5953 Explore P: 0.7582
Episode: 4399 Total reward: 13.0 Training loss: 0.0800 Explore P: 0.7581
Episode: 4400 Total reward: 14.0 Training loss: 0.5749 Explore P: 0.7581
Episode: 4401 Total reward: 8.0 Training loss: 1.4445 Explore P: 0.7581
Episode: 4402 Total reward: 14.0 Training loss: 5.2595 Explore P: 0.7581
Episode: 4403 Total reward: 24.0 Training loss: 7.5935 Explore P: 0.7580
Episode: 4404 Total reward: 9.0 Training loss: 0.7144 Explore P: 0.7580
Episode: 4405 Total reward: 34.0 Training loss: 0.6353 Explore P: 0.7580
Episode: 4406 Total reward: 17.0 Training loss: 0.7130 Explore P: 0.7580
Episode: 4407 Total reward: 17.0 Training loss: 1.6246 Explore P: 0.7579
Episode: 4408 Total reward: 35.0 Training loss: 0.6404 Explore P: 0.7579
Episode: 4409 Total reward: 16.0 Training loss: 2.2683 Explore P: 0.7579
Episode: 4410 Total reward: 46.0 Training loss: 2.5524 Explore P: 0.7578
Episode: 4411 Total reward: 36.0 Training loss: 0.2013 Explore P: 0.7577
Episode: 4412 Total reward: 19.0 Training loss: 18.7948 Explore P: 0.7577
Episode: 4413 Total reward: 14.0 Training loss: 4.9687 Explore P: 0.7577
Episode: 4414 Total reward: 39.0 Training loss: 12.1544 Explore P: 0.7576
Episode: 4415 Total reward: 23.0 Training loss: 0.0659 Explore P: 0.7576
Episode: 4416 Total reward: 11.0 Training loss: 11.4316 Explore P: 0.7576
Episode: 4417 Total reward: 15.0 Training loss: 7.4671 Explore P: 0.7576
Episode: 4418 Total reward: 23.0 Training loss: 11.0028 Explore P: 0.7575
Episode: 4419 Total reward: 19.0 Training loss: 14.9340 Explore P: 0.7575
Episode: 4420 Total reward: 9.0 Training loss: 0.0783 Explore P: 0.7575
Episode: 4421 Total reward: 13.0 Training loss: 0.2729 Explore P: 0.7575
Episode: 4422 Total reward: 23.0 Training loss: 0.6293 Explore P: 0.7574
Episode: 4423 Total reward: 20.0 Training loss: 0.1041 Explore P: 0.7574
Episode: 4424 Total reward: 12.0 Training loss: 2.3583 Explore P: 0.7574
Episode: 4425 Total reward: 18.0 Training loss: 9.3523 Explore P: 0.7573
Episode: 4426 Total reward: 62.0 Training loss: 0.5739 Explore P: 0.7573
Episode: 4427 Total reward: 32.0 Training loss: 3.1670 Explore P: 0.7572
Episode: 4428 Total reward: 71.0 Training loss: 17.3121 Explore P: 0.7571
Episode: 4429 Total reward: 29.0 Training loss: 3.4816 Explore P: 0.7571
Episode: 4430 Total reward: 11.0 Training loss: 2.4252 Explore P: 0.7570
Episode: 4431 Total reward: 20.0 Training loss: 3.3233 Explore P: 0.7570
Episode: 4432 Total reward: 16.0 Training loss: 5.2923 Explore P: 0.7570
Episode: 4433 Total reward: 47.0 Training loss: 1.7739 Explore P: 0.7569
Episode: 4434 Total reward: 23.0 Training loss: 0.0210 Explore P: 0.7569
Episode: 4435 Total reward: 22.0 Training loss: 6.6252 Explore P: 0.7568
Episode: 4436 Total reward: 9.0 Training loss: 0.3823 Explore P: 0.7568
Episode: 4437 Total reward: 9.0 Training loss: 0.0493 Explore P: 0.7568
Episode: 4438 Total reward: 34.0 Training loss: 0.0825 Explore P: 0.7568
Episode: 4439 Total reward: 11.0 Training loss: 23.1279 Explore P: 0.7568
Episode: 4440 Total reward: 14.0 Training loss: 4.6561 Explore P: 0.7567
Episode: 4441 Total reward: 12.0 Training loss: 0.0968 Explore P: 0.7567
Episode: 4442 Total reward: 48.0 Training loss: 1.6003 Explore P: 0.7566
Episode: 4443 Total reward: 20.0 Training loss: 3.3505 Explore P: 0.7566
Episode: 4444 Total reward: 10.0 Training loss: 21.9799 Explore P: 0.7566
Episode: 4445 Total reward: 36.0 Training loss: 2.9258 Explore P: 0.7565
Episode: 4446 Total reward: 21.0 Training loss: 13.1274 Explore P: 0.7565
Episode: 4447 Total reward: 22.0 Training loss: 2.1985 Explore P: 0.7565
Episode: 4448 Total reward: 15.0 Training loss: 15.5398 Explore P: 0.7565
Episode: 4449 Total reward: 11.0 Training loss: 0.0422 Explore P: 0.7564
Episode: 4450 Total reward: 35.0 Training loss: 0.0669 Explore P: 0.7564
Episode: 4451 Total reward: 16.0 Training loss: 2.6308 Explore P: 0.7564
Episode: 4452 Total reward: 11.0 Training loss: 0.0661 Explore P: 0.7563
Episode: 4453 Total reward: 11.0 Training loss: 4.8587 Explore P: 0.7563
Episode: 4454 Total reward: 15.0 Training loss: 4.0237 Explore P: 0.7563
Episode: 4455 Total reward: 21.0 Training loss: 5.8659 Explore P: 0.7563
Episode: 4456 Total reward: 19.0 Training loss: 2.2141 Explore P: 0.7563
Episode: 4457 Total reward: 27.0 Training loss: 0.1832 Explore P: 0.7562
Episode: 4458 Total reward: 13.0 Training loss: 5.9127 Explore P: 0.7562
Episode: 4459 Total reward: 21.0 Training loss: 4.0646 Explore P: 0.7562
Episode: 4460 Total reward: 46.0 Training loss: 2.3285 Explore P: 0.7561
Episode: 4461 Total reward: 11.0 Training loss: 4.2652 Explore P: 0.7561
Episode: 4462 Total reward: 9.0 Training loss: 0.0347 Explore P: 0.7561
Episode: 4463 Total reward: 40.0 Training loss: 0.1339 Explore P: 0.7560
Episode: 4464 Total reward: 16.0 Training loss: 3.9501 Explore P: 0.7560
Episode: 4465 Total reward: 11.0 Training loss: 1.5948 Explore P: 0.7560
Episode: 4466 Total reward: 34.0 Training loss: 6.0814 Explore P: 0.7559
Episode: 4467 Total reward: 15.0 Training loss: 0.4469 Explore P: 0.7559
Episode: 4468 Total reward: 33.0 Training loss: 0.1517 Explore P: 0.7558
Episode: 4469 Total reward: 12.0 Training loss: 0.0914 Explore P: 0.7558
Episode: 4470 Total reward: 17.0 Training loss: 8.6493 Explore P: 0.7558
Episode: 4471 Total reward: 15.0 Training loss: 0.1837 Explore P: 0.7558
Episode: 4472 Total reward: 23.0 Training loss: 6.2526 Explore P: 0.7557
Episode: 4473 Total reward: 28.0 Training loss: 0.0814 Explore P: 0.7557
Episode: 4474 Total reward: 23.0 Training loss: 0.6049 Explore P: 0.7557
Episode: 4475 Total reward: 10.0 Training loss: 1.6385 Explore P: 0.7556
Episode: 4476 Total reward: 11.0 Training loss: 4.9549 Explore P: 0.7556
Episode: 4477 Total reward: 17.0 Training loss: 0.1198 Explore P: 0.7556
Episode: 4478 Total reward: 24.0 Training loss: 0.2749 Explore P: 0.7556
Episode: 4479 Total reward: 12.0 Training loss: 0.0639 Explore P: 0.7556
Episode: 4480 Total reward: 14.0 Training loss: 4.3682 Explore P: 0.7555
Episode: 4481 Total reward: 12.0 Training loss: 6.2640 Explore P: 0.7555
Episode: 4482 Total reward: 15.0 Training loss: 0.1226 Explore P: 0.7555
Episode: 4483 Total reward: 11.0 Training loss: 0.1586 Explore P: 0.7555
Episode: 4484 Total reward: 17.0 Training loss: 0.1570 Explore P: 0.7554
Episode: 4485 Total reward: 30.0 Training loss: 2.7010 Explore P: 0.7554
Episode: 4486 Total reward: 26.0 Training loss: 3.4646 Explore P: 0.7554
Episode: 4487 Total reward: 30.0 Training loss: 0.7852 Explore P: 0.7553
Episode: 4488 Total reward: 15.0 Training loss: 0.2320 Explore P: 0.7553
Episode: 4489 Total reward: 24.0 Training loss: 1.8093 Explore P: 0.7553
Episode: 4490 Total reward: 15.0 Training loss: 0.0787 Explore P: 0.7552
Episode: 4491 Total reward: 10.0 Training loss: 4.3077 Explore P: 0.7552
Episode: 4492 Total reward: 22.0 Training loss: 0.1330 Explore P: 0.7552
Episode: 4493 Total reward: 21.0 Training loss: 1.1456 Explore P: 0.7552
Episode: 4494 Total reward: 17.0 Training loss: 5.2814 Explore P: 0.7551
Episode: 4495 Total reward: 23.0 Training loss: 1.6024 Explore P: 0.7551
Episode: 4496 Total reward: 13.0 Training loss: 4.8174 Explore P: 0.7551
Episode: 4497 Total reward: 27.0 Training loss: 4.7036 Explore P: 0.7550
Episode: 4498 Total reward: 10.0 Training loss: 5.8489 Explore P: 0.7550
Episode: 4499 Total reward: 12.0 Training loss: 0.1013 Explore P: 0.7550
Episode: 4500 Total reward: 30.0 Training loss: 0.5751 Explore P: 0.7550
Episode: 4501 Total reward: 16.0 Training loss: 0.0455 Explore P: 0.7549
Episode: 4502 Total reward: 11.0 Training loss: 2.8140 Explore P: 0.7549
Episode: 4503 Total reward: 24.0 Training loss: 1.4026 Explore P: 0.7549
Episode: 4504 Total reward: 38.0 Training loss: 7.6063 Explore P: 0.7548
Episode: 4505 Total reward: 14.0 Training loss: 0.1322 Explore P: 0.7548
Episode: 4506 Total reward: 17.0 Training loss: 3.6232 Explore P: 0.7548
Episode: 4507 Total reward: 10.0 Training loss: 0.1131 Explore P: 0.7548
Episode: 4508 Total reward: 19.0 Training loss: 0.4324 Explore P: 0.7547
Episode: 4509 Total reward: 18.0 Training loss: 0.0782 Explore P: 0.7547
Episode: 4510 Total reward: 32.0 Training loss: 31.3657 Explore P: 0.7547
Episode: 4511 Total reward: 44.0 Training loss: 0.1435 Explore P: 0.7546
Episode: 4512 Total reward: 14.0 Training loss: 3.2999 Explore P: 0.7546
Episode: 4513 Total reward: 16.0 Training loss: 0.0611 Explore P: 0.7546
Episode: 4514 Total reward: 18.0 Training loss: 13.8039 Explore P: 0.7545
Episode: 4515 Total reward: 18.0 Training loss: 1.1070 Explore P: 0.7545
Episode: 4516 Total reward: 34.0 Training loss: 1.9793 Explore P: 0.7545
Episode: 4517 Total reward: 10.0 Training loss: 0.5533 Explore P: 0.7544
Episode: 4518 Total reward: 42.0 Training loss: 0.0621 Explore P: 0.7544
Episode: 4519 Total reward: 10.0 Training loss: 1.9295 Explore P: 0.7544
Episode: 4520 Total reward: 10.0 Training loss: 2.6872 Explore P: 0.7543
Episode: 4521 Total reward: 27.0 Training loss: 0.1657 Explore P: 0.7543
Episode: 4522 Total reward: 12.0 Training loss: 0.0746 Explore P: 0.7543
Episode: 4523 Total reward: 17.0 Training loss: 0.7394 Explore P: 0.7543
Episode: 4524 Total reward: 31.0 Training loss: 27.5354 Explore P: 0.7542
Episode: 4525 Total reward: 18.0 Training loss: 50.8614 Explore P: 0.7542
Episode: 4526 Total reward: 22.0 Training loss: 3.3428 Explore P: 0.7542
Episode: 4527 Total reward: 14.0 Training loss: 5.8152 Explore P: 0.7541
Episode: 4528 Total reward: 31.0 Training loss: 12.3888 Explore P: 0.7541
Episode: 4529 Total reward: 12.0 Training loss: 0.7111 Explore P: 0.7541
Episode: 4530 Total reward: 24.0 Training loss: 0.0329 Explore P: 0.7540
Episode: 4531 Total reward: 33.0 Training loss: 1.5952 Explore P: 0.7540
Episode: 4532 Total reward: 10.0 Training loss: 14.9372 Explore P: 0.7540
Episode: 4533 Total reward: 15.0 Training loss: 1.2958 Explore P: 0.7540
Episode: 4534 Total reward: 13.0 Training loss: 20.2102 Explore P: 0.7539
Episode: 4535 Total reward: 24.0 Training loss: 3.8506 Explore P: 0.7539
Episode: 4536 Total reward: 40.0 Training loss: 5.1731 Explore P: 0.7538
Episode: 4537 Total reward: 20.0 Training loss: 0.0840 Explore P: 0.7538
Episode: 4538 Total reward: 9.0 Training loss: 12.5342 Explore P: 0.7538
Episode: 4539 Total reward: 17.0 Training loss: 0.1445 Explore P: 0.7538
Episode: 4540 Total reward: 9.0 Training loss: 7.7024 Explore P: 0.7538
Episode: 4541 Total reward: 16.0 Training loss: 0.1218 Explore P: 0.7537
Episode: 4542 Total reward: 9.0 Training loss: 16.4247 Explore P: 0.7537
Episode: 4543 Total reward: 16.0 Training loss: 1.4578 Explore P: 0.7537
Episode: 4544 Total reward: 27.0 Training loss: 5.4738 Explore P: 0.7537
Episode: 4545 Total reward: 11.0 Training loss: 0.0548 Explore P: 0.7536
Episode: 4546 Total reward: 22.0 Training loss: 3.6623 Explore P: 0.7536
Episode: 4547 Total reward: 18.0 Training loss: 3.6828 Explore P: 0.7536
Episode: 4548 Total reward: 19.0 Training loss: 0.2082 Explore P: 0.7535
Episode: 4549 Total reward: 30.0 Training loss: 0.2295 Explore P: 0.7535
Episode: 4550 Total reward: 10.0 Training loss: 0.1477 Explore P: 0.7535
Episode: 4551 Total reward: 28.0 Training loss: 3.7264 Explore P: 0.7534
Episode: 4552 Total reward: 19.0 Training loss: 0.1154 Explore P: 0.7534
Episode: 4553 Total reward: 14.0 Training loss: 0.3798 Explore P: 0.7534
Episode: 4554 Total reward: 15.0 Training loss: 54.8234 Explore P: 0.7534
Episode: 4555 Total reward: 24.0 Training loss: 0.4367 Explore P: 0.7533
Episode: 4556 Total reward: 9.0 Training loss: 0.0448 Explore P: 0.7533
Episode: 4557 Total reward: 10.0 Training loss: 0.7073 Explore P: 0.7533
Episode: 4558 Total reward: 10.0 Training loss: 2.7820 Explore P: 0.7533
Episode: 4559 Total reward: 8.0 Training loss: 3.9460 Explore P: 0.7533
Episode: 4560 Total reward: 24.0 Training loss: 4.9143 Explore P: 0.7533
Episode: 4561 Total reward: 24.0 Training loss: 4.1784 Explore P: 0.7532
Episode: 4562 Total reward: 30.0 Training loss: 11.0597 Explore P: 0.7532
Episode: 4563 Total reward: 34.0 Training loss: 2.5341 Explore P: 0.7531
Episode: 4564 Total reward: 22.0 Training loss: 0.1708 Explore P: 0.7531
Episode: 4565 Total reward: 17.0 Training loss: 16.0121 Explore P: 0.7531
Episode: 4566 Total reward: 20.0 Training loss: 0.1051 Explore P: 0.7530
Episode: 4567 Total reward: 12.0 Training loss: 3.1886 Explore P: 0.7530
Episode: 4568 Total reward: 18.0 Training loss: 0.0318 Explore P: 0.7530
Episode: 4569 Total reward: 19.0 Training loss: 17.8306 Explore P: 0.7530
Episode: 4570 Total reward: 8.0 Training loss: 12.7192 Explore P: 0.7529
Episode: 4571 Total reward: 14.0 Training loss: 6.5673 Explore P: 0.7529
Episode: 4572 Total reward: 16.0 Training loss: 1.2275 Explore P: 0.7529
Episode: 4573 Total reward: 12.0 Training loss: 1.7555 Explore P: 0.7529
Episode: 4574 Total reward: 16.0 Training loss: 1.1450 Explore P: 0.7529
Episode: 4575 Total reward: 19.0 Training loss: 0.0335 Explore P: 0.7528
Episode: 4576 Total reward: 27.0 Training loss: 24.9828 Explore P: 0.7528
Episode: 4577 Total reward: 12.0 Training loss: 5.4289 Explore P: 0.7528
Episode: 4578 Total reward: 11.0 Training loss: 0.1100 Explore P: 0.7528
Episode: 4579 Total reward: 36.0 Training loss: 0.1883 Explore P: 0.7527
Episode: 4580 Total reward: 41.0 Training loss: 2.3816 Explore P: 0.7526
Episode: 4581 Total reward: 30.0 Training loss: 4.2380 Explore P: 0.7526
Episode: 4582 Total reward: 25.0 Training loss: 4.1253 Explore P: 0.7526
Episode: 4583 Total reward: 13.0 Training loss: 0.1243 Explore P: 0.7525
Episode: 4584 Total reward: 12.0 Training loss: 4.8103 Explore P: 0.7525
Episode: 4585 Total reward: 27.0 Training loss: 0.1455 Explore P: 0.7525
Episode: 4586 Total reward: 10.0 Training loss: 0.4431 Explore P: 0.7525
Episode: 4587 Total reward: 24.0 Training loss: 1.0964 Explore P: 0.7524
Episode: 4588 Total reward: 12.0 Training loss: 0.0759 Explore P: 0.7524
Episode: 4589 Total reward: 19.0 Training loss: 0.1197 Explore P: 0.7524
Episode: 4590 Total reward: 11.0 Training loss: 1.9233 Explore P: 0.7524
Episode: 4591 Total reward: 25.0 Training loss: 1.9542 Explore P: 0.7523
Episode: 4592 Total reward: 29.0 Training loss: 5.2219 Explore P: 0.7523
Episode: 4593 Total reward: 15.0 Training loss: 3.2073 Explore P: 0.7523
Episode: 4594 Total reward: 8.0 Training loss: 4.5997 Explore P: 0.7523
Episode: 4595 Total reward: 17.0 Training loss: 0.0516 Explore P: 0.7522
Episode: 4596 Total reward: 17.0 Training loss: 0.1401 Explore P: 0.7522
Episode: 4597 Total reward: 26.0 Training loss: 2.2108 Explore P: 0.7522
Episode: 4598 Total reward: 78.0 Training loss: 180.2822 Explore P: 0.7521
Episode: 4599 Total reward: 18.0 Training loss: 0.4891 Explore P: 0.7520
Episode: 4600 Total reward: 11.0 Training loss: 0.7651 Explore P: 0.7520
Episode: 4601 Total reward: 38.0 Training loss: 0.7477 Explore P: 0.7520
Episode: 4602 Total reward: 10.0 Training loss: 0.4094 Explore P: 0.7519
Episode: 4603 Total reward: 9.0 Training loss: 8.0213 Explore P: 0.7519
Episode: 4604 Total reward: 21.0 Training loss: 0.1530 Explore P: 0.7519
Episode: 4605 Total reward: 15.0 Training loss: 4.8540 Explore P: 0.7519
Episode: 4606 Total reward: 16.0 Training loss: 0.0875 Explore P: 0.7518
Episode: 4607 Total reward: 18.0 Training loss: 0.0606 Explore P: 0.7518
Episode: 4608 Total reward: 19.0 Training loss: 21.7887 Explore P: 0.7518
Episode: 4609 Total reward: 9.0 Training loss: 0.0672 Explore P: 0.7518
Episode: 4610 Total reward: 29.0 Training loss: 12.0243 Explore P: 0.7517
Episode: 4611 Total reward: 32.0 Training loss: 0.9802 Explore P: 0.7517
Episode: 4612 Total reward: 10.0 Training loss: 8.3053 Explore P: 0.7517
Episode: 4613 Total reward: 18.0 Training loss: 31.1343 Explore P: 0.7516
Episode: 4614 Total reward: 30.0 Training loss: 8.0754 Explore P: 0.7516
Episode: 4615 Total reward: 15.0 Training loss: 0.4972 Explore P: 0.7516
Episode: 4616 Total reward: 23.0 Training loss: 2.6068 Explore P: 0.7515
Episode: 4617 Total reward: 13.0 Training loss: 18.4033 Explore P: 0.7515
Episode: 4618 Total reward: 14.0 Training loss: 0.0646 Explore P: 0.7515
Episode: 4619 Total reward: 25.0 Training loss: 17.7711 Explore P: 0.7515
Episode: 4620 Total reward: 10.0 Training loss: 0.0503 Explore P: 0.7515
Episode: 4621 Total reward: 12.0 Training loss: 13.3378 Explore P: 0.7514
Episode: 4622 Total reward: 41.0 Training loss: 12.6181 Explore P: 0.7514
Episode: 4623 Total reward: 12.0 Training loss: 15.8836 Explore P: 0.7514
Episode: 4624 Total reward: 50.0 Training loss: 3.0929 Explore P: 0.7513
Episode: 4625 Total reward: 13.0 Training loss: 0.0371 Explore P: 0.7513
Episode: 4626 Total reward: 11.0 Training loss: 0.1006 Explore P: 0.7512
Episode: 4627 Total reward: 10.0 Training loss: 8.6098 Explore P: 0.7512
Episode: 4628 Total reward: 21.0 Training loss: 2.4217 Explore P: 0.7512
Episode: 4629 Total reward: 21.0 Training loss: 4.5870 Explore P: 0.7512
Episode: 4630 Total reward: 11.0 Training loss: 1.4373 Explore P: 0.7512
Episode: 4631 Total reward: 12.0 Training loss: 0.0079 Explore P: 0.7511
Episode: 4632 Total reward: 16.0 Training loss: 1.1229 Explore P: 0.7511
Episode: 4633 Total reward: 20.0 Training loss: 1.9949 Explore P: 0.7511
Episode: 4634 Total reward: 25.0 Training loss: 0.1568 Explore P: 0.7510
Episode: 4635 Total reward: 30.0 Training loss: 9.9706 Explore P: 0.7510
Episode: 4636 Total reward: 13.0 Training loss: 11.0195 Explore P: 0.7510
Episode: 4637 Total reward: 83.0 Training loss: 4.5085 Explore P: 0.7509
Episode: 4638 Total reward: 29.0 Training loss: 0.0979 Explore P: 0.7508
Episode: 4639 Total reward: 79.0 Training loss: 16.9681 Explore P: 0.7507
Episode: 4640 Total reward: 8.0 Training loss: 2.1586 Explore P: 0.7507
Episode: 4641 Total reward: 9.0 Training loss: 0.1473 Explore P: 0.7507
Episode: 4642 Total reward: 11.0 Training loss: 26.6013 Explore P: 0.7507
Episode: 4643 Total reward: 17.0 Training loss: 3.2491 Explore P: 0.7506
Episode: 4644 Total reward: 32.0 Training loss: 0.1996 Explore P: 0.7506
Episode: 4645 Total reward: 16.0 Training loss: 6.1447 Explore P: 0.7506
Episode: 4646 Total reward: 16.0 Training loss: 12.7812 Explore P: 0.7505
Episode: 4647 Total reward: 9.0 Training loss: 0.1169 Explore P: 0.7505
Episode: 4648 Total reward: 11.0 Training loss: 5.9426 Explore P: 0.7505
Episode: 4649 Total reward: 12.0 Training loss: 15.0163 Explore P: 0.7505
Episode: 4650 Total reward: 12.0 Training loss: 0.0873 Explore P: 0.7505
Episode: 4651 Total reward: 38.0 Training loss: 0.1593 Explore P: 0.7504
Episode: 4652 Total reward: 17.0 Training loss: 13.8518 Explore P: 0.7504
Episode: 4653 Total reward: 33.0 Training loss: 0.1054 Explore P: 0.7503
Episode: 4654 Total reward: 23.0 Training loss: 0.5833 Explore P: 0.7503
Episode: 4655 Total reward: 10.0 Training loss: 2.9130 Explore P: 0.7503
Episode: 4656 Total reward: 32.0 Training loss: 7.0451 Explore P: 0.7502
Episode: 4657 Total reward: 9.0 Training loss: 1.9371 Explore P: 0.7502
Episode: 4658 Total reward: 17.0 Training loss: 23.6861 Explore P: 0.7502
Episode: 4659 Total reward: 32.0 Training loss: 8.5206 Explore P: 0.7502
Episode: 4660 Total reward: 11.0 Training loss: 275.0941 Explore P: 0.7501
Episode: 4661 Total reward: 17.0 Training loss: 0.0644 Explore P: 0.7501
Episode: 4662 Total reward: 37.0 Training loss: 9.8201 Explore P: 0.7501
Episode: 4663 Total reward: 12.0 Training loss: 20.1903 Explore P: 0.7500
Episode: 4664 Total reward: 22.0 Training loss: 0.0801 Explore P: 0.7500
Episode: 4665 Total reward: 14.0 Training loss: 3.5073 Explore P: 0.7500
Episode: 4666 Total reward: 14.0 Training loss: 2.7364 Explore P: 0.7500
Episode: 4667 Total reward: 27.0 Training loss: 9.1948 Explore P: 0.7499
Episode: 4668 Total reward: 15.0 Training loss: 19.7895 Explore P: 0.7499
Episode: 4669 Total reward: 48.0 Training loss: 6.1002 Explore P: 0.7498
Episode: 4670 Total reward: 32.0 Training loss: 6.8006 Explore P: 0.7498
Episode: 4671 Total reward: 10.0 Training loss: 0.3833 Explore P: 0.7498
Episode: 4672 Total reward: 10.0 Training loss: 0.0381 Explore P: 0.7498
Episode: 4673 Total reward: 61.0 Training loss: 2.0724 Explore P: 0.7497
Episode: 4674 Total reward: 21.0 Training loss: 0.2114 Explore P: 0.7496
Episode: 4675 Total reward: 16.0 Training loss: 7.9492 Explore P: 0.7496
Episode: 4676 Total reward: 19.0 Training loss: 1.6658 Explore P: 0.7496
Episode: 4677 Total reward: 14.0 Training loss: 15.4307 Explore P: 0.7496
Episode: 4678 Total reward: 44.0 Training loss: 0.4608 Explore P: 0.7495
Episode: 4679 Total reward: 36.0 Training loss: 2.4293 Explore P: 0.7495
Episode: 4680 Total reward: 15.0 Training loss: 0.0852 Explore P: 0.7494
Episode: 4681 Total reward: 28.0 Training loss: 2.4362 Explore P: 0.7494
Episode: 4682 Total reward: 11.0 Training loss: 2.8286 Explore P: 0.7494
Episode: 4683 Total reward: 10.0 Training loss: 0.3250 Explore P: 0.7494
Episode: 4684 Total reward: 15.0 Training loss: 0.0626 Explore P: 0.7493
Episode: 4685 Total reward: 26.0 Training loss: 140.2514 Explore P: 0.7493
Episode: 4686 Total reward: 12.0 Training loss: 0.0968 Explore P: 0.7493
Episode: 4687 Total reward: 34.0 Training loss: 17.8520 Explore P: 0.7492
Episode: 4688 Total reward: 13.0 Training loss: 2.5780 Explore P: 0.7492
Episode: 4689 Total reward: 14.0 Training loss: 0.0811 Explore P: 0.7492
Episode: 4690 Total reward: 20.0 Training loss: 0.0694 Explore P: 0.7492
Episode: 4691 Total reward: 12.0 Training loss: 14.4032 Explore P: 0.7491
Episode: 4692 Total reward: 15.0 Training loss: 0.0812 Explore P: 0.7491
Episode: 4693 Total reward: 11.0 Training loss: 0.2164 Explore P: 0.7491
Episode: 4694 Total reward: 13.0 Training loss: 6.1256 Explore P: 0.7491
Episode: 4695 Total reward: 45.0 Training loss: 6.9721 Explore P: 0.7490
Episode: 4696 Total reward: 18.0 Training loss: 1.0365 Explore P: 0.7490
Episode: 4697 Total reward: 24.0 Training loss: 3.1268 Explore P: 0.7490
Episode: 4698 Total reward: 15.0 Training loss: 5.3342 Explore P: 0.7489
Episode: 4699 Total reward: 12.0 Training loss: 2.3702 Explore P: 0.7489
Episode: 4700 Total reward: 11.0 Training loss: 1.3585 Explore P: 0.7489
Episode: 4701 Total reward: 46.0 Training loss: 0.6034 Explore P: 0.7488
Episode: 4702 Total reward: 32.0 Training loss: 5.7429 Explore P: 0.7488
Episode: 4703 Total reward: 17.0 Training loss: 1.6513 Explore P: 0.7488
Episode: 4704 Total reward: 10.0 Training loss: 67.0215 Explore P: 0.7487
Episode: 4705 Total reward: 30.0 Training loss: 2.7176 Explore P: 0.7487
Episode: 4706 Total reward: 34.0 Training loss: 8.3913 Explore P: 0.7486
Episode: 4707 Total reward: 30.0 Training loss: 5.1788 Explore P: 0.7486
Episode: 4708 Total reward: 16.0 Training loss: 0.1796 Explore P: 0.7486
Episode: 4709 Total reward: 30.0 Training loss: 1.4436 Explore P: 0.7485
Episode: 4710 Total reward: 20.0 Training loss: 0.2377 Explore P: 0.7485
Episode: 4711 Total reward: 22.0 Training loss: 3.0318 Explore P: 0.7485
Episode: 4712 Total reward: 23.0 Training loss: 21.1528 Explore P: 0.7484
Episode: 4713 Total reward: 20.0 Training loss: 7.6997 Explore P: 0.7484
Episode: 4714 Total reward: 25.0 Training loss: 7.7830 Explore P: 0.7484
Episode: 4715 Total reward: 22.0 Training loss: 56.4397 Explore P: 0.7483
Episode: 4716 Total reward: 14.0 Training loss: 4.5092 Explore P: 0.7483
Episode: 4717 Total reward: 29.0 Training loss: 3.2571 Explore P: 0.7483
Episode: 4718 Total reward: 23.0 Training loss: 0.0556 Explore P: 0.7482
Episode: 4719 Total reward: 13.0 Training loss: 0.0557 Explore P: 0.7482
Episode: 4720 Total reward: 23.0 Training loss: 0.5145 Explore P: 0.7482
Episode: 4721 Total reward: 27.0 Training loss: 0.0270 Explore P: 0.7482
Episode: 4722 Total reward: 18.0 Training loss: 0.4705 Explore P: 0.7481
Episode: 4723 Total reward: 21.0 Training loss: 10.6598 Explore P: 0.7481
Episode: 4724 Total reward: 13.0 Training loss: 1.1649 Explore P: 0.7481
Episode: 4725 Total reward: 11.0 Training loss: 0.1090 Explore P: 0.7481
Episode: 4726 Total reward: 23.0 Training loss: 1.9822 Explore P: 0.7480
Episode: 4727 Total reward: 13.0 Training loss: 1.4780 Explore P: 0.7480
Episode: 4728 Total reward: 16.0 Training loss: 12.2259 Explore P: 0.7480
Episode: 4729 Total reward: 9.0 Training loss: 0.1552 Explore P: 0.7480
Episode: 4730 Total reward: 17.0 Training loss: 6.4045 Explore P: 0.7479
Episode: 4731 Total reward: 17.0 Training loss: 3.3829 Explore P: 0.7479
Episode: 4732 Total reward: 12.0 Training loss: 0.0918 Explore P: 0.7479
Episode: 4733 Total reward: 40.0 Training loss: 0.1973 Explore P: 0.7478
Episode: 4734 Total reward: 18.0 Training loss: 0.1140 Explore P: 0.7478
Episode: 4735 Total reward: 29.0 Training loss: 1.0162 Explore P: 0.7478
Episode: 4736 Total reward: 23.0 Training loss: 5.6737 Explore P: 0.7477
Episode: 4737 Total reward: 11.0 Training loss: 0.6409 Explore P: 0.7477
Episode: 4738 Total reward: 14.0 Training loss: 1.9184 Explore P: 0.7477
Episode: 4739 Total reward: 60.0 Training loss: 0.3014 Explore P: 0.7476
Episode: 4740 Total reward: 16.0 Training loss: 0.1315 Explore P: 0.7476
Episode: 4741 Total reward: 21.0 Training loss: 10.1252 Explore P: 0.7476
Episode: 4742 Total reward: 11.0 Training loss: 0.9506 Explore P: 0.7475
Episode: 4743 Total reward: 30.0 Training loss: 25.9579 Explore P: 0.7475
Episode: 4744 Total reward: 10.0 Training loss: 1.3275 Explore P: 0.7475
Episode: 4745 Total reward: 12.0 Training loss: 0.6617 Explore P: 0.7475
Episode: 4746 Total reward: 56.0 Training loss: 19.6430 Explore P: 0.7474
Episode: 4747 Total reward: 11.0 Training loss: 4.1833 Explore P: 0.7474
Episode: 4748 Total reward: 23.0 Training loss: 10.3581 Explore P: 0.7473
Episode: 4749 Total reward: 28.0 Training loss: 0.1149 Explore P: 0.7473
Episode: 4750 Total reward: 14.0 Training loss: 8.1531 Explore P: 0.7473
Episode: 4751 Total reward: 19.0 Training loss: 1.9868 Explore P: 0.7472
Episode: 4752 Total reward: 11.0 Training loss: 11.2992 Explore P: 0.7472
Episode: 4753 Total reward: 30.0 Training loss: 3.5812 Explore P: 0.7472
Episode: 4754 Total reward: 17.0 Training loss: 2.6543 Explore P: 0.7472
Episode: 4755 Total reward: 9.0 Training loss: 0.5515 Explore P: 0.7471
Episode: 4756 Total reward: 15.0 Training loss: 1.7729 Explore P: 0.7471
Episode: 4757 Total reward: 18.0 Training loss: 0.4790 Explore P: 0.7471
Episode: 4758 Total reward: 15.0 Training loss: 3.1875 Explore P: 0.7471
Episode: 4759 Total reward: 24.0 Training loss: 0.0452 Explore P: 0.7470
Episode: 4760 Total reward: 21.0 Training loss: 21.4275 Explore P: 0.7470
Episode: 4761 Total reward: 10.0 Training loss: 4.5984 Explore P: 0.7470
Episode: 4762 Total reward: 25.0 Training loss: 1.2414 Explore P: 0.7470
Episode: 4763 Total reward: 11.0 Training loss: 12.1437 Explore P: 0.7469
Episode: 4764 Total reward: 8.0 Training loss: 1.1232 Explore P: 0.7469
Episode: 4765 Total reward: 14.0 Training loss: 0.0353 Explore P: 0.7469
Episode: 4766 Total reward: 13.0 Training loss: 0.7078 Explore P: 0.7469
Episode: 4767 Total reward: 17.0 Training loss: 0.8310 Explore P: 0.7469
Episode: 4768 Total reward: 17.0 Training loss: 0.0715 Explore P: 0.7468
Episode: 4769 Total reward: 16.0 Training loss: 0.2313 Explore P: 0.7468
Episode: 4770 Total reward: 16.0 Training loss: 7.1813 Explore P: 0.7468
Episode: 4771 Total reward: 35.0 Training loss: 3.3353 Explore P: 0.7467
Episode: 4772 Total reward: 28.0 Training loss: 9.7627 Explore P: 0.7467
Episode: 4773 Total reward: 11.0 Training loss: 0.1441 Explore P: 0.7467
Episode: 4774 Total reward: 32.0 Training loss: 0.1407 Explore P: 0.7466
Episode: 4775 Total reward: 10.0 Training loss: 0.2425 Explore P: 0.7466
Episode: 4776 Total reward: 20.0 Training loss: 27.0719 Explore P: 0.7466
Episode: 4777 Total reward: 18.0 Training loss: 0.0411 Explore P: 0.7466
Episode: 4778 Total reward: 24.0 Training loss: 0.0995 Explore P: 0.7465
Episode: 4779 Total reward: 13.0 Training loss: 0.1134 Explore P: 0.7465
Episode: 4780 Total reward: 67.0 Training loss: 0.3233 Explore P: 0.7464
Episode: 4781 Total reward: 9.0 Training loss: 0.2965 Explore P: 0.7464
Episode: 4782 Total reward: 29.0 Training loss: 0.0404 Explore P: 0.7464
Episode: 4783 Total reward: 13.0 Training loss: 2.3517 Explore P: 0.7463
Episode: 4784 Total reward: 28.0 Training loss: 40.7855 Explore P: 0.7463
Episode: 4785 Total reward: 18.0 Training loss: 2.6396 Explore P: 0.7463
Episode: 4786 Total reward: 21.0 Training loss: 19.3302 Explore P: 0.7462
Episode: 4787 Total reward: 15.0 Training loss: 4.4612 Explore P: 0.7462
Episode: 4788 Total reward: 20.0 Training loss: 1.9848 Explore P: 0.7462
Episode: 4789 Total reward: 20.0 Training loss: 2.3255 Explore P: 0.7462
Episode: 4790 Total reward: 14.0 Training loss: 2.1936 Explore P: 0.7461
Episode: 4791 Total reward: 27.0 Training loss: 5.3312 Explore P: 0.7461
Episode: 4792 Total reward: 33.0 Training loss: 0.1371 Explore P: 0.7460
Episode: 4793 Total reward: 16.0 Training loss: 0.2306 Explore P: 0.7460
Episode: 4794 Total reward: 12.0 Training loss: 0.0916 Explore P: 0.7460
Episode: 4795 Total reward: 31.0 Training loss: 1.1504 Explore P: 0.7460
Episode: 4796 Total reward: 14.0 Training loss: 8.9403 Explore P: 0.7459
Episode: 4797 Total reward: 15.0 Training loss: 0.0202 Explore P: 0.7459
Episode: 4798 Total reward: 13.0 Training loss: 24.5863 Explore P: 0.7459
Episode: 4799 Total reward: 16.0 Training loss: 0.0184 Explore P: 0.7459
Episode: 4800 Total reward: 12.0 Training loss: 3.7273 Explore P: 0.7459
Episode: 4801 Total reward: 19.0 Training loss: 0.1149 Explore P: 0.7458
Episode: 4802 Total reward: 22.0 Training loss: 0.6523 Explore P: 0.7458
Episode: 4803 Total reward: 10.0 Training loss: 0.0075 Explore P: 0.7458
Episode: 4804 Total reward: 55.0 Training loss: 26.9311 Explore P: 0.7457
Episode: 4805 Total reward: 9.0 Training loss: 0.0776 Explore P: 0.7457
Episode: 4806 Total reward: 24.0 Training loss: 8.5721 Explore P: 0.7457
Episode: 4807 Total reward: 33.0 Training loss: 0.3418 Explore P: 0.7456
Episode: 4808 Total reward: 12.0 Training loss: 27.7823 Explore P: 0.7456
Episode: 4809 Total reward: 13.0 Training loss: 0.1089 Explore P: 0.7456
Episode: 4810 Total reward: 27.0 Training loss: 0.7655 Explore P: 0.7455
Episode: 4811 Total reward: 25.0 Training loss: 0.0571 Explore P: 0.7455
Episode: 4812 Total reward: 22.0 Training loss: 2.1805 Explore P: 0.7455
Episode: 4813 Total reward: 56.0 Training loss: 11.3546 Explore P: 0.7454
Episode: 4814 Total reward: 22.0 Training loss: 0.1013 Explore P: 0.7453
Episode: 4815 Total reward: 15.0 Training loss: 0.2623 Explore P: 0.7453
Episode: 4816 Total reward: 17.0 Training loss: 31.2442 Explore P: 0.7453
Episode: 4817 Total reward: 36.0 Training loss: 0.1288 Explore P: 0.7452
Episode: 4818 Total reward: 9.0 Training loss: 3.2207 Explore P: 0.7452
Episode: 4819 Total reward: 24.0 Training loss: 0.0618 Explore P: 0.7452
Episode: 4820 Total reward: 23.0 Training loss: 1.2525 Explore P: 0.7452
Episode: 4821 Total reward: 12.0 Training loss: 4.6984 Explore P: 0.7451
Episode: 4822 Total reward: 45.0 Training loss: 3.9191 Explore P: 0.7451
Episode: 4823 Total reward: 26.0 Training loss: 27.2344 Explore P: 0.7450
Episode: 4824 Total reward: 8.0 Training loss: 1.4735 Explore P: 0.7450
Episode: 4825 Total reward: 26.0 Training loss: 1.2663 Explore P: 0.7450
Episode: 4826 Total reward: 19.0 Training loss: 6.6828 Explore P: 0.7450
Episode: 4827 Total reward: 45.0 Training loss: 0.0383 Explore P: 0.7449
Episode: 4828 Total reward: 11.0 Training loss: 2.6880 Explore P: 0.7449
Episode: 4829 Total reward: 13.0 Training loss: 4.7137 Explore P: 0.7449
Episode: 4830 Total reward: 38.0 Training loss: 1.5100 Explore P: 0.7448
Episode: 4831 Total reward: 11.0 Training loss: 1.4826 Explore P: 0.7448
Episode: 4832 Total reward: 10.0 Training loss: 1.3416 Explore P: 0.7448
Episode: 4833 Total reward: 12.0 Training loss: 0.0704 Explore P: 0.7448
Episode: 4834 Total reward: 8.0 Training loss: 10.8674 Explore P: 0.7447
Episode: 4835 Total reward: 14.0 Training loss: 192.6168 Explore P: 0.7447
Episode: 4836 Total reward: 34.0 Training loss: 8.1366 Explore P: 0.7447
Episode: 4837 Total reward: 11.0 Training loss: 12.7271 Explore P: 0.7447
Episode: 4838 Total reward: 60.0 Training loss: 27.6274 Explore P: 0.7446
Episode: 4839 Total reward: 11.0 Training loss: 2.4641 Explore P: 0.7446
Episode: 4840 Total reward: 36.0 Training loss: 17.8250 Explore P: 0.7445
Episode: 4841 Total reward: 35.0 Training loss: 3.7824 Explore P: 0.7444
Episode: 4842 Total reward: 17.0 Training loss: 0.0375 Explore P: 0.7444
Episode: 4843 Total reward: 11.0 Training loss: 0.2528 Explore P: 0.7444
Episode: 4844 Total reward: 12.0 Training loss: 1.0317 Explore P: 0.7444
Episode: 4845 Total reward: 8.0 Training loss: 1.9005 Explore P: 0.7444
Episode: 4846 Total reward: 10.0 Training loss: 0.1207 Explore P: 0.7444
Episode: 4847 Total reward: 27.0 Training loss: 0.0620 Explore P: 0.7443
Episode: 4848 Total reward: 14.0 Training loss: 0.1111 Explore P: 0.7443
Episode: 4849 Total reward: 47.0 Training loss: 0.0444 Explore P: 0.7442
Episode: 4850 Total reward: 12.0 Training loss: 1.2222 Explore P: 0.7442
Episode: 4851 Total reward: 24.0 Training loss: 0.1306 Explore P: 0.7442
Episode: 4852 Total reward: 28.0 Training loss: 2.6255 Explore P: 0.7441
Episode: 4853 Total reward: 9.0 Training loss: 5.8431 Explore P: 0.7441
Episode: 4854 Total reward: 12.0 Training loss: 1.7055 Explore P: 0.7441
Episode: 4855 Total reward: 14.0 Training loss: 5.4694 Explore P: 0.7441
Episode: 4856 Total reward: 22.0 Training loss: 1.5753 Explore P: 0.7441
Episode: 4857 Total reward: 19.0 Training loss: 2.8602 Explore P: 0.7440
Episode: 4858 Total reward: 13.0 Training loss: 0.0401 Explore P: 0.7440
Episode: 4859 Total reward: 24.0 Training loss: 6.6066 Explore P: 0.7440
Episode: 4860 Total reward: 20.0 Training loss: 3.7196 Explore P: 0.7439
Episode: 4861 Total reward: 26.0 Training loss: 7.9755 Explore P: 0.7439
Episode: 4862 Total reward: 14.0 Training loss: 0.0388 Explore P: 0.7439
Episode: 4863 Total reward: 14.0 Training loss: 0.0779 Explore P: 0.7439
Episode: 4864 Total reward: 13.0 Training loss: 0.0855 Explore P: 0.7438
Episode: 4865 Total reward: 21.0 Training loss: 7.0046 Explore P: 0.7438
Episode: 4866 Total reward: 11.0 Training loss: 4.3812 Explore P: 0.7438
Episode: 4867 Total reward: 17.0 Training loss: 88.6995 Explore P: 0.7438
Episode: 4868 Total reward: 11.0 Training loss: 3.3666 Explore P: 0.7438
Episode: 4869 Total reward: 29.0 Training loss: 1.1240 Explore P: 0.7437
Episode: 4870 Total reward: 21.0 Training loss: 3.9636 Explore P: 0.7437
Episode: 4871 Total reward: 12.0 Training loss: 0.3959 Explore P: 0.7437
Episode: 4872 Total reward: 10.0 Training loss: 3.3564 Explore P: 0.7437
Episode: 4873 Total reward: 14.0 Training loss: 0.5145 Explore P: 0.7436
Episode: 4874 Total reward: 28.0 Training loss: 0.0789 Explore P: 0.7436
Episode: 4875 Total reward: 14.0 Training loss: 1.7776 Explore P: 0.7436
Episode: 4876 Total reward: 30.0 Training loss: 14.4269 Explore P: 0.7435
Episode: 4877 Total reward: 14.0 Training loss: 0.0219 Explore P: 0.7435
Episode: 4878 Total reward: 12.0 Training loss: 1.2576 Explore P: 0.7435
Episode: 4879 Total reward: 38.0 Training loss: 0.0137 Explore P: 0.7434
Episode: 4880 Total reward: 30.0 Training loss: 1.7808 Explore P: 0.7434
Episode: 4881 Total reward: 12.0 Training loss: 0.2889 Explore P: 0.7434
Episode: 4882 Total reward: 29.0 Training loss: 0.1222 Explore P: 0.7433
Episode: 4883 Total reward: 14.0 Training loss: 3.7394 Explore P: 0.7433
Episode: 4884 Total reward: 30.0 Training loss: 0.1277 Explore P: 0.7433
Episode: 4885 Total reward: 13.0 Training loss: 0.1115 Explore P: 0.7432
Episode: 4886 Total reward: 16.0 Training loss: 9.6285 Explore P: 0.7432
Episode: 4887 Total reward: 15.0 Training loss: 3.4539 Explore P: 0.7432
Episode: 4888 Total reward: 23.0 Training loss: 8.5244 Explore P: 0.7432
Episode: 4889 Total reward: 9.0 Training loss: 9.9230 Explore P: 0.7432
Episode: 4890 Total reward: 14.0 Training loss: 0.1079 Explore P: 0.7431
Episode: 4891 Total reward: 27.0 Training loss: 3.1496 Explore P: 0.7431
Episode: 4892 Total reward: 14.0 Training loss: 1.6865 Explore P: 0.7431
Episode: 4893 Total reward: 21.0 Training loss: 2.1887 Explore P: 0.7430
Episode: 4894 Total reward: 16.0 Training loss: 10.7402 Explore P: 0.7430
Episode: 4895 Total reward: 15.0 Training loss: 11.3353 Explore P: 0.7430
Episode: 4896 Total reward: 11.0 Training loss: 1.0860 Explore P: 0.7430
Episode: 4897 Total reward: 15.0 Training loss: 0.0782 Explore P: 0.7430
Episode: 4898 Total reward: 15.0 Training loss: 5.9883 Explore P: 0.7429
Episode: 4899 Total reward: 26.0 Training loss: 2.0139 Explore P: 0.7429
Episode: 4900 Total reward: 24.0 Training loss: 3.3049 Explore P: 0.7429
Episode: 4901 Total reward: 27.0 Training loss: 7.2906 Explore P: 0.7428
Episode: 4902 Total reward: 11.0 Training loss: 0.3621 Explore P: 0.7428
Episode: 4903 Total reward: 22.0 Training loss: 2.4150 Explore P: 0.7428
Episode: 4904 Total reward: 21.0 Training loss: 0.0107 Explore P: 0.7427
Episode: 4905 Total reward: 15.0 Training loss: 7.3535 Explore P: 0.7427
Episode: 4906 Total reward: 14.0 Training loss: 5.9579 Explore P: 0.7427
Episode: 4907 Total reward: 28.0 Training loss: 0.6296 Explore P: 0.7427
Episode: 4908 Total reward: 23.0 Training loss: 3.7903 Explore P: 0.7426
Episode: 4909 Total reward: 26.0 Training loss: 3.9884 Explore P: 0.7426
Episode: 4910 Total reward: 20.0 Training loss: 0.1430 Explore P: 0.7426
Episode: 4911 Total reward: 37.0 Training loss: 4.3530 Explore P: 0.7425
Episode: 4912 Total reward: 10.0 Training loss: 0.1985 Explore P: 0.7425
Episode: 4913 Total reward: 56.0 Training loss: 0.9502 Explore P: 0.7424
Episode: 4914 Total reward: 19.0 Training loss: 2.3048 Explore P: 0.7424
Episode: 4915 Total reward: 30.0 Training loss: 2.5467 Explore P: 0.7423
Episode: 4916 Total reward: 20.0 Training loss: 4.4869 Explore P: 0.7423
Episode: 4917 Total reward: 13.0 Training loss: 0.1155 Explore P: 0.7423
Episode: 4918 Total reward: 10.0 Training loss: 3.1164 Explore P: 0.7423
Episode: 4919 Total reward: 13.0 Training loss: 0.1802 Explore P: 0.7423
Episode: 4920 Total reward: 9.0 Training loss: 0.7530 Explore P: 0.7422
Episode: 4921 Total reward: 21.0 Training loss: 0.2990 Explore P: 0.7422
Episode: 4922 Total reward: 20.0 Training loss: 0.3722 Explore P: 0.7422
Episode: 4923 Total reward: 18.0 Training loss: 1.2442 Explore P: 0.7422
Episode: 4924 Total reward: 11.0 Training loss: 0.0890 Explore P: 0.7421
Episode: 4925 Total reward: 25.0 Training loss: 0.9050 Explore P: 0.7421
Episode: 4926 Total reward: 21.0 Training loss: 4.2145 Explore P: 0.7421
Episode: 4927 Total reward: 28.0 Training loss: 1.1354 Explore P: 0.7420
Episode: 4928 Total reward: 37.0 Training loss: 0.1491 Explore P: 0.7420
Episode: 4929 Total reward: 12.0 Training loss: 3.1941 Explore P: 0.7420
Episode: 4930 Total reward: 16.0 Training loss: 3.4012 Explore P: 0.7419
Episode: 4931 Total reward: 17.0 Training loss: 4.0545 Explore P: 0.7419
Episode: 4932 Total reward: 11.0 Training loss: 0.5778 Explore P: 0.7419
Episode: 4933 Total reward: 20.0 Training loss: 5.3148 Explore P: 0.7419
Episode: 4934 Total reward: 13.0 Training loss: 0.1168 Explore P: 0.7418
Episode: 4935 Total reward: 15.0 Training loss: 0.0885 Explore P: 0.7418
Episode: 4936 Total reward: 32.0 Training loss: 16.7635 Explore P: 0.7418
Episode: 4937 Total reward: 14.0 Training loss: 16.1433 Explore P: 0.7418
Episode: 4938 Total reward: 23.0 Training loss: 0.6929 Explore P: 0.7417
Episode: 4939 Total reward: 18.0 Training loss: 0.5583 Explore P: 0.7417
Episode: 4940 Total reward: 33.0 Training loss: 15.0394 Explore P: 0.7416
Episode: 4941 Total reward: 16.0 Training loss: 4.6998 Explore P: 0.7416
Episode: 4942 Total reward: 9.0 Training loss: 0.1320 Explore P: 0.7416
Episode: 4943 Total reward: 28.0 Training loss: 0.0573 Explore P: 0.7416
Episode: 4944 Total reward: 17.0 Training loss: 11.8406 Explore P: 0.7415
Episode: 4945 Total reward: 36.0 Training loss: 1.8019 Explore P: 0.7415
Episode: 4946 Total reward: 12.0 Training loss: 0.0547 Explore P: 0.7415
Episode: 4947 Total reward: 35.0 Training loss: 0.8270 Explore P: 0.7414
Episode: 4948 Total reward: 19.0 Training loss: 34.5637 Explore P: 0.7414
Episode: 4949 Total reward: 12.0 Training loss: 0.5776 Explore P: 0.7414
Episode: 4950 Total reward: 40.0 Training loss: 0.2220 Explore P: 0.7413
Episode: 4951 Total reward: 21.0 Training loss: 0.8484 Explore P: 0.7413
Episode: 4952 Total reward: 79.0 Training loss: 14.8463 Explore P: 0.7412
Episode: 4953 Total reward: 14.0 Training loss: 1.3456 Explore P: 0.7412
Episode: 4954 Total reward: 27.0 Training loss: 2.9367 Explore P: 0.7411
Episode: 4955 Total reward: 39.0 Training loss: 1.2474 Explore P: 0.7411
Episode: 4956 Total reward: 11.0 Training loss: 2.5457 Explore P: 0.7410
Episode: 4957 Total reward: 11.0 Training loss: 21.7571 Explore P: 0.7410
Episode: 4958 Total reward: 23.0 Training loss: 0.0735 Explore P: 0.7410
Episode: 4959 Total reward: 8.0 Training loss: 5.9602 Explore P: 0.7410
Episode: 4960 Total reward: 8.0 Training loss: 1.6105 Explore P: 0.7410
Episode: 4961 Total reward: 22.0 Training loss: 6.9356 Explore P: 0.7409
Episode: 4962 Total reward: 13.0 Training loss: 1.0975 Explore P: 0.7409
Episode: 4963 Total reward: 26.0 Training loss: 21.8273 Explore P: 0.7409
Episode: 4964 Total reward: 7.0 Training loss: 5.7574 Explore P: 0.7409
Episode: 4965 Total reward: 19.0 Training loss: 0.5366 Explore P: 0.7408
Episode: 4966 Total reward: 19.0 Training loss: 122.5868 Explore P: 0.7408
Episode: 4967 Total reward: 16.0 Training loss: 4.3696 Explore P: 0.7408
Episode: 4968 Total reward: 28.0 Training loss: 0.0492 Explore P: 0.7407
Episode: 4969 Total reward: 17.0 Training loss: 0.1615 Explore P: 0.7407
Episode: 4970 Total reward: 44.0 Training loss: 1.5282 Explore P: 0.7407
Episode: 4971 Total reward: 22.0 Training loss: 0.1070 Explore P: 0.7406
Episode: 4972 Total reward: 19.0 Training loss: 1.0320 Explore P: 0.7406
Episode: 4973 Total reward: 14.0 Training loss: 0.7836 Explore P: 0.7406
Episode: 4974 Total reward: 16.0 Training loss: 0.1040 Explore P: 0.7406
Episode: 4975 Total reward: 13.0 Training loss: 0.3200 Explore P: 0.7405
Episode: 4976 Total reward: 18.0 Training loss: 0.1193 Explore P: 0.7405
Episode: 4977 Total reward: 10.0 Training loss: 0.0860 Explore P: 0.7405
Episode: 4978 Total reward: 17.0 Training loss: 1.5702 Explore P: 0.7405
Episode: 4979 Total reward: 24.0 Training loss: 0.3792 Explore P: 0.7404
Episode: 4980 Total reward: 20.0 Training loss: 22.4259 Explore P: 0.7404
Episode: 4981 Total reward: 9.0 Training loss: 0.5333 Explore P: 0.7404
Episode: 4982 Total reward: 14.0 Training loss: 0.4892 Explore P: 0.7404
Episode: 4983 Total reward: 22.0 Training loss: 0.0360 Explore P: 0.7403
Episode: 4984 Total reward: 33.0 Training loss: 0.3813 Explore P: 0.7403
Episode: 4985 Total reward: 31.0 Training loss: 8.1781 Explore P: 0.7402
Episode: 4986 Total reward: 13.0 Training loss: 1.1152 Explore P: 0.7402
Episode: 4987 Total reward: 27.0 Training loss: 0.0280 Explore P: 0.7402
Episode: 4988 Total reward: 23.0 Training loss: 8.4206 Explore P: 0.7402
Episode: 4989 Total reward: 42.0 Training loss: 10.9747 Explore P: 0.7401
Episode: 4990 Total reward: 19.0 Training loss: 0.0081 Explore P: 0.7401
Episode: 4991 Total reward: 17.0 Training loss: 1.8286 Explore P: 0.7400
Episode: 4992 Total reward: 17.0 Training loss: 0.9267 Explore P: 0.7400
Episode: 4993 Total reward: 17.0 Training loss: 3.0993 Explore P: 0.7400
Episode: 4994 Total reward: 11.0 Training loss: 7.6704 Explore P: 0.7400
Episode: 4995 Total reward: 11.0 Training loss: 367.6236 Explore P: 0.7400
Episode: 4996 Total reward: 11.0 Training loss: 2.2155 Explore P: 0.7399
Episode: 4997 Total reward: 16.0 Training loss: 1.8390 Explore P: 0.7399
Episode: 4998 Total reward: 25.0 Training loss: 13.6038 Explore P: 0.7399
Episode: 4999 Total reward: 19.0 Training loss: 0.6882 Explore P: 0.7399
Episode: 5000 Total reward: 34.0 Training loss: 11.1554 Explore P: 0.7398
Episode: 5001 Total reward: 10.0 Training loss: 0.1021 Explore P: 0.7398
Episode: 5002 Total reward: 11.0 Training loss: 2.9551 Explore P: 0.7398
Episode: 5003 Total reward: 25.0 Training loss: 6.9713 Explore P: 0.7397
Episode: 5004 Total reward: 26.0 Training loss: 0.0136 Explore P: 0.7397
Episode: 5005 Total reward: 11.0 Training loss: 1.7560 Explore P: 0.7397
Episode: 5006 Total reward: 8.0 Training loss: 0.0521 Explore P: 0.7397
Episode: 5007 Total reward: 12.0 Training loss: 3.0722 Explore P: 0.7397
Episode: 5008 Total reward: 18.0 Training loss: 0.1700 Explore P: 0.7396
Episode: 5009 Total reward: 26.0 Training loss: 4.6327 Explore P: 0.7396
Episode: 5010 Total reward: 56.0 Training loss: 0.1808 Explore P: 0.7395
Episode: 5011 Total reward: 19.0 Training loss: 2.4281 Explore P: 0.7395
Episode: 5012 Total reward: 57.0 Training loss: 1.1902 Explore P: 0.7394
Episode: 5013 Total reward: 18.0 Training loss: 3.8010 Explore P: 0.7394
Episode: 5014 Total reward: 9.0 Training loss: 0.1381 Explore P: 0.7394
Episode: 5015 Total reward: 16.0 Training loss: 3.2684 Explore P: 0.7393
Episode: 5016 Total reward: 44.0 Training loss: 0.1704 Explore P: 0.7393
Episode: 5017 Total reward: 27.0 Training loss: 0.1023 Explore P: 0.7392
Episode: 5018 Total reward: 21.0 Training loss: 0.5355 Explore P: 0.7392
Episode: 5019 Total reward: 26.0 Training loss: 3.6652 Explore P: 0.7392
Episode: 5020 Total reward: 15.0 Training loss: 0.0379 Explore P: 0.7391
Episode: 5021 Total reward: 11.0 Training loss: 0.0883 Explore P: 0.7391
Episode: 5022 Total reward: 11.0 Training loss: 4.3029 Explore P: 0.7391
Episode: 5023 Total reward: 14.0 Training loss: 53.4430 Explore P: 0.7391
Episode: 5024 Total reward: 23.0 Training loss: 0.2903 Explore P: 0.7391
Episode: 5025 Total reward: 8.0 Training loss: 1.5669 Explore P: 0.7390
Episode: 5026 Total reward: 18.0 Training loss: 1.4571 Explore P: 0.7390
Episode: 5027 Total reward: 18.0 Training loss: 4.6690 Explore P: 0.7390
Episode: 5028 Total reward: 19.0 Training loss: 0.0357 Explore P: 0.7390
Episode: 5029 Total reward: 32.0 Training loss: 0.0240 Explore P: 0.7389
Episode: 5030 Total reward: 9.0 Training loss: 0.0613 Explore P: 0.7389
Episode: 5031 Total reward: 50.0 Training loss: 2.1242 Explore P: 0.7388
Episode: 5032 Total reward: 49.0 Training loss: 5.5028 Explore P: 0.7388
Episode: 5033 Total reward: 31.0 Training loss: 0.0709 Explore P: 0.7387
Episode: 5034 Total reward: 42.0 Training loss: 1.9524 Explore P: 0.7387
Episode: 5035 Total reward: 19.0 Training loss: 0.0217 Explore P: 0.7386
Episode: 5036 Total reward: 14.0 Training loss: 2.0552 Explore P: 0.7386
Episode: 5037 Total reward: 25.0 Training loss: 4.2076 Explore P: 0.7386
Episode: 5038 Total reward: 14.0 Training loss: 0.0177 Explore P: 0.7385
Episode: 5039 Total reward: 17.0 Training loss: 1.4751 Explore P: 0.7385
Episode: 5040 Total reward: 18.0 Training loss: 20.3534 Explore P: 0.7385
Episode: 5041 Total reward: 10.0 Training loss: 1.4060 Explore P: 0.7385
Episode: 5042 Total reward: 17.0 Training loss: 0.0678 Explore P: 0.7385
Episode: 5043 Total reward: 32.0 Training loss: 6.5491 Explore P: 0.7384
Episode: 5044 Total reward: 13.0 Training loss: 8.6105 Explore P: 0.7384
Episode: 5045 Total reward: 29.0 Training loss: 4.3563 Explore P: 0.7384
Episode: 5046 Total reward: 22.0 Training loss: 0.1287 Explore P: 0.7383
Episode: 5047 Total reward: 11.0 Training loss: 3.4375 Explore P: 0.7383
Episode: 5048 Total reward: 12.0 Training loss: 0.1008 Explore P: 0.7383
Episode: 5049 Total reward: 15.0 Training loss: 0.0485 Explore P: 0.7383
Episode: 5050 Total reward: 14.0 Training loss: 4.4428 Explore P: 0.7382
Episode: 5051 Total reward: 16.0 Training loss: 1.9175 Explore P: 0.7382
Episode: 5052 Total reward: 21.0 Training loss: 1.3783 Explore P: 0.7382
Episode: 5053 Total reward: 13.0 Training loss: 0.0479 Explore P: 0.7382
Episode: 5054 Total reward: 27.0 Training loss: 0.1363 Explore P: 0.7381
Episode: 5055 Total reward: 14.0 Training loss: 1.3801 Explore P: 0.7381
Episode: 5056 Total reward: 15.0 Training loss: 10.8957 Explore P: 0.7381
Episode: 5057 Total reward: 35.0 Training loss: 8.6216 Explore P: 0.7380
Episode: 5058 Total reward: 15.0 Training loss: 38.8242 Explore P: 0.7380
Episode: 5059 Total reward: 38.0 Training loss: 0.9509 Explore P: 0.7380
Episode: 5060 Total reward: 17.0 Training loss: 0.1690 Explore P: 0.7379
Episode: 5061 Total reward: 9.0 Training loss: 0.6889 Explore P: 0.7379
Episode: 5062 Total reward: 15.0 Training loss: 11.4141 Explore P: 0.7379
Episode: 5063 Total reward: 13.0 Training loss: 2.2210 Explore P: 0.7379
Episode: 5064 Total reward: 27.0 Training loss: 3.4400 Explore P: 0.7378
Episode: 5065 Total reward: 11.0 Training loss: 4.0744 Explore P: 0.7378
Episode: 5066 Total reward: 23.0 Training loss: 2.7552 Explore P: 0.7378
Episode: 5067 Total reward: 16.0 Training loss: 3.7032 Explore P: 0.7378
Episode: 5068 Total reward: 26.0 Training loss: 3.0710 Explore P: 0.7377
Episode: 5069 Total reward: 16.0 Training loss: 0.0458 Explore P: 0.7377
Episode: 5070 Total reward: 20.0 Training loss: 4.6553 Explore P: 0.7377
Episode: 5071 Total reward: 15.0 Training loss: 0.1209 Explore P: 0.7377
Episode: 5072 Total reward: 20.0 Training loss: 0.0951 Explore P: 0.7376
Episode: 5073 Total reward: 14.0 Training loss: 0.0581 Explore P: 0.7376
Episode: 5074 Total reward: 16.0 Training loss: 7.3640 Explore P: 0.7376
Episode: 5075 Total reward: 15.0 Training loss: 1.5384 Explore P: 0.7376
Episode: 5076 Total reward: 17.0 Training loss: 0.0622 Explore P: 0.7375
Episode: 5077 Total reward: 18.0 Training loss: 8.9733 Explore P: 0.7375
Episode: 5078 Total reward: 16.0 Training loss: 2.3824 Explore P: 0.7375
Episode: 5079 Total reward: 15.0 Training loss: 0.0495 Explore P: 0.7375
Episode: 5080 Total reward: 10.0 Training loss: 0.1267 Explore P: 0.7375
Episode: 5081 Total reward: 15.0 Training loss: 1.7727 Explore P: 0.7374
Episode: 5082 Total reward: 12.0 Training loss: 24.0957 Explore P: 0.7374
Episode: 5083 Total reward: 17.0 Training loss: 3.5044 Explore P: 0.7374
Episode: 5084 Total reward: 17.0 Training loss: 5.1342 Explore P: 0.7374
Episode: 5085 Total reward: 14.0 Training loss: 7.6903 Explore P: 0.7373
Episode: 5086 Total reward: 61.0 Training loss: 2.7333 Explore P: 0.7373
Episode: 5087 Total reward: 21.0 Training loss: 24.6903 Explore P: 0.7372
Episode: 5088 Total reward: 17.0 Training loss: 6.6896 Explore P: 0.7372
Episode: 5089 Total reward: 25.0 Training loss: 5.8830 Explore P: 0.7372
Episode: 5090 Total reward: 19.0 Training loss: 2.2868 Explore P: 0.7371
Episode: 5091 Total reward: 26.0 Training loss: 0.0372 Explore P: 0.7371
Episode: 5092 Total reward: 30.0 Training loss: 0.7722 Explore P: 0.7371
Episode: 5093 Total reward: 18.0 Training loss: 3.1498 Explore P: 0.7370
Episode: 5094 Total reward: 32.0 Training loss: 5.7850 Explore P: 0.7370
Episode: 5095 Total reward: 37.0 Training loss: 2.4826 Explore P: 0.7369
Episode: 5096 Total reward: 13.0 Training loss: 0.3104 Explore P: 0.7369
Episode: 5097 Total reward: 20.0 Training loss: 0.4246 Explore P: 0.7369
Episode: 5098 Total reward: 20.0 Training loss: 1.1505 Explore P: 0.7369
Episode: 5099 Total reward: 14.0 Training loss: 0.2336 Explore P: 0.7368
Episode: 5100 Total reward: 39.0 Training loss: 5.8563 Explore P: 0.7368
Episode: 5101 Total reward: 8.0 Training loss: 0.0625 Explore P: 0.7368
Episode: 5102 Total reward: 25.0 Training loss: 2.9796 Explore P: 0.7367
Episode: 5103 Total reward: 59.0 Training loss: 0.0823 Explore P: 0.7366
Episode: 5104 Total reward: 8.0 Training loss: 2.2239 Explore P: 0.7366
Episode: 5105 Total reward: 12.0 Training loss: 17.6257 Explore P: 0.7366
Episode: 5106 Total reward: 15.0 Training loss: 0.1789 Explore P: 0.7366
Episode: 5107 Total reward: 12.0 Training loss: 0.8028 Explore P: 0.7366
Episode: 5108 Total reward: 27.0 Training loss: 2.5619 Explore P: 0.7365
Episode: 5109 Total reward: 47.0 Training loss: 0.4052 Explore P: 0.7365
Episode: 5110 Total reward: 23.0 Training loss: 0.0725 Explore P: 0.7364
Episode: 5111 Total reward: 10.0 Training loss: 0.0565 Explore P: 0.7364
Episode: 5112 Total reward: 27.0 Training loss: 7.7935 Explore P: 0.7364
Episode: 5113 Total reward: 18.0 Training loss: 0.7458 Explore P: 0.7364
Episode: 5114 Total reward: 10.0 Training loss: 0.0158 Explore P: 0.7363
Episode: 5115 Total reward: 18.0 Training loss: 0.1178 Explore P: 0.7363
Episode: 5116 Total reward: 25.0 Training loss: 0.2045 Explore P: 0.7363
Episode: 5117 Total reward: 15.0 Training loss: 1.0838 Explore P: 0.7363
Episode: 5118 Total reward: 16.0 Training loss: 0.0893 Explore P: 0.7362
Episode: 5119 Total reward: 28.0 Training loss: 2.9253 Explore P: 0.7362
Episode: 5120 Total reward: 14.0 Training loss: 4.5345 Explore P: 0.7362
Episode: 5121 Total reward: 9.0 Training loss: 46.4242 Explore P: 0.7362
Episode: 5122 Total reward: 24.0 Training loss: 6.3223 Explore P: 0.7361
Episode: 5123 Total reward: 19.0 Training loss: 6.0701 Explore P: 0.7361
Episode: 5124 Total reward: 29.0 Training loss: 183.5636 Explore P: 0.7361
Episode: 5125 Total reward: 29.0 Training loss: 0.0230 Explore P: 0.7360
Episode: 5126 Total reward: 38.0 Training loss: 0.4582 Explore P: 0.7360
Episode: 5127 Total reward: 16.0 Training loss: 3.8644 Explore P: 0.7359
Episode: 5128 Total reward: 19.0 Training loss: 0.0968 Explore P: 0.7359
Episode: 5129 Total reward: 27.0 Training loss: 0.1223 Explore P: 0.7359
Episode: 5130 Total reward: 11.0 Training loss: 0.2402 Explore P: 0.7358
Episode: 5131 Total reward: 57.0 Training loss: 0.0378 Explore P: 0.7358
Episode: 5132 Total reward: 14.0 Training loss: 0.4127 Explore P: 0.7357
Episode: 5133 Total reward: 62.0 Training loss: 0.0230 Explore P: 0.7357
Episode: 5134 Total reward: 18.0 Training loss: 3.4618 Explore P: 0.7356
Episode: 5135 Total reward: 11.0 Training loss: 0.9494 Explore P: 0.7356
Episode: 5136 Total reward: 13.0 Training loss: 1.2316 Explore P: 0.7356
Episode: 5137 Total reward: 7.0 Training loss: 2.7420 Explore P: 0.7356
Episode: 5138 Total reward: 11.0 Training loss: 0.5980 Explore P: 0.7356
Episode: 5139 Total reward: 31.0 Training loss: 3.7914 Explore P: 0.7355
Episode: 5140 Total reward: 15.0 Training loss: 2.4749 Explore P: 0.7355
Episode: 5141 Total reward: 48.0 Training loss: 16.3438 Explore P: 0.7354
Episode: 5142 Total reward: 13.0 Training loss: 0.0543 Explore P: 0.7354
Episode: 5143 Total reward: 15.0 Training loss: 0.0336 Explore P: 0.7354
Episode: 5144 Total reward: 11.0 Training loss: 0.0821 Explore P: 0.7354
Episode: 5145 Total reward: 24.0 Training loss: 10.9884 Explore P: 0.7353
Episode: 5146 Total reward: 12.0 Training loss: 1.4995 Explore P: 0.7353
Episode: 5147 Total reward: 38.0 Training loss: 4.0016 Explore P: 0.7353
Episode: 5148 Total reward: 15.0 Training loss: 5.8252 Explore P: 0.7352
Episode: 5149 Total reward: 19.0 Training loss: 1.0034 Explore P: 0.7352
Episode: 5150 Total reward: 19.0 Training loss: 0.0751 Explore P: 0.7352
Episode: 5151 Total reward: 21.0 Training loss: 1.9962 Explore P: 0.7352
Episode: 5152 Total reward: 18.0 Training loss: 0.1825 Explore P: 0.7351
Episode: 5153 Total reward: 31.0 Training loss: 3.1528 Explore P: 0.7351
Episode: 5154 Total reward: 19.0 Training loss: 3.7660 Explore P: 0.7351
Episode: 5155 Total reward: 18.0 Training loss: 0.0740 Explore P: 0.7350
Episode: 5156 Total reward: 18.0 Training loss: 0.0351 Explore P: 0.7350
Episode: 5157 Total reward: 40.0 Training loss: 0.0668 Explore P: 0.7350
Episode: 5158 Total reward: 33.0 Training loss: 0.0486 Explore P: 0.7349
Episode: 5159 Total reward: 28.0 Training loss: 12.2897 Explore P: 0.7349
Episode: 5160 Total reward: 13.0 Training loss: 4.2568 Explore P: 0.7348
Episode: 5161 Total reward: 15.0 Training loss: 0.1349 Explore P: 0.7348
Episode: 5162 Total reward: 10.0 Training loss: 0.6975 Explore P: 0.7348
Episode: 5163 Total reward: 9.0 Training loss: 0.0562 Explore P: 0.7348
Episode: 5164 Total reward: 19.0 Training loss: 4.6035 Explore P: 0.7348
Episode: 5165 Total reward: 28.0 Training loss: 0.7137 Explore P: 0.7347
Episode: 5166 Total reward: 13.0 Training loss: 5.4601 Explore P: 0.7347
Episode: 5167 Total reward: 15.0 Training loss: 20.2086 Explore P: 0.7347
Episode: 5168 Total reward: 14.0 Training loss: 14.0487 Explore P: 0.7347
Episode: 5169 Total reward: 25.0 Training loss: 0.5412 Explore P: 0.7346
Episode: 5170 Total reward: 16.0 Training loss: 2.3612 Explore P: 0.7346
Episode: 5171 Total reward: 14.0 Training loss: 6.9480 Explore P: 0.7346
Episode: 5172 Total reward: 18.0 Training loss: 0.1799 Explore P: 0.7346
Episode: 5173 Total reward: 31.0 Training loss: 1.0445 Explore P: 0.7345
Episode: 5174 Total reward: 27.0 Training loss: 0.1595 Explore P: 0.7345
Episode: 5175 Total reward: 9.0 Training loss: 2.1523 Explore P: 0.7345
Episode: 5176 Total reward: 12.0 Training loss: 4.4174 Explore P: 0.7344
Episode: 5177 Total reward: 15.0 Training loss: 2.6772 Explore P: 0.7344
Episode: 5178 Total reward: 15.0 Training loss: 1.0693 Explore P: 0.7344
Episode: 5179 Total reward: 13.0 Training loss: 16.2648 Explore P: 0.7344
Episode: 5180 Total reward: 21.0 Training loss: 0.1997 Explore P: 0.7344
Episode: 5181 Total reward: 18.0 Training loss: 12.1182 Explore P: 0.7343
Episode: 5182 Total reward: 11.0 Training loss: 6.0806 Explore P: 0.7343
Episode: 5183 Total reward: 25.0 Training loss: 5.3800 Explore P: 0.7343
Episode: 5184 Total reward: 20.0 Training loss: 0.0680 Explore P: 0.7342
Episode: 5185 Total reward: 14.0 Training loss: 3.2052 Explore P: 0.7342
Episode: 5186 Total reward: 17.0 Training loss: 0.6849 Explore P: 0.7342
Episode: 5187 Total reward: 19.0 Training loss: 0.1077 Explore P: 0.7342
Episode: 5188 Total reward: 17.0 Training loss: 0.3730 Explore P: 0.7341
Episode: 5189 Total reward: 12.0 Training loss: 0.0331 Explore P: 0.7341
Episode: 5190 Total reward: 13.0 Training loss: 2.8296 Explore P: 0.7341
Episode: 5191 Total reward: 21.0 Training loss: 1.0941 Explore P: 0.7341
Episode: 5192 Total reward: 18.0 Training loss: 1.6598 Explore P: 0.7341
Episode: 5193 Total reward: 44.0 Training loss: 12.1610 Explore P: 0.7340
Episode: 5194 Total reward: 26.0 Training loss: 1.2927 Explore P: 0.7340
Episode: 5195 Total reward: 16.0 Training loss: 0.2801 Explore P: 0.7339
Episode: 5196 Total reward: 16.0 Training loss: 8.5573 Explore P: 0.7339
Episode: 5197 Total reward: 34.0 Training loss: 0.2172 Explore P: 0.7339
Episode: 5198 Total reward: 18.0 Training loss: 2.3549 Explore P: 0.7338
Episode: 5199 Total reward: 25.0 Training loss: 0.0895 Explore P: 0.7338
Episode: 5200 Total reward: 10.0 Training loss: 0.0534 Explore P: 0.7338
Episode: 5201 Total reward: 57.0 Training loss: 54.3461 Explore P: 0.7337
Episode: 5202 Total reward: 11.0 Training loss: 5.0755 Explore P: 0.7337
Episode: 5203 Total reward: 16.0 Training loss: 0.1288 Explore P: 0.7337
Episode: 5204 Total reward: 12.0 Training loss: 31.2569 Explore P: 0.7336
Episode: 5205 Total reward: 65.0 Training loss: 0.7926 Explore P: 0.7335
Episode: 5206 Total reward: 17.0 Training loss: 1.9572 Explore P: 0.7335
Episode: 5207 Total reward: 10.0 Training loss: 2.0613 Explore P: 0.7335
Episode: 5208 Total reward: 14.0 Training loss: 0.1042 Explore P: 0.7335
Episode: 5209 Total reward: 24.0 Training loss: 0.0400 Explore P: 0.7335
Episode: 5210 Total reward: 11.0 Training loss: 31.3623 Explore P: 0.7334
Episode: 5211 Total reward: 13.0 Training loss: 0.7708 Explore P: 0.7334
Episode: 5212 Total reward: 16.0 Training loss: 49.8865 Explore P: 0.7334
Episode: 5213 Total reward: 13.0 Training loss: 2.4304 Explore P: 0.7334
Episode: 5214 Total reward: 14.0 Training loss: 4.9708 Explore P: 0.7334
Episode: 5215 Total reward: 18.0 Training loss: 0.1693 Explore P: 0.7333
Episode: 5216 Total reward: 13.0 Training loss: 0.1857 Explore P: 0.7333
Episode: 5217 Total reward: 10.0 Training loss: 0.8934 Explore P: 0.7333
Episode: 5218 Total reward: 9.0 Training loss: 0.0748 Explore P: 0.7333
Episode: 5219 Total reward: 21.0 Training loss: 1.3831 Explore P: 0.7333
Episode: 5220 Total reward: 12.0 Training loss: 2.6450 Explore P: 0.7332
Episode: 5221 Total reward: 11.0 Training loss: 0.1874 Explore P: 0.7332
Episode: 5222 Total reward: 28.0 Training loss: 1.0796 Explore P: 0.7332
Episode: 5223 Total reward: 30.0 Training loss: 0.3076 Explore P: 0.7331
Episode: 5224 Total reward: 51.0 Training loss: 9.4344 Explore P: 0.7331
Episode: 5225 Total reward: 57.0 Training loss: 0.0701 Explore P: 0.7330
Episode: 5226 Total reward: 8.0 Training loss: 0.5426 Explore P: 0.7330
Episode: 5227 Total reward: 40.0 Training loss: 4.7574 Explore P: 0.7329
Episode: 5228 Total reward: 16.0 Training loss: 0.9392 Explore P: 0.7329
Episode: 5229 Total reward: 42.0 Training loss: 2.9571 Explore P: 0.7328
Episode: 5230 Total reward: 10.0 Training loss: 13.2380 Explore P: 0.7328
Episode: 5231 Total reward: 24.0 Training loss: 0.5807 Explore P: 0.7328
Episode: 5232 Total reward: 21.0 Training loss: 0.0659 Explore P: 0.7327
Episode: 5233 Total reward: 26.0 Training loss: 0.1021 Explore P: 0.7327
Episode: 5234 Total reward: 21.0 Training loss: 12.4953 Explore P: 0.7327
Episode: 5235 Total reward: 46.0 Training loss: 0.8501 Explore P: 0.7326
Episode: 5236 Total reward: 13.0 Training loss: 4.9933 Explore P: 0.7326
Episode: 5237 Total reward: 14.0 Training loss: 1.3027 Explore P: 0.7326
Episode: 5238 Total reward: 20.0 Training loss: 6.6516 Explore P: 0.7325
Episode: 5239 Total reward: 21.0 Training loss: 16.0840 Explore P: 0.7325
Episode: 5240 Total reward: 12.0 Training loss: 7.8176 Explore P: 0.7325
Episode: 5241 Total reward: 28.0 Training loss: 0.2278 Explore P: 0.7325
Episode: 5242 Total reward: 8.0 Training loss: 0.5286 Explore P: 0.7324
Episode: 5243 Total reward: 41.0 Training loss: 6.8157 Explore P: 0.7324
Episode: 5244 Total reward: 27.0 Training loss: 4.3976 Explore P: 0.7323
Episode: 5245 Total reward: 18.0 Training loss: 0.0669 Explore P: 0.7323
Episode: 5246 Total reward: 11.0 Training loss: 0.1539 Explore P: 0.7323
Episode: 5247 Total reward: 15.0 Training loss: 0.0784 Explore P: 0.7323
Episode: 5248 Total reward: 32.0 Training loss: 0.0069 Explore P: 0.7322
Episode: 5249 Total reward: 30.0 Training loss: 0.0927 Explore P: 0.7322
Episode: 5250 Total reward: 11.0 Training loss: 0.4594 Explore P: 0.7322
Episode: 5251 Total reward: 9.0 Training loss: 3.2980 Explore P: 0.7322
Episode: 5252 Total reward: 14.0 Training loss: 0.0459 Explore P: 0.7321
Episode: 5253 Total reward: 17.0 Training loss: 0.0534 Explore P: 0.7321
Episode: 5254 Total reward: 17.0 Training loss: 1.3871 Explore P: 0.7321
Episode: 5255 Total reward: 18.0 Training loss: 0.0767 Explore P: 0.7321
Episode: 5256 Total reward: 12.0 Training loss: 3.3019 Explore P: 0.7321
Episode: 5257 Total reward: 20.0 Training loss: 1.4992 Explore P: 0.7320
Episode: 5258 Total reward: 34.0 Training loss: 28.8363 Explore P: 0.7320
Episode: 5259 Total reward: 16.0 Training loss: 4.3597 Explore P: 0.7320
Episode: 5260 Total reward: 16.0 Training loss: 0.1068 Explore P: 0.7319
Episode: 5261 Total reward: 17.0 Training loss: 0.0138 Explore P: 0.7319
Episode: 5262 Total reward: 10.0 Training loss: 0.2281 Explore P: 0.7319
Episode: 5263 Total reward: 15.0 Training loss: 2.5453 Explore P: 0.7319
Episode: 5264 Total reward: 9.0 Training loss: 3.3233 Explore P: 0.7319
Episode: 5265 Total reward: 20.0 Training loss: 0.0721 Explore P: 0.7318
Episode: 5266 Total reward: 13.0 Training loss: 10.3828 Explore P: 0.7318
Episode: 5267 Total reward: 29.0 Training loss: 0.5606 Explore P: 0.7318
Episode: 5268 Total reward: 15.0 Training loss: 0.0664 Explore P: 0.7317
Episode: 5269 Total reward: 34.0 Training loss: 0.0338 Explore P: 0.7317
Episode: 5270 Total reward: 20.0 Training loss: 0.5937 Explore P: 0.7317
Episode: 5271 Total reward: 21.0 Training loss: 0.0635 Explore P: 0.7316
Episode: 5272 Total reward: 19.0 Training loss: 0.6805 Explore P: 0.7316
Episode: 5273 Total reward: 9.0 Training loss: 3.2892 Explore P: 0.7316
Episode: 5274 Total reward: 13.0 Training loss: 0.9934 Explore P: 0.7316
Episode: 5275 Total reward: 20.0 Training loss: 2.1757 Explore P: 0.7315
Episode: 5276 Total reward: 13.0 Training loss: 8.8299 Explore P: 0.7315
Episode: 5277 Total reward: 36.0 Training loss: 0.3109 Explore P: 0.7315
Episode: 5278 Total reward: 30.0 Training loss: 57.3046 Explore P: 0.7314
Episode: 5279 Total reward: 12.0 Training loss: 21.7844 Explore P: 0.7314
Episode: 5280 Total reward: 10.0 Training loss: 3.3533 Explore P: 0.7314
Episode: 5281 Total reward: 36.0 Training loss: 0.0536 Explore P: 0.7314
Episode: 5282 Total reward: 14.0 Training loss: 1.2786 Explore P: 0.7313
Episode: 5283 Total reward: 27.0 Training loss: 0.0077 Explore P: 0.7313
Episode: 5284 Total reward: 43.0 Training loss: 0.0302 Explore P: 0.7312
Episode: 5285 Total reward: 20.0 Training loss: 0.0733 Explore P: 0.7312
Episode: 5286 Total reward: 23.0 Training loss: 4.1185 Explore P: 0.7312
Episode: 5287 Total reward: 27.0 Training loss: 3.7098 Explore P: 0.7311
Episode: 5288 Total reward: 17.0 Training loss: 3.4876 Explore P: 0.7311
Episode: 5289 Total reward: 17.0 Training loss: 0.1333 Explore P: 0.7311
Episode: 5290 Total reward: 14.0 Training loss: 1.4956 Explore P: 0.7311
Episode: 5291 Total reward: 16.0 Training loss: 0.0453 Explore P: 0.7310
Episode: 5292 Total reward: 21.0 Training loss: 0.0383 Explore P: 0.7310
Episode: 5293 Total reward: 16.0 Training loss: 0.7524 Explore P: 0.7310
Episode: 5294 Total reward: 15.0 Training loss: 5.3995 Explore P: 0.7310
Episode: 5295 Total reward: 20.0 Training loss: 0.3649 Explore P: 0.7309
Episode: 5296 Total reward: 40.0 Training loss: 21.2892 Explore P: 0.7309
Episode: 5297 Total reward: 22.0 Training loss: 0.6485 Explore P: 0.7308
Episode: 5298 Total reward: 34.0 Training loss: 0.1990 Explore P: 0.7308
Episode: 5299 Total reward: 29.0 Training loss: 0.0738 Explore P: 0.7308
Episode: 5300 Total reward: 21.0 Training loss: 0.0797 Explore P: 0.7307
Episode: 5301 Total reward: 14.0 Training loss: 0.0489 Explore P: 0.7307
Episode: 5302 Total reward: 13.0 Training loss: 2.9578 Explore P: 0.7307
Episode: 5303 Total reward: 31.0 Training loss: 7.5505 Explore P: 0.7306
Episode: 5304 Total reward: 17.0 Training loss: 7.9390 Explore P: 0.7306
Episode: 5305 Total reward: 9.0 Training loss: 3.2434 Explore P: 0.7306
Episode: 5306 Total reward: 22.0 Training loss: 0.6740 Explore P: 0.7306
Episode: 5307 Total reward: 13.0 Training loss: 0.1213 Explore P: 0.7306
Episode: 5308 Total reward: 36.0 Training loss: 0.2817 Explore P: 0.7305
Episode: 5309 Total reward: 14.0 Training loss: 5.6041 Explore P: 0.7305
Episode: 5310 Total reward: 19.0 Training loss: 9.4291 Explore P: 0.7305
Episode: 5311 Total reward: 23.0 Training loss: 1.1061 Explore P: 0.7304
Episode: 5312 Total reward: 17.0 Training loss: 0.6991 Explore P: 0.7304
Episode: 5313 Total reward: 24.0 Training loss: 2.5946 Explore P: 0.7304
Episode: 5314 Total reward: 9.0 Training loss: 1.9496 Explore P: 0.7303
Episode: 5315 Total reward: 14.0 Training loss: 6.5149 Explore P: 0.7303
Episode: 5316 Total reward: 32.0 Training loss: 11.4145 Explore P: 0.7303
Episode: 5317 Total reward: 16.0 Training loss: 4.8358 Explore P: 0.7303
Episode: 5318 Total reward: 16.0 Training loss: 0.1359 Explore P: 0.7302
Episode: 5319 Total reward: 10.0 Training loss: 29.3190 Explore P: 0.7302
Episode: 5320 Total reward: 12.0 Training loss: 2.1073 Explore P: 0.7302
Episode: 5321 Total reward: 10.0 Training loss: 0.1701 Explore P: 0.7302
Episode: 5322 Total reward: 10.0 Training loss: 0.0933 Explore P: 0.7302
Episode: 5323 Total reward: 15.0 Training loss: 6.5800 Explore P: 0.7302
Episode: 5324 Total reward: 13.0 Training loss: 0.7460 Explore P: 0.7301
Episode: 5325 Total reward: 18.0 Training loss: 0.1148 Explore P: 0.7301
Episode: 5326 Total reward: 9.0 Training loss: 5.2894 Explore P: 0.7301
Episode: 5327 Total reward: 15.0 Training loss: 5.0930 Explore P: 0.7301
Episode: 5328 Total reward: 18.0 Training loss: 0.0526 Explore P: 0.7300
Episode: 5329 Total reward: 37.0 Training loss: 4.9873 Explore P: 0.7300
Episode: 5330 Total reward: 13.0 Training loss: 1.5412 Explore P: 0.7300
Episode: 5331 Total reward: 14.0 Training loss: 5.3886 Explore P: 0.7300
Episode: 5332 Total reward: 34.0 Training loss: 0.1382 Explore P: 0.7299
Episode: 5333 Total reward: 15.0 Training loss: 0.0255 Explore P: 0.7299
Episode: 5334 Total reward: 85.0 Training loss: 0.3566 Explore P: 0.7298
Episode: 5335 Total reward: 14.0 Training loss: 0.0633 Explore P: 0.7297
Episode: 5336 Total reward: 12.0 Training loss: 4.0764 Explore P: 0.7297
Episode: 5337 Total reward: 23.0 Training loss: 5.2052 Explore P: 0.7297
Episode: 5338 Total reward: 31.0 Training loss: 10.4457 Explore P: 0.7296
Episode: 5339 Total reward: 30.0 Training loss: 15.0933 Explore P: 0.7296
Episode: 5340 Total reward: 22.0 Training loss: 0.5375 Explore P: 0.7296
Episode: 5341 Total reward: 11.0 Training loss: 2.3707 Explore P: 0.7296
Episode: 5342 Total reward: 12.0 Training loss: 0.2127 Explore P: 0.7295
Episode: 5343 Total reward: 13.0 Training loss: 2.5551 Explore P: 0.7295
Episode: 5344 Total reward: 15.0 Training loss: 0.1185 Explore P: 0.7295
Episode: 5345 Total reward: 14.0 Training loss: 0.4357 Explore P: 0.7295
Episode: 5346 Total reward: 12.0 Training loss: 0.1939 Explore P: 0.7295
Episode: 5347 Total reward: 17.0 Training loss: 2.3605 Explore P: 0.7294
Episode: 5348 Total reward: 16.0 Training loss: 2.3028 Explore P: 0.7294
Episode: 5349 Total reward: 13.0 Training loss: 0.1647 Explore P: 0.7294
Episode: 5350 Total reward: 37.0 Training loss: 0.5839 Explore P: 0.7293
Episode: 5351 Total reward: 21.0 Training loss: 8.3966 Explore P: 0.7293
Episode: 5352 Total reward: 30.0 Training loss: 1.7924 Explore P: 0.7293
Episode: 5353 Total reward: 16.0 Training loss: 2.2429 Explore P: 0.7292
Episode: 5354 Total reward: 16.0 Training loss: 0.6062 Explore P: 0.7292
Episode: 5355 Total reward: 12.0 Training loss: 1.3089 Explore P: 0.7292
Episode: 5356 Total reward: 19.0 Training loss: 0.0937 Explore P: 0.7292
Episode: 5357 Total reward: 38.0 Training loss: 0.0791 Explore P: 0.7291
Episode: 5358 Total reward: 25.0 Training loss: 3.0488 Explore P: 0.7291
Episode: 5359 Total reward: 18.0 Training loss: 0.0398 Explore P: 0.7291
Episode: 5360 Total reward: 10.0 Training loss: 7.6537 Explore P: 0.7290
Episode: 5361 Total reward: 30.0 Training loss: 1.3611 Explore P: 0.7290
Episode: 5362 Total reward: 27.0 Training loss: 3.8028 Explore P: 0.7290
Episode: 5363 Total reward: 10.0 Training loss: 0.0314 Explore P: 0.7289
Episode: 5364 Total reward: 16.0 Training loss: 0.1457 Explore P: 0.7289
Episode: 5365 Total reward: 20.0 Training loss: 0.1414 Explore P: 0.7289
Episode: 5366 Total reward: 27.0 Training loss: 2.0652 Explore P: 0.7289
Episode: 5367 Total reward: 25.0 Training loss: 9.8891 Explore P: 0.7288
Episode: 5368 Total reward: 19.0 Training loss: 11.9919 Explore P: 0.7288
Episode: 5369 Total reward: 11.0 Training loss: 0.0224 Explore P: 0.7288
Episode: 5370 Total reward: 20.0 Training loss: 0.9431 Explore P: 0.7288
Episode: 5371 Total reward: 30.0 Training loss: 0.0508 Explore P: 0.7287
Episode: 5372 Total reward: 15.0 Training loss: 6.1710 Explore P: 0.7287
Episode: 5373 Total reward: 17.0 Training loss: 0.0241 Explore P: 0.7287
Episode: 5374 Total reward: 17.0 Training loss: 2.0220 Explore P: 0.7286
Episode: 5375 Total reward: 41.0 Training loss: 0.0639 Explore P: 0.7286
Episode: 5376 Total reward: 9.0 Training loss: 6.7658 Explore P: 0.7286
Episode: 5377 Total reward: 10.0 Training loss: 1.8436 Explore P: 0.7286
Episode: 5378 Total reward: 20.0 Training loss: 0.7245 Explore P: 0.7285
Episode: 5379 Total reward: 26.0 Training loss: 0.0334 Explore P: 0.7285
Episode: 5380 Total reward: 38.0 Training loss: 20.7298 Explore P: 0.7284
Episode: 5381 Total reward: 12.0 Training loss: 0.4515 Explore P: 0.7284
Episode: 5382 Total reward: 21.0 Training loss: 5.8482 Explore P: 0.7284
Episode: 5383 Total reward: 14.0 Training loss: 1.3270 Explore P: 0.7284
Episode: 5384 Total reward: 23.0 Training loss: 0.9546 Explore P: 0.7283
Episode: 5385 Total reward: 11.0 Training loss: 25.7572 Explore P: 0.7283
Episode: 5386 Total reward: 14.0 Training loss: 7.7534 Explore P: 0.7283
Episode: 5387 Total reward: 11.0 Training loss: 3.3542 Explore P: 0.7283
Episode: 5388 Total reward: 17.0 Training loss: 7.9383 Explore P: 0.7283
Episode: 5389 Total reward: 19.0 Training loss: 3.1336 Explore P: 0.7282
Episode: 5390 Total reward: 15.0 Training loss: 0.0654 Explore P: 0.7282
Episode: 5391 Total reward: 34.0 Training loss: 4.6696 Explore P: 0.7282
Episode: 5392 Total reward: 13.0 Training loss: 0.0140 Explore P: 0.7281
Episode: 5393 Total reward: 24.0 Training loss: 3.3764 Explore P: 0.7281
Episode: 5394 Total reward: 17.0 Training loss: 0.1038 Explore P: 0.7281
Episode: 5395 Total reward: 23.0 Training loss: 1.4833 Explore P: 0.7280
Episode: 5396 Total reward: 36.0 Training loss: 0.1380 Explore P: 0.7280
Episode: 5397 Total reward: 14.0 Training loss: 0.3161 Explore P: 0.7280
Episode: 5398 Total reward: 28.0 Training loss: 46.1672 Explore P: 0.7279
Episode: 5399 Total reward: 29.0 Training loss: 0.7581 Explore P: 0.7279
Episode: 5400 Total reward: 23.0 Training loss: 0.1888 Explore P: 0.7279
Episode: 5401 Total reward: 10.0 Training loss: 2.4929 Explore P: 0.7278
Episode: 5402 Total reward: 11.0 Training loss: 2.5036 Explore P: 0.7278
Episode: 5403 Total reward: 51.0 Training loss: 0.0782 Explore P: 0.7278
Episode: 5404 Total reward: 27.0 Training loss: 0.0331 Explore P: 0.7277
Episode: 5405 Total reward: 53.0 Training loss: 32.8821 Explore P: 0.7276
Episode: 5406 Total reward: 56.0 Training loss: 7.3303 Explore P: 0.7276
Episode: 5407 Total reward: 14.0 Training loss: 0.1296 Explore P: 0.7275
Episode: 5408 Total reward: 22.0 Training loss: 13.5734 Explore P: 0.7275
Episode: 5409 Total reward: 25.0 Training loss: 1.3705 Explore P: 0.7275
Episode: 5410 Total reward: 18.0 Training loss: 2.0499 Explore P: 0.7274
Episode: 5411 Total reward: 16.0 Training loss: 0.5922 Explore P: 0.7274
Episode: 5412 Total reward: 43.0 Training loss: 0.3966 Explore P: 0.7274
Episode: 5413 Total reward: 20.0 Training loss: 1.4563 Explore P: 0.7273
Episode: 5414 Total reward: 17.0 Training loss: 0.0748 Explore P: 0.7273
Episode: 5415 Total reward: 14.0 Training loss: 5.0051 Explore P: 0.7273
Episode: 5416 Total reward: 10.0 Training loss: 0.1211 Explore P: 0.7273
Episode: 5417 Total reward: 22.0 Training loss: 1.6954 Explore P: 0.7272
Episode: 5418 Total reward: 10.0 Training loss: 0.0906 Explore P: 0.7272
Episode: 5419 Total reward: 21.0 Training loss: 1.8889 Explore P: 0.7272
Episode: 5420 Total reward: 19.0 Training loss: 0.0215 Explore P: 0.7272
Episode: 5421 Total reward: 15.0 Training loss: 24.1351 Explore P: 0.7272
Episode: 5422 Total reward: 18.0 Training loss: 1.2700 Explore P: 0.7271
Episode: 5423 Total reward: 22.0 Training loss: 3.7863 Explore P: 0.7271
Episode: 5424 Total reward: 46.0 Training loss: 2.9278 Explore P: 0.7270
Episode: 5425 Total reward: 20.0 Training loss: 0.7631 Explore P: 0.7270
Episode: 5426 Total reward: 27.0 Training loss: 7.6236 Explore P: 0.7270
Episode: 5427 Total reward: 10.0 Training loss: 1.8902 Explore P: 0.7269
Episode: 5428 Total reward: 29.0 Training loss: 5.0983 Explore P: 0.7269
Episode: 5429 Total reward: 16.0 Training loss: 0.0982 Explore P: 0.7269
Episode: 5430 Total reward: 18.0 Training loss: 2.2890 Explore P: 0.7269
Episode: 5431 Total reward: 14.0 Training loss: 0.1754 Explore P: 0.7268
Episode: 5432 Total reward: 13.0 Training loss: 0.1360 Explore P: 0.7268
Episode: 5433 Total reward: 17.0 Training loss: 1.7978 Explore P: 0.7268
Episode: 5434 Total reward: 22.0 Training loss: 0.5188 Explore P: 0.7268
Episode: 5435 Total reward: 15.0 Training loss: 0.6827 Explore P: 0.7267
Episode: 5436 Total reward: 27.0 Training loss: 0.2191 Explore P: 0.7267
Episode: 5437 Total reward: 17.0 Training loss: 1.1544 Explore P: 0.7267
Episode: 5438 Total reward: 13.0 Training loss: 0.0847 Explore P: 0.7267
Episode: 5439 Total reward: 10.0 Training loss: 0.7339 Explore P: 0.7266
Episode: 5440 Total reward: 17.0 Training loss: 0.1408 Explore P: 0.7266
Episode: 5441 Total reward: 46.0 Training loss: 1.7130 Explore P: 0.7266
Episode: 5442 Total reward: 9.0 Training loss: 0.2168 Explore P: 0.7265
Episode: 5443 Total reward: 37.0 Training loss: 4.4888 Explore P: 0.7265
Episode: 5444 Total reward: 26.0 Training loss: 0.0536 Explore P: 0.7264
Episode: 5445 Total reward: 40.0 Training loss: 0.0681 Explore P: 0.7264
Episode: 5446 Total reward: 19.0 Training loss: 0.2060 Explore P: 0.7264
Episode: 5447 Total reward: 23.0 Training loss: 0.7440 Explore P: 0.7263
Episode: 5448 Total reward: 14.0 Training loss: 1.7100 Explore P: 0.7263
Episode: 5449 Total reward: 21.0 Training loss: 1.8945 Explore P: 0.7263
Episode: 5450 Total reward: 20.0 Training loss: 5.0917 Explore P: 0.7263
Episode: 5451 Total reward: 19.0 Training loss: 0.0694 Explore P: 0.7262
Episode: 5452 Total reward: 41.0 Training loss: 0.8740 Explore P: 0.7262
Episode: 5453 Total reward: 16.0 Training loss: 4.9063 Explore P: 0.7261
Episode: 5454 Total reward: 12.0 Training loss: 5.6390 Explore P: 0.7261
Episode: 5455 Total reward: 47.0 Training loss: 10.9143 Explore P: 0.7261
Episode: 5456 Total reward: 15.0 Training loss: 0.4735 Explore P: 0.7260
Episode: 5457 Total reward: 38.0 Training loss: 9.1266 Explore P: 0.7260
Episode: 5458 Total reward: 25.0 Training loss: 0.1260 Explore P: 0.7259
Episode: 5459 Total reward: 20.0 Training loss: 0.0436 Explore P: 0.7259
Episode: 5460 Total reward: 13.0 Training loss: 10.2393 Explore P: 0.7259
Episode: 5461 Total reward: 11.0 Training loss: 7.8992 Explore P: 0.7259
Episode: 5462 Total reward: 14.0 Training loss: 0.2527 Explore P: 0.7259
Episode: 5463 Total reward: 18.0 Training loss: 0.0518 Explore P: 0.7258
Episode: 5464 Total reward: 14.0 Training loss: 0.5440 Explore P: 0.7258
Episode: 5465 Total reward: 17.0 Training loss: 0.3156 Explore P: 0.7258
Episode: 5466 Total reward: 16.0 Training loss: 0.4072 Explore P: 0.7258
Episode: 5467 Total reward: 37.0 Training loss: 0.0890 Explore P: 0.7257
Episode: 5468 Total reward: 41.0 Training loss: 0.1912 Explore P: 0.7257
Episode: 5469 Total reward: 15.0 Training loss: 11.8519 Explore P: 0.7256
Episode: 5470 Total reward: 15.0 Training loss: 5.8415 Explore P: 0.7256
Episode: 5471 Total reward: 8.0 Training loss: 1.6802 Explore P: 0.7256
Episode: 5472 Total reward: 13.0 Training loss: 0.2781 Explore P: 0.7256
Episode: 5473 Total reward: 22.0 Training loss: 0.0843 Explore P: 0.7256
Episode: 5474 Total reward: 12.0 Training loss: 3.4376 Explore P: 0.7255
Episode: 5475 Total reward: 15.0 Training loss: 1.3197 Explore P: 0.7255
Episode: 5476 Total reward: 20.0 Training loss: 3.1077 Explore P: 0.7255
Episode: 5477 Total reward: 12.0 Training loss: 3.0751 Explore P: 0.7255
Episode: 5478 Total reward: 12.0 Training loss: 0.3740 Explore P: 0.7255
Episode: 5479 Total reward: 32.0 Training loss: 1.5723 Explore P: 0.7254
Episode: 5480 Total reward: 35.0 Training loss: 1.1338 Explore P: 0.7254
Episode: 5481 Total reward: 27.0 Training loss: 1.0119 Explore P: 0.7253
Episode: 5482 Total reward: 35.0 Training loss: 0.1111 Explore P: 0.7253
Episode: 5483 Total reward: 12.0 Training loss: 1.1489 Explore P: 0.7253
Episode: 5484 Total reward: 24.0 Training loss: 0.1689 Explore P: 0.7252
Episode: 5485 Total reward: 13.0 Training loss: 0.6799 Explore P: 0.7252
Episode: 5486 Total reward: 53.0 Training loss: 9.5279 Explore P: 0.7251
Episode: 5487 Total reward: 25.0 Training loss: 0.8489 Explore P: 0.7251
Episode: 5488 Total reward: 20.0 Training loss: 2.2998 Explore P: 0.7251
Episode: 5489 Total reward: 49.0 Training loss: 11.1482 Explore P: 0.7250
Episode: 5490 Total reward: 60.0 Training loss: 1.0726 Explore P: 0.7249
Episode: 5491 Total reward: 31.0 Training loss: 0.3741 Explore P: 0.7249
Episode: 5492 Total reward: 12.0 Training loss: 1.1961 Explore P: 0.7248
Episode: 5493 Total reward: 16.0 Training loss: 0.0752 Explore P: 0.7248
Episode: 5494 Total reward: 16.0 Training loss: 0.2180 Explore P: 0.7248
Episode: 5495 Total reward: 23.0 Training loss: 0.2947 Explore P: 0.7248
Episode: 5496 Total reward: 14.0 Training loss: 0.0618 Explore P: 0.7247
Episode: 5497 Total reward: 13.0 Training loss: 0.9659 Explore P: 0.7247
Episode: 5498 Total reward: 23.0 Training loss: 5.6339 Explore P: 0.7247
Episode: 5499 Total reward: 15.0 Training loss: 1.4502 Explore P: 0.7247
Episode: 5500 Total reward: 23.0 Training loss: 4.5514 Explore P: 0.7246
Episode: 5501 Total reward: 12.0 Training loss: 0.5843 Explore P: 0.7246
Episode: 5502 Total reward: 17.0 Training loss: 0.5278 Explore P: 0.7246
Episode: 5503 Total reward: 62.0 Training loss: 0.5769 Explore P: 0.7245
Episode: 5504 Total reward: 16.0 Training loss: 3.6082 Explore P: 0.7245
Episode: 5505 Total reward: 23.0 Training loss: 2.8921 Explore P: 0.7245
Episode: 5506 Total reward: 32.0 Training loss: 0.0782 Explore P: 0.7244
Episode: 5507 Total reward: 42.0 Training loss: 3.1884 Explore P: 0.7243
Episode: 5508 Total reward: 24.0 Training loss: 3.0673 Explore P: 0.7243
Episode: 5509 Total reward: 18.0 Training loss: 2.0272 Explore P: 0.7243
Episode: 5510 Total reward: 10.0 Training loss: 0.7860 Explore P: 0.7243
Episode: 5511 Total reward: 33.0 Training loss: 0.1033 Explore P: 0.7242
Episode: 5512 Total reward: 24.0 Training loss: 0.0842 Explore P: 0.7242
Episode: 5513 Total reward: 29.0 Training loss: 0.1493 Explore P: 0.7241
Episode: 5514 Total reward: 30.0 Training loss: 0.1677 Explore P: 0.7241
Episode: 5515 Total reward: 11.0 Training loss: 3.7835 Explore P: 0.7241
Episode: 5516 Total reward: 28.0 Training loss: 9.2533 Explore P: 0.7241
Episode: 5517 Total reward: 11.0 Training loss: 1.2224 Explore P: 0.7240
Episode: 5518 Total reward: 14.0 Training loss: 0.8235 Explore P: 0.7240
Episode: 5519 Total reward: 8.0 Training loss: 4.2364 Explore P: 0.7240
Episode: 5520 Total reward: 30.0 Training loss: 0.0613 Explore P: 0.7240
Episode: 5521 Total reward: 12.0 Training loss: 0.0209 Explore P: 0.7239
Episode: 5522 Total reward: 10.0 Training loss: 0.0237 Explore P: 0.7239
Episode: 5523 Total reward: 80.0 Training loss: 1.1610 Explore P: 0.7238
Episode: 5524 Total reward: 16.0 Training loss: 0.0943 Explore P: 0.7238
Episode: 5525 Total reward: 20.0 Training loss: 1.3165 Explore P: 0.7238
Episode: 5526 Total reward: 12.0 Training loss: 0.3399 Explore P: 0.7237
Episode: 5527 Total reward: 19.0 Training loss: 0.0900 Explore P: 0.7237
Episode: 5528 Total reward: 20.0 Training loss: 0.4044 Explore P: 0.7237
Episode: 5529 Total reward: 10.0 Training loss: 2.7336 Explore P: 0.7237
Episode: 5530 Total reward: 22.0 Training loss: 0.8877 Explore P: 0.7236
Episode: 5531 Total reward: 31.0 Training loss: 16.4196 Explore P: 0.7236
Episode: 5532 Total reward: 14.0 Training loss: 0.8472 Explore P: 0.7236
Episode: 5533 Total reward: 11.0 Training loss: 0.1288 Explore P: 0.7236
Episode: 5534 Total reward: 24.0 Training loss: 1.1064 Explore P: 0.7235
Episode: 5535 Total reward: 12.0 Training loss: 4.6688 Explore P: 0.7235
Episode: 5536 Total reward: 11.0 Training loss: 8.0117 Explore P: 0.7235
Episode: 5537 Total reward: 17.0 Training loss: 8.0038 Explore P: 0.7235
Episode: 5538 Total reward: 15.0 Training loss: 0.0478 Explore P: 0.7235
Episode: 5539 Total reward: 65.0 Training loss: 6.5626 Explore P: 0.7234
Episode: 5540 Total reward: 40.0 Training loss: 0.4321 Explore P: 0.7233
Episode: 5541 Total reward: 12.0 Training loss: 6.8785 Explore P: 0.7233
Episode: 5542 Total reward: 16.0 Training loss: 0.1396 Explore P: 0.7233
Episode: 5543 Total reward: 24.0 Training loss: 0.1040 Explore P: 0.7232
Episode: 5544 Total reward: 14.0 Training loss: 0.1779 Explore P: 0.7232
Episode: 5545 Total reward: 14.0 Training loss: 2.0752 Explore P: 0.7232
Episode: 5546 Total reward: 9.0 Training loss: 0.5045 Explore P: 0.7232
Episode: 5547 Total reward: 35.0 Training loss: 6.7795 Explore P: 0.7231
Episode: 5548 Total reward: 10.0 Training loss: 1.0235 Explore P: 0.7231
Episode: 5549 Total reward: 30.0 Training loss: 0.4636 Explore P: 0.7231
Episode: 5550 Total reward: 27.0 Training loss: 1.6226 Explore P: 0.7230
Episode: 5551 Total reward: 19.0 Training loss: 0.2441 Explore P: 0.7230
Episode: 5552 Total reward: 13.0 Training loss: 0.0044 Explore P: 0.7230
Episode: 5553 Total reward: 12.0 Training loss: 1.3080 Explore P: 0.7230
Episode: 5554 Total reward: 26.0 Training loss: 0.0799 Explore P: 0.7229
Episode: 5555 Total reward: 11.0 Training loss: 0.1901 Explore P: 0.7229
Episode: 5556 Total reward: 15.0 Training loss: 0.2999 Explore P: 0.7229
Episode: 5557 Total reward: 11.0 Training loss: 0.0866 Explore P: 0.7229
Episode: 5558 Total reward: 20.0 Training loss: 1.7251 Explore P: 0.7228
Episode: 5559 Total reward: 21.0 Training loss: 0.0875 Explore P: 0.7228
Episode: 5560 Total reward: 16.0 Training loss: 2.3244 Explore P: 0.7228
Episode: 5561 Total reward: 11.0 Training loss: 3.0651 Explore P: 0.7228
Episode: 5562 Total reward: 16.0 Training loss: 8.2060 Explore P: 0.7228
Episode: 5563 Total reward: 14.0 Training loss: 0.5733 Explore P: 0.7227
Episode: 5564 Total reward: 23.0 Training loss: 2.9584 Explore P: 0.7227
Episode: 5565 Total reward: 39.0 Training loss: 0.0371 Explore P: 0.7226
Episode: 5566 Total reward: 25.0 Training loss: 0.0907 Explore P: 0.7226
Episode: 5567 Total reward: 18.0 Training loss: 1.3267 Explore P: 0.7226
Episode: 5568 Total reward: 12.0 Training loss: 1.1421 Explore P: 0.7226
Episode: 5569 Total reward: 17.0 Training loss: 0.3244 Explore P: 0.7225
Episode: 5570 Total reward: 9.0 Training loss: 0.1093 Explore P: 0.7225
Episode: 5571 Total reward: 15.0 Training loss: 0.0301 Explore P: 0.7225
Episode: 5572 Total reward: 15.0 Training loss: 0.0489 Explore P: 0.7225
Episode: 5573 Total reward: 9.0 Training loss: 0.1136 Explore P: 0.7225
Episode: 5574 Total reward: 18.0 Training loss: 3.5574 Explore P: 0.7225
Episode: 5575 Total reward: 33.0 Training loss: 47.2810 Explore P: 0.7224
Episode: 5576 Total reward: 21.0 Training loss: 0.8917 Explore P: 0.7224
Episode: 5577 Total reward: 18.0 Training loss: 0.0336 Explore P: 0.7224
Episode: 5578 Total reward: 15.0 Training loss: 1.8028 Explore P: 0.7223
Episode: 5579 Total reward: 36.0 Training loss: 0.9573 Explore P: 0.7223
Episode: 5580 Total reward: 16.0 Training loss: 0.7904 Explore P: 0.7223
Episode: 5581 Total reward: 24.0 Training loss: 2.1560 Explore P: 0.7222
Episode: 5582 Total reward: 46.0 Training loss: 0.0357 Explore P: 0.7222
Episode: 5583 Total reward: 13.0 Training loss: 0.1534 Explore P: 0.7221
Episode: 5584 Total reward: 15.0 Training loss: 0.0515 Explore P: 0.7221
Episode: 5585 Total reward: 28.0 Training loss: 0.0152 Explore P: 0.7221
Episode: 5586 Total reward: 19.0 Training loss: 0.7478 Explore P: 0.7220
Episode: 5587 Total reward: 24.0 Training loss: 0.1258 Explore P: 0.7220
Episode: 5588 Total reward: 20.0 Training loss: 2.3951 Explore P: 0.7220
Episode: 5589 Total reward: 10.0 Training loss: 1.4501 Explore P: 0.7220
Episode: 5590 Total reward: 23.0 Training loss: 1.0889 Explore P: 0.7219
Episode: 5591 Total reward: 61.0 Training loss: 5.5943 Explore P: 0.7219
Episode: 5592 Total reward: 15.0 Training loss: 0.1870 Explore P: 0.7218
Episode: 5593 Total reward: 10.0 Training loss: 0.0085 Explore P: 0.7218
Episode: 5594 Total reward: 40.0 Training loss: 0.1263 Explore P: 0.7218
Episode: 5595 Total reward: 19.0 Training loss: 0.9443 Explore P: 0.7217
Episode: 5596 Total reward: 13.0 Training loss: 0.0760 Explore P: 0.7217
Episode: 5597 Total reward: 13.0 Training loss: 0.1258 Explore P: 0.7217
Episode: 5598 Total reward: 53.0 Training loss: 12.0994 Explore P: 0.7216
Episode: 5599 Total reward: 15.0 Training loss: 1.1591 Explore P: 0.7216
Episode: 5600 Total reward: 43.0 Training loss: 1.1315 Explore P: 0.7215
Episode: 5601 Total reward: 34.0 Training loss: 0.4220 Explore P: 0.7215
Episode: 5602 Total reward: 18.0 Training loss: 34.1735 Explore P: 0.7215
Episode: 5603 Total reward: 38.0 Training loss: 0.8856 Explore P: 0.7214
Episode: 5604 Total reward: 25.0 Training loss: 0.3788 Explore P: 0.7214
Episode: 5605 Total reward: 25.0 Training loss: 0.3149 Explore P: 0.7213
Episode: 5606 Total reward: 12.0 Training loss: 28.8842 Explore P: 0.7213
Episode: 5607 Total reward: 10.0 Training loss: 2.7494 Explore P: 0.7213
Episode: 5608 Total reward: 9.0 Training loss: 0.7998 Explore P: 0.7213
Episode: 5609 Total reward: 16.0 Training loss: 9.1741 Explore P: 0.7213
Episode: 5610 Total reward: 18.0 Training loss: 0.1894 Explore P: 0.7212
Episode: 5611 Total reward: 13.0 Training loss: 0.4610 Explore P: 0.7212
Episode: 5612 Total reward: 12.0 Training loss: 1.7120 Explore P: 0.7212
Episode: 5613 Total reward: 17.0 Training loss: 0.1346 Explore P: 0.7212
Episode: 5614 Total reward: 41.0 Training loss: 0.1398 Explore P: 0.7211
Episode: 5615 Total reward: 10.0 Training loss: 1.4039 Explore P: 0.7211
Episode: 5616 Total reward: 21.0 Training loss: 0.7864 Explore P: 0.7211
Episode: 5617 Total reward: 22.0 Training loss: 1.7170 Explore P: 0.7211
Episode: 5618 Total reward: 33.0 Training loss: 0.0694 Explore P: 0.7210
Episode: 5619 Total reward: 11.0 Training loss: 0.0241 Explore P: 0.7210
Episode: 5620 Total reward: 9.0 Training loss: 4.0952 Explore P: 0.7210
Episode: 5621 Total reward: 13.0 Training loss: 0.0787 Explore P: 0.7210
Episode: 5622 Total reward: 16.0 Training loss: 0.1819 Explore P: 0.7209
Episode: 5623 Total reward: 47.0 Training loss: 1.2060 Explore P: 0.7209
Episode: 5624 Total reward: 15.0 Training loss: 19.4188 Explore P: 0.7208
Episode: 5625 Total reward: 23.0 Training loss: 0.2121 Explore P: 0.7208
Episode: 5626 Total reward: 33.0 Training loss: 1.6949 Explore P: 0.7208
Episode: 5627 Total reward: 23.0 Training loss: 62.5303 Explore P: 0.7207
Episode: 5628 Total reward: 9.0 Training loss: 1.1319 Explore P: 0.7207
Episode: 5629 Total reward: 14.0 Training loss: 0.0291 Explore P: 0.7207
Episode: 5630 Total reward: 13.0 Training loss: 0.5927 Explore P: 0.7207
Episode: 5631 Total reward: 37.0 Training loss: 0.0522 Explore P: 0.7206
Episode: 5632 Total reward: 40.0 Training loss: 0.1610 Explore P: 0.7206
Episode: 5633 Total reward: 20.0 Training loss: 1.5328 Explore P: 0.7205
Episode: 5634 Total reward: 34.0 Training loss: 0.5025 Explore P: 0.7205
Episode: 5635 Total reward: 20.0 Training loss: 1.1833 Explore P: 0.7205
Episode: 5636 Total reward: 16.0 Training loss: 0.9525 Explore P: 0.7204
Episode: 5637 Total reward: 15.0 Training loss: 1.7793 Explore P: 0.7204
Episode: 5638 Total reward: 25.0 Training loss: 0.3415 Explore P: 0.7204
Episode: 5639 Total reward: 22.0 Training loss: 0.0064 Explore P: 0.7204
Episode: 5640 Total reward: 35.0 Training loss: 0.9938 Explore P: 0.7203
Episode: 5641 Total reward: 18.0 Training loss: 0.0178 Explore P: 0.7203
Episode: 5642 Total reward: 20.0 Training loss: 5.1420 Explore P: 0.7203
Episode: 5643 Total reward: 12.0 Training loss: 1.5227 Explore P: 0.7202
Episode: 5644 Total reward: 16.0 Training loss: 2.3527 Explore P: 0.7202
Episode: 5645 Total reward: 18.0 Training loss: 0.0497 Explore P: 0.7202
Episode: 5646 Total reward: 18.0 Training loss: 4.3291 Explore P: 0.7202
Episode: 5647 Total reward: 11.0 Training loss: 0.9232 Explore P: 0.7201
Episode: 5648 Total reward: 20.0 Training loss: 2.7946 Explore P: 0.7201
Episode: 5649 Total reward: 19.0 Training loss: 4.8352 Explore P: 0.7201
Episode: 5650 Total reward: 35.0 Training loss: 0.1538 Explore P: 0.7200
Episode: 5651 Total reward: 15.0 Training loss: 6.7119 Explore P: 0.7200
Episode: 5652 Total reward: 36.0 Training loss: 4.3464 Explore P: 0.7200
Episode: 5653 Total reward: 12.0 Training loss: 13.5978 Explore P: 0.7200
Episode: 5654 Total reward: 14.0 Training loss: 0.5687 Explore P: 0.7199
Episode: 5655 Total reward: 13.0 Training loss: 0.3178 Explore P: 0.7199
Episode: 5656 Total reward: 10.0 Training loss: 2.2210 Explore P: 0.7199
Episode: 5657 Total reward: 17.0 Training loss: 0.1653 Explore P: 0.7199
Episode: 5658 Total reward: 35.0 Training loss: 1.0719 Explore P: 0.7198
Episode: 5659 Total reward: 16.0 Training loss: 0.0505 Explore P: 0.7198
Episode: 5660 Total reward: 31.0 Training loss: 0.5800 Explore P: 0.7198
Episode: 5661 Total reward: 11.0 Training loss: 0.0332 Explore P: 0.7197
Episode: 5662 Total reward: 17.0 Training loss: 0.8853 Explore P: 0.7197
Episode: 5663 Total reward: 18.0 Training loss: 0.3530 Explore P: 0.7197
Episode: 5664 Total reward: 32.0 Training loss: 0.5377 Explore P: 0.7196
Episode: 5665 Total reward: 8.0 Training loss: 2.9925 Explore P: 0.7196
Episode: 5666 Total reward: 27.0 Training loss: 2.5782 Explore P: 0.7196
Episode: 5667 Total reward: 17.0 Training loss: 3.6170 Explore P: 0.7196
Episode: 5668 Total reward: 28.0 Training loss: 4.4517 Explore P: 0.7195
Episode: 5669 Total reward: 9.0 Training loss: 8.9143 Explore P: 0.7195
Episode: 5670 Total reward: 23.0 Training loss: 0.6756 Explore P: 0.7195
Episode: 5671 Total reward: 15.0 Training loss: 0.9095 Explore P: 0.7195
Episode: 5672 Total reward: 13.0 Training loss: 1.9676 Explore P: 0.7195
Episode: 5673 Total reward: 20.0 Training loss: 1.4836 Explore P: 0.7194
Episode: 5674 Total reward: 18.0 Training loss: 2.8703 Explore P: 0.7194
Episode: 5675 Total reward: 28.0 Training loss: 3.7284 Explore P: 0.7194
Episode: 5676 Total reward: 16.0 Training loss: 0.0597 Explore P: 0.7193
Episode: 5677 Total reward: 12.0 Training loss: 3.8098 Explore P: 0.7193
Episode: 5678 Total reward: 39.0 Training loss: 0.4292 Explore P: 0.7193
Episode: 5679 Total reward: 64.0 Training loss: 173.0081 Explore P: 0.7192
Episode: 5680 Total reward: 16.0 Training loss: 5.0521 Explore P: 0.7191
Episode: 5681 Total reward: 14.0 Training loss: 0.7799 Explore P: 0.7191
Episode: 5682 Total reward: 14.0 Training loss: 0.0287 Explore P: 0.7191
Episode: 5683 Total reward: 15.0 Training loss: 1.9745 Explore P: 0.7191
Episode: 5684 Total reward: 22.0 Training loss: 0.8708 Explore P: 0.7191
Episode: 5685 Total reward: 16.0 Training loss: 0.9145 Explore P: 0.7190
Episode: 5686 Total reward: 20.0 Training loss: 0.5802 Explore P: 0.7190
Episode: 5687 Total reward: 11.0 Training loss: 1.5696 Explore P: 0.7190
Episode: 5688 Total reward: 24.0 Training loss: 0.0731 Explore P: 0.7190
Episode: 5689 Total reward: 24.0 Training loss: 11.0884 Explore P: 0.7189
Episode: 5690 Total reward: 29.0 Training loss: 0.1157 Explore P: 0.7189
Episode: 5691 Total reward: 20.0 Training loss: 0.0995 Explore P: 0.7189
Episode: 5692 Total reward: 19.0 Training loss: 0.5916 Explore P: 0.7188
Episode: 5693 Total reward: 59.0 Training loss: 3.0363 Explore P: 0.7187
Episode: 5694 Total reward: 12.0 Training loss: 4.3101 Explore P: 0.7187
Episode: 5695 Total reward: 14.0 Training loss: 1.4207 Explore P: 0.7187
Episode: 5696 Total reward: 17.0 Training loss: 48.5532 Explore P: 0.7187
Episode: 5697 Total reward: 11.0 Training loss: 0.3279 Explore P: 0.7187
Episode: 5698 Total reward: 27.0 Training loss: 0.0444 Explore P: 0.7186
Episode: 5699 Total reward: 18.0 Training loss: 2.4364 Explore P: 0.7186
Episode: 5700 Total reward: 17.0 Training loss: 1.7253 Explore P: 0.7186
Episode: 5701 Total reward: 10.0 Training loss: 4.7572 Explore P: 0.7186
Episode: 5702 Total reward: 15.0 Training loss: 2.6705 Explore P: 0.7185
Episode: 5703 Total reward: 28.0 Training loss: 1.5832 Explore P: 0.7185
Episode: 5704 Total reward: 46.0 Training loss: 2.3985 Explore P: 0.7184
Episode: 5705 Total reward: 26.0 Training loss: 0.3416 Explore P: 0.7184
Episode: 5706 Total reward: 58.0 Training loss: 0.3971 Explore P: 0.7183
Episode: 5707 Total reward: 10.0 Training loss: 1.3729 Explore P: 0.7183
Episode: 5708 Total reward: 10.0 Training loss: 1.3380 Explore P: 0.7183
Episode: 5709 Total reward: 38.0 Training loss: 0.1327 Explore P: 0.7182
Episode: 5710 Total reward: 9.0 Training loss: 0.4470 Explore P: 0.7182
Episode: 5711 Total reward: 15.0 Training loss: 0.0330 Explore P: 0.7182
Episode: 5712 Total reward: 17.0 Training loss: 0.0765 Explore P: 0.7182
Episode: 5713 Total reward: 44.0 Training loss: 0.9277 Explore P: 0.7181
Episode: 5714 Total reward: 20.0 Training loss: 0.1092 Explore P: 0.7181
Episode: 5715 Total reward: 14.0 Training loss: 0.0642 Explore P: 0.7181
Episode: 5716 Total reward: 29.0 Training loss: 5.1451 Explore P: 0.7180
Episode: 5717 Total reward: 33.0 Training loss: 2.0123 Explore P: 0.7180
Episode: 5718 Total reward: 26.0 Training loss: 0.1081 Explore P: 0.7179
Episode: 5719 Total reward: 23.0 Training loss: 70.3867 Explore P: 0.7179
Episode: 5720 Total reward: 23.0 Training loss: 1.4560 Explore P: 0.7179
Episode: 5721 Total reward: 79.0 Training loss: 11.7568 Explore P: 0.7178
Episode: 5722 Total reward: 39.0 Training loss: 3.6311 Explore P: 0.7177
Episode: 5723 Total reward: 8.0 Training loss: 1.9766 Explore P: 0.7177
Episode: 5724 Total reward: 24.0 Training loss: 0.0640 Explore P: 0.7177
Episode: 5725 Total reward: 27.0 Training loss: 0.0926 Explore P: 0.7176
Episode: 5726 Total reward: 31.0 Training loss: 1.4912 Explore P: 0.7176
Episode: 5727 Total reward: 16.0 Training loss: 0.5428 Explore P: 0.7176
Episode: 5728 Total reward: 12.0 Training loss: 0.7829 Explore P: 0.7175
Episode: 5729 Total reward: 34.0 Training loss: 8.7154 Explore P: 0.7175
Episode: 5730 Total reward: 72.0 Training loss: 0.4135 Explore P: 0.7174
Episode: 5731 Total reward: 10.0 Training loss: 0.3278 Explore P: 0.7174
Episode: 5732 Total reward: 15.0 Training loss: 0.1435 Explore P: 0.7174
Episode: 5733 Total reward: 22.0 Training loss: 1.0917 Explore P: 0.7173
Episode: 5734 Total reward: 20.0 Training loss: 0.2350 Explore P: 0.7173
Episode: 5735 Total reward: 21.0 Training loss: 0.2864 Explore P: 0.7173
Episode: 5736 Total reward: 21.0 Training loss: 0.0096 Explore P: 0.7172
Episode: 5737 Total reward: 11.0 Training loss: 0.8542 Explore P: 0.7172
Episode: 5738 Total reward: 30.0 Training loss: 4.8491 Explore P: 0.7172
Episode: 5739 Total reward: 13.0 Training loss: 0.0527 Explore P: 0.7172
Episode: 5740 Total reward: 25.0 Training loss: 0.2591 Explore P: 0.7171
Episode: 5741 Total reward: 12.0 Training loss: 0.5570 Explore P: 0.7171
Episode: 5742 Total reward: 25.0 Training loss: 10.6343 Explore P: 0.7171
Episode: 5743 Total reward: 39.0 Training loss: 0.5328 Explore P: 0.7170
Episode: 5744 Total reward: 31.0 Training loss: 55.1445 Explore P: 0.7170
Episode: 5745 Total reward: 15.0 Training loss: 0.9482 Explore P: 0.7170
Episode: 5746 Total reward: 10.0 Training loss: 3.3438 Explore P: 0.7169
Episode: 5747 Total reward: 10.0 Training loss: 0.1503 Explore P: 0.7169
Episode: 5748 Total reward: 11.0 Training loss: 0.0068 Explore P: 0.7169
Episode: 5749 Total reward: 20.0 Training loss: 0.5026 Explore P: 0.7169
Episode: 5750 Total reward: 34.0 Training loss: 2.6170 Explore P: 0.7168
Episode: 5751 Total reward: 19.0 Training loss: 0.1422 Explore P: 0.7168
Episode: 5752 Total reward: 11.0 Training loss: 3.0961 Explore P: 0.7168
Episode: 5753 Total reward: 8.0 Training loss: 0.7584 Explore P: 0.7168
Episode: 5754 Total reward: 34.0 Training loss: 0.0581 Explore P: 0.7167
Episode: 5755 Total reward: 21.0 Training loss: 0.0886 Explore P: 0.7167
Episode: 5756 Total reward: 16.0 Training loss: 0.0845 Explore P: 0.7167
Episode: 5757 Total reward: 25.0 Training loss: 0.8533 Explore P: 0.7166
Episode: 5758 Total reward: 20.0 Training loss: 0.0941 Explore P: 0.7166
Episode: 5759 Total reward: 19.0 Training loss: 1.7820 Explore P: 0.7166
Episode: 5760 Total reward: 34.0 Training loss: 0.0499 Explore P: 0.7165
Episode: 5761 Total reward: 10.0 Training loss: 0.0330 Explore P: 0.7165
Episode: 5762 Total reward: 20.0 Training loss: 2.8861 Explore P: 0.7165
Episode: 5763 Total reward: 25.0 Training loss: 2.3265 Explore P: 0.7165
Episode: 5764 Total reward: 11.0 Training loss: 2.7346 Explore P: 0.7164
Episode: 5765 Total reward: 18.0 Training loss: 1.4722 Explore P: 0.7164
Episode: 5766 Total reward: 14.0 Training loss: 4.3195 Explore P: 0.7164
Episode: 5767 Total reward: 13.0 Training loss: 0.4170 Explore P: 0.7164
Episode: 5768 Total reward: 45.0 Training loss: 0.9610 Explore P: 0.7163
Episode: 5769 Total reward: 9.0 Training loss: 0.1669 Explore P: 0.7163
Episode: 5770 Total reward: 18.0 Training loss: 0.1186 Explore P: 0.7163
Episode: 5771 Total reward: 21.0 Training loss: 10.2882 Explore P: 0.7163
Episode: 5772 Total reward: 13.0 Training loss: 1.6891 Explore P: 0.7162
Episode: 5773 Total reward: 10.0 Training loss: 6.8628 Explore P: 0.7162
Episode: 5774 Total reward: 16.0 Training loss: 0.6668 Explore P: 0.7162
Episode: 5775 Total reward: 11.0 Training loss: 3.9758 Explore P: 0.7162
Episode: 5776 Total reward: 13.0 Training loss: 0.0801 Explore P: 0.7162
Episode: 5777 Total reward: 42.0 Training loss: 3.1956 Explore P: 0.7161
Episode: 5778 Total reward: 16.0 Training loss: 0.6483 Explore P: 0.7161
Episode: 5779 Total reward: 13.0 Training loss: 0.3893 Explore P: 0.7161
Episode: 5780 Total reward: 62.0 Training loss: 0.2758 Explore P: 0.7160
Episode: 5781 Total reward: 10.0 Training loss: 0.0239 Explore P: 0.7160
Episode: 5782 Total reward: 10.0 Training loss: 0.0874 Explore P: 0.7159
Episode: 5783 Total reward: 28.0 Training loss: 0.4662 Explore P: 0.7159
Episode: 5784 Total reward: 10.0 Training loss: 1.8267 Explore P: 0.7159
Episode: 5785 Total reward: 11.0 Training loss: 0.4032 Explore P: 0.7159
Episode: 5786 Total reward: 48.0 Training loss: 0.5779 Explore P: 0.7158
Episode: 5787 Total reward: 22.0 Training loss: 0.0312 Explore P: 0.7158
Episode: 5788 Total reward: 26.0 Training loss: 510.3427 Explore P: 0.7157
Episode: 5789 Total reward: 32.0 Training loss: 0.3493 Explore P: 0.7157
Episode: 5790 Total reward: 15.0 Training loss: 0.0402 Explore P: 0.7157
Episode: 5791 Total reward: 22.0 Training loss: 1.4110 Explore P: 0.7156
Episode: 5792 Total reward: 9.0 Training loss: 0.0850 Explore P: 0.7156
Episode: 5793 Total reward: 11.0 Training loss: 1.6762 Explore P: 0.7156
Episode: 5794 Total reward: 10.0 Training loss: 0.4688 Explore P: 0.7156
Episode: 5795 Total reward: 19.0 Training loss: 0.5121 Explore P: 0.7156
Episode: 5796 Total reward: 15.0 Training loss: 5.3902 Explore P: 0.7156
Episode: 5797 Total reward: 12.0 Training loss: 1.2320 Explore P: 0.7155
Episode: 5798 Total reward: 20.0 Training loss: 0.9943 Explore P: 0.7155
Episode: 5799 Total reward: 25.0 Training loss: 0.0428 Explore P: 0.7155
Episode: 5800 Total reward: 12.0 Training loss: 0.0578 Explore P: 0.7155
Episode: 5801 Total reward: 15.0 Training loss: 0.9868 Explore P: 0.7154
Episode: 5802 Total reward: 55.0 Training loss: 3.3703 Explore P: 0.7154
Episode: 5803 Total reward: 17.0 Training loss: 0.1256 Explore P: 0.7153
Episode: 5804 Total reward: 19.0 Training loss: 1.8420 Explore P: 0.7153
Episode: 5805 Total reward: 39.0 Training loss: 1.8149 Explore P: 0.7153
Episode: 5806 Total reward: 22.0 Training loss: 0.4203 Explore P: 0.7152
Episode: 5807 Total reward: 22.0 Training loss: 1.5380 Explore P: 0.7152
Episode: 5808 Total reward: 43.0 Training loss: 0.0646 Explore P: 0.7151
Episode: 5809 Total reward: 36.0 Training loss: 0.6646 Explore P: 0.7151
Episode: 5810 Total reward: 27.0 Training loss: 4.3206 Explore P: 0.7150
Episode: 5811 Total reward: 47.0 Training loss: 0.6974 Explore P: 0.7150
Episode: 5812 Total reward: 11.0 Training loss: 0.0262 Explore P: 0.7150
Episode: 5813 Total reward: 12.0 Training loss: 1.1554 Explore P: 0.7149
Episode: 5814 Total reward: 19.0 Training loss: 170.2634 Explore P: 0.7149
Episode: 5815 Total reward: 10.0 Training loss: 0.0570 Explore P: 0.7149
Episode: 5816 Total reward: 14.0 Training loss: 0.0289 Explore P: 0.7149
Episode: 5817 Total reward: 34.0 Training loss: 9.4565 Explore P: 0.7148
Episode: 5818 Total reward: 17.0 Training loss: 0.0581 Explore P: 0.7148
Episode: 5819 Total reward: 21.0 Training loss: 0.0864 Explore P: 0.7148
Episode: 5820 Total reward: 16.0 Training loss: 0.6940 Explore P: 0.7148
Episode: 5821 Total reward: 38.0 Training loss: 0.0549 Explore P: 0.7147
Episode: 5822 Total reward: 12.0 Training loss: 0.1238 Explore P: 0.7147
Episode: 5823 Total reward: 18.0 Training loss: 0.2261 Explore P: 0.7147
Episode: 5824 Total reward: 17.0 Training loss: 0.0272 Explore P: 0.7146
Episode: 5825 Total reward: 8.0 Training loss: 0.4347 Explore P: 0.7146
Episode: 5826 Total reward: 48.0 Training loss: 0.2790 Explore P: 0.7146
Episode: 5827 Total reward: 27.0 Training loss: 0.9865 Explore P: 0.7145
Episode: 5828 Total reward: 9.0 Training loss: 0.9496 Explore P: 0.7145
Episode: 5829 Total reward: 21.0 Training loss: 0.1863 Explore P: 0.7145
Episode: 5830 Total reward: 14.0 Training loss: 0.6879 Explore P: 0.7145
Episode: 5831 Total reward: 26.0 Training loss: 0.1561 Explore P: 0.7144
Episode: 5832 Total reward: 10.0 Training loss: 0.5360 Explore P: 0.7144
Episode: 5833 Total reward: 22.0 Training loss: 6.1084 Explore P: 0.7144
Episode: 5834 Total reward: 12.0 Training loss: 0.8038 Explore P: 0.7144
Episode: 5835 Total reward: 14.0 Training loss: 17.4841 Explore P: 0.7143
Episode: 5836 Total reward: 17.0 Training loss: 0.0896 Explore P: 0.7143
Episode: 5837 Total reward: 19.0 Training loss: 0.1302 Explore P: 0.7143
Episode: 5838 Total reward: 19.0 Training loss: 0.3333 Explore P: 0.7143
Episode: 5839 Total reward: 16.0 Training loss: 0.0228 Explore P: 0.7142
Episode: 5840 Total reward: 9.0 Training loss: 0.0732 Explore P: 0.7142
Episode: 5841 Total reward: 8.0 Training loss: 3.9403 Explore P: 0.7142
Episode: 5842 Total reward: 20.0 Training loss: 0.0537 Explore P: 0.7142
Episode: 5843 Total reward: 16.0 Training loss: 0.0439 Explore P: 0.7142
Episode: 5844 Total reward: 8.0 Training loss: 0.3154 Explore P: 0.7142
Episode: 5845 Total reward: 27.0 Training loss: 0.1221 Explore P: 0.7141
Episode: 5846 Total reward: 15.0 Training loss: 1.8042 Explore P: 0.7141
Episode: 5847 Total reward: 28.0 Training loss: 2.5250 Explore P: 0.7141
Episode: 5848 Total reward: 29.0 Training loss: 0.9378 Explore P: 0.7140
Episode: 5849 Total reward: 20.0 Training loss: 0.4446 Explore P: 0.7140
Episode: 5850 Total reward: 24.0 Training loss: 0.5299 Explore P: 0.7140
Episode: 5851 Total reward: 15.0 Training loss: 0.1312 Explore P: 0.7139
Episode: 5852 Total reward: 19.0 Training loss: 0.1554 Explore P: 0.7139
Episode: 5853 Total reward: 13.0 Training loss: 0.0393 Explore P: 0.7139
Episode: 5854 Total reward: 12.0 Training loss: 2.6188 Explore P: 0.7139
Episode: 5855 Total reward: 13.0 Training loss: 9.3659 Explore P: 0.7139
Episode: 5856 Total reward: 18.0 Training loss: 0.2392 Explore P: 0.7138
Episode: 5857 Total reward: 15.0 Training loss: 0.1147 Explore P: 0.7138
Episode: 5858 Total reward: 21.0 Training loss: 7.7727 Explore P: 0.7138
Episode: 5859 Total reward: 35.0 Training loss: 2.0393 Explore P: 0.7137
Episode: 5860 Total reward: 37.0 Training loss: 1.6681 Explore P: 0.7137
Episode: 5861 Total reward: 18.0 Training loss: 0.0277 Explore P: 0.7137
Episode: 5862 Total reward: 9.0 Training loss: 0.8992 Explore P: 0.7136
Episode: 5863 Total reward: 30.0 Training loss: 2.6251 Explore P: 0.7136
Episode: 5864 Total reward: 10.0 Training loss: 0.4280 Explore P: 0.7136
Episode: 5865 Total reward: 18.0 Training loss: 0.0362 Explore P: 0.7136
Episode: 5866 Total reward: 34.0 Training loss: 0.6968 Explore P: 0.7135
Episode: 5867 Total reward: 14.0 Training loss: 0.5524 Explore P: 0.7135
Episode: 5868 Total reward: 13.0 Training loss: 0.0479 Explore P: 0.7135
Episode: 5869 Total reward: 29.0 Training loss: 1.2976 Explore P: 0.7134
Episode: 5870 Total reward: 25.0 Training loss: 0.0605 Explore P: 0.7134
Episode: 5871 Total reward: 25.0 Training loss: 6.2604 Explore P: 0.7134
Episode: 5872 Total reward: 18.0 Training loss: 102.4268 Explore P: 0.7133
Episode: 5873 Total reward: 13.0 Training loss: 0.0322 Explore P: 0.7133
Episode: 5874 Total reward: 18.0 Training loss: 0.0066 Explore P: 0.7133
Episode: 5875 Total reward: 26.0 Training loss: 0.0109 Explore P: 0.7133
Episode: 5876 Total reward: 21.0 Training loss: 1.4179 Explore P: 0.7132
Episode: 5877 Total reward: 20.0 Training loss: 0.0623 Explore P: 0.7132
Episode: 5878 Total reward: 14.0 Training loss: 0.2828 Explore P: 0.7132
Episode: 5879 Total reward: 24.0 Training loss: 6.2846 Explore P: 0.7131
Episode: 5880 Total reward: 14.0 Training loss: 4.8368 Explore P: 0.7131
Episode: 5881 Total reward: 10.0 Training loss: 0.1816 Explore P: 0.7131
Episode: 5882 Total reward: 16.0 Training loss: 1.3705 Explore P: 0.7131
Episode: 5883 Total reward: 11.0 Training loss: 0.0827 Explore P: 0.7131
Episode: 5884 Total reward: 12.0 Training loss: 0.0249 Explore P: 0.7131
Episode: 5885 Total reward: 30.0 Training loss: 2.1891 Explore P: 0.7130
Episode: 5886 Total reward: 16.0 Training loss: 0.2297 Explore P: 0.7130
Episode: 5887 Total reward: 19.0 Training loss: 2.3968 Explore P: 0.7130
Episode: 5888 Total reward: 11.0 Training loss: 2.1031 Explore P: 0.7129
Episode: 5889 Total reward: 11.0 Training loss: 0.1067 Explore P: 0.7129
Episode: 5890 Total reward: 43.0 Training loss: 0.4638 Explore P: 0.7129
Episode: 5891 Total reward: 42.0 Training loss: 0.2464 Explore P: 0.7128
Episode: 5892 Total reward: 16.0 Training loss: 0.1534 Explore P: 0.7128
Episode: 5893 Total reward: 20.0 Training loss: 0.4586 Explore P: 0.7128
Episode: 5894 Total reward: 19.0 Training loss: 0.7233 Explore P: 0.7127
Episode: 5895 Total reward: 17.0 Training loss: 0.2432 Explore P: 0.7127
Episode: 5896 Total reward: 13.0 Training loss: 0.5772 Explore P: 0.7127
Episode: 5897 Total reward: 18.0 Training loss: 5.1136 Explore P: 0.7127
Episode: 5898 Total reward: 10.0 Training loss: 0.1622 Explore P: 0.7127
Episode: 5899 Total reward: 18.0 Training loss: 1.8028 Explore P: 0.7126
Episode: 5900 Total reward: 25.0 Training loss: 9.4713 Explore P: 0.7126
Episode: 5901 Total reward: 25.0 Training loss: 4.3854 Explore P: 0.7126
Episode: 5902 Total reward: 21.0 Training loss: 2.3242 Explore P: 0.7125
Episode: 5903 Total reward: 12.0 Training loss: 0.8025 Explore P: 0.7125
Episode: 5904 Total reward: 25.0 Training loss: 0.0284 Explore P: 0.7125
Episode: 5905 Total reward: 16.0 Training loss: 0.2246 Explore P: 0.7125
Episode: 5906 Total reward: 33.0 Training loss: 0.5994 Explore P: 0.7124
Episode: 5907 Total reward: 11.0 Training loss: 5.4904 Explore P: 0.7124
Episode: 5908 Total reward: 12.0 Training loss: 0.0600 Explore P: 0.7124
Episode: 5909 Total reward: 9.0 Training loss: 0.1015 Explore P: 0.7124
Episode: 5910 Total reward: 23.0 Training loss: 6.2464 Explore P: 0.7123
Episode: 5911 Total reward: 8.0 Training loss: 1.9226 Explore P: 0.7123
Episode: 5912 Total reward: 14.0 Training loss: 0.4964 Explore P: 0.7123
Episode: 5913 Total reward: 16.0 Training loss: 0.3388 Explore P: 0.7123
Episode: 5914 Total reward: 9.0 Training loss: 66.1467 Explore P: 0.7123
Episode: 5915 Total reward: 13.0 Training loss: 1.3742 Explore P: 0.7122
Episode: 5916 Total reward: 13.0 Training loss: 1.0165 Explore P: 0.7122
Episode: 5917 Total reward: 14.0 Training loss: 1.5922 Explore P: 0.7122
Episode: 5918 Total reward: 23.0 Training loss: 0.0155 Explore P: 0.7122
Episode: 5919 Total reward: 18.0 Training loss: 5.4019 Explore P: 0.7122
Episode: 5920 Total reward: 21.0 Training loss: 0.8517 Explore P: 0.7121
Episode: 5921 Total reward: 14.0 Training loss: 9.9513 Explore P: 0.7121
Episode: 5922 Total reward: 29.0 Training loss: 0.0654 Explore P: 0.7121
Episode: 5923 Total reward: 14.0 Training loss: 0.0106 Explore P: 0.7120
Episode: 5924 Total reward: 32.0 Training loss: 0.0480 Explore P: 0.7120
Episode: 5925 Total reward: 19.0 Training loss: 0.0797 Explore P: 0.7120
Episode: 5926 Total reward: 28.0 Training loss: 0.0992 Explore P: 0.7119
Episode: 5927 Total reward: 8.0 Training loss: 1.3400 Explore P: 0.7119
Episode: 5928 Total reward: 18.0 Training loss: 0.2310 Explore P: 0.7119
Episode: 5929 Total reward: 24.0 Training loss: 7.3165 Explore P: 0.7119
Episode: 5930 Total reward: 10.0 Training loss: 0.2209 Explore P: 0.7118
Episode: 5931 Total reward: 12.0 Training loss: 2.6232 Explore P: 0.7118
Episode: 5932 Total reward: 20.0 Training loss: 1.3507 Explore P: 0.7118
Episode: 5933 Total reward: 23.0 Training loss: 0.2164 Explore P: 0.7118
Episode: 5934 Total reward: 26.0 Training loss: 0.5201 Explore P: 0.7117
Episode: 5935 Total reward: 44.0 Training loss: 2.3888 Explore P: 0.7117
Episode: 5936 Total reward: 30.0 Training loss: 2.1281 Explore P: 0.7116
Episode: 5937 Total reward: 15.0 Training loss: 4.8035 Explore P: 0.7116
Episode: 5938 Total reward: 28.0 Training loss: 0.7930 Explore P: 0.7116
Episode: 5939 Total reward: 29.0 Training loss: 1.1960 Explore P: 0.7115
Episode: 5940 Total reward: 30.0 Training loss: 0.5488 Explore P: 0.7115
Episode: 5941 Total reward: 44.0 Training loss: 7.2087 Explore P: 0.7114
Episode: 5942 Total reward: 18.0 Training loss: 3.4616 Explore P: 0.7114
Episode: 5943 Total reward: 29.0 Training loss: 0.1070 Explore P: 0.7114
Episode: 5944 Total reward: 38.0 Training loss: 0.6537 Explore P: 0.7113
Episode: 5945 Total reward: 26.0 Training loss: 3.0464 Explore P: 0.7113
Episode: 5946 Total reward: 26.0 Training loss: 4.4343 Explore P: 0.7112
Episode: 5947 Total reward: 10.0 Training loss: 0.7501 Explore P: 0.7112
Episode: 5948 Total reward: 17.0 Training loss: 24.7544 Explore P: 0.7112
Episode: 5949 Total reward: 28.0 Training loss: 2.6705 Explore P: 0.7112
Episode: 5950 Total reward: 18.0 Training loss: 0.8550 Explore P: 0.7111
Episode: 5951 Total reward: 18.0 Training loss: 5.2375 Explore P: 0.7111
Episode: 5952 Total reward: 15.0 Training loss: 8.7215 Explore P: 0.7111
Episode: 5953 Total reward: 11.0 Training loss: 0.1215 Explore P: 0.7111
Episode: 5954 Total reward: 15.0 Training loss: 7.6699 Explore P: 0.7110
Episode: 5955 Total reward: 19.0 Training loss: 0.2362 Explore P: 0.7110
Episode: 5956 Total reward: 8.0 Training loss: 0.3541 Explore P: 0.7110
Episode: 5957 Total reward: 30.0 Training loss: 0.0119 Explore P: 0.7110
Episode: 5958 Total reward: 31.0 Training loss: 2.2561 Explore P: 0.7109
Episode: 5959 Total reward: 50.0 Training loss: 0.1277 Explore P: 0.7109
Episode: 5960 Total reward: 64.0 Training loss: 0.0258 Explore P: 0.7108
Episode: 5961 Total reward: 36.0 Training loss: 9.3128 Explore P: 0.7107
Episode: 5962 Total reward: 24.0 Training loss: 0.9612 Explore P: 0.7107
Episode: 5963 Total reward: 23.0 Training loss: 280.1772 Explore P: 0.7106
Episode: 5964 Total reward: 9.0 Training loss: 0.0423 Explore P: 0.7106
Episode: 5965 Total reward: 34.0 Training loss: 1.1074 Explore P: 0.7106
Episode: 5966 Total reward: 18.0 Training loss: 0.0466 Explore P: 0.7106
Episode: 5967 Total reward: 8.0 Training loss: 0.1299 Explore P: 0.7106
Episode: 5968 Total reward: 19.0 Training loss: 1.9175 Explore P: 0.7105
Episode: 5969 Total reward: 18.0 Training loss: 2.5660 Explore P: 0.7105
Episode: 5970 Total reward: 9.0 Training loss: 0.2019 Explore P: 0.7105
Episode: 5971 Total reward: 25.0 Training loss: 0.1201 Explore P: 0.7105
Episode: 5972 Total reward: 10.0 Training loss: 0.3485 Explore P: 0.7104
Episode: 5973 Total reward: 26.0 Training loss: 1.1424 Explore P: 0.7104
Episode: 5974 Total reward: 31.0 Training loss: 1.9907 Explore P: 0.7104
Episode: 5975 Total reward: 21.0 Training loss: 4.4886 Explore P: 0.7103
Episode: 5976 Total reward: 10.0 Training loss: 0.5911 Explore P: 0.7103
Episode: 5977 Total reward: 17.0 Training loss: 0.0488 Explore P: 0.7103
Episode: 5978 Total reward: 51.0 Training loss: 0.0346 Explore P: 0.7102
Episode: 5979 Total reward: 12.0 Training loss: 0.4433 Explore P: 0.7102
Episode: 5980 Total reward: 35.0 Training loss: 0.7628 Explore P: 0.7102
Episode: 5981 Total reward: 13.0 Training loss: 0.5726 Explore P: 0.7101
Episode: 5982 Total reward: 43.0 Training loss: 0.8120 Explore P: 0.7101
Episode: 5983 Total reward: 13.0 Training loss: 0.4748 Explore P: 0.7101
Episode: 5984 Total reward: 11.0 Training loss: 0.0391 Explore P: 0.7100
Episode: 5985 Total reward: 49.0 Training loss: 0.2072 Explore P: 0.7100
Episode: 5986 Total reward: 37.0 Training loss: 1.5024 Explore P: 0.7099
Episode: 5987 Total reward: 17.0 Training loss: 0.0352 Explore P: 0.7099
Episode: 5988 Total reward: 13.0 Training loss: 0.0373 Explore P: 0.7099
Episode: 5989 Total reward: 23.0 Training loss: 0.0611 Explore P: 0.7098
Episode: 5990 Total reward: 22.0 Training loss: 0.1085 Explore P: 0.7098
Episode: 5991 Total reward: 25.0 Training loss: 66.4336 Explore P: 0.7098
Episode: 5992 Total reward: 10.0 Training loss: 4.4716 Explore P: 0.7098
Episode: 5993 Total reward: 38.0 Training loss: 1.0453 Explore P: 0.7097
Episode: 5994 Total reward: 37.0 Training loss: 0.0131 Explore P: 0.7097
Episode: 5995 Total reward: 27.0 Training loss: 0.0234 Explore P: 0.7096
Episode: 5996 Total reward: 13.0 Training loss: 0.2327 Explore P: 0.7096
Episode: 5997 Total reward: 32.0 Training loss: 0.0701 Explore P: 0.7096
Episode: 5998 Total reward: 38.0 Training loss: 1.0867 Explore P: 0.7095
Episode: 5999 Total reward: 14.0 Training loss: 6.7736 Explore P: 0.7095
Episode: 6000 Total reward: 63.0 Training loss: 1.3327 Explore P: 0.7094
Episode: 6001 Total reward: 17.0 Training loss: 0.5805 Explore P: 0.7094
Episode: 6002 Total reward: 14.0 Training loss: 0.0325 Explore P: 0.7094
Episode: 6003 Total reward: 17.0 Training loss: 0.6074 Explore P: 0.7093
Episode: 6004 Total reward: 25.0 Training loss: 0.6354 Explore P: 0.7093
Episode: 6005 Total reward: 23.0 Training loss: 4.3881 Explore P: 0.7093
Episode: 6006 Total reward: 27.0 Training loss: 0.0059 Explore P: 0.7092
Episode: 6007 Total reward: 30.0 Training loss: 4.1844 Explore P: 0.7092
Episode: 6008 Total reward: 11.0 Training loss: 0.4970 Explore P: 0.7092
Episode: 6009 Total reward: 11.0 Training loss: 0.0242 Explore P: 0.7092
Episode: 6010 Total reward: 26.0 Training loss: 0.4675 Explore P: 0.7091
Episode: 6011 Total reward: 16.0 Training loss: 1.1042 Explore P: 0.7091
Episode: 6012 Total reward: 11.0 Training loss: 1.7252 Explore P: 0.7091
Episode: 6013 Total reward: 23.0 Training loss: 0.3359 Explore P: 0.7090
Episode: 6014 Total reward: 28.0 Training loss: 0.0106 Explore P: 0.7090
Episode: 6015 Total reward: 19.0 Training loss: 0.0550 Explore P: 0.7090
Episode: 6016 Total reward: 41.0 Training loss: 0.4119 Explore P: 0.7089
Episode: 6017 Total reward: 22.0 Training loss: 0.0516 Explore P: 0.7089
Episode: 6018 Total reward: 43.0 Training loss: 2.5923 Explore P: 0.7088
Episode: 6019 Total reward: 10.0 Training loss: 2.4826 Explore P: 0.7088
Episode: 6020 Total reward: 8.0 Training loss: 1.8864 Explore P: 0.7088
Episode: 6021 Total reward: 14.0 Training loss: 1.4198 Explore P: 0.7088
Episode: 6022 Total reward: 26.0 Training loss: 28.3377 Explore P: 0.7088
Episode: 6023 Total reward: 28.0 Training loss: 0.3052 Explore P: 0.7087
Episode: 6024 Total reward: 23.0 Training loss: 0.5382 Explore P: 0.7087
Episode: 6025 Total reward: 20.0 Training loss: 0.6382 Explore P: 0.7087
Episode: 6026 Total reward: 21.0 Training loss: 7.6996 Explore P: 0.7086
Episode: 6027 Total reward: 37.0 Training loss: 2.2866 Explore P: 0.7086
Episode: 6028 Total reward: 13.0 Training loss: 0.0539 Explore P: 0.7086
Episode: 6029 Total reward: 10.0 Training loss: 0.0547 Explore P: 0.7085
Episode: 6030 Total reward: 12.0 Training loss: 0.5291 Explore P: 0.7085
Episode: 6031 Total reward: 11.0 Training loss: 1.4224 Explore P: 0.7085
Episode: 6032 Total reward: 21.0 Training loss: 1.6673 Explore P: 0.7085
Episode: 6033 Total reward: 15.0 Training loss: 2.7282 Explore P: 0.7085
Episode: 6034 Total reward: 25.0 Training loss: 0.5465 Explore P: 0.7084
Episode: 6035 Total reward: 8.0 Training loss: 0.6509 Explore P: 0.7084
Episode: 6036 Total reward: 39.0 Training loss: 0.6703 Explore P: 0.7084
Episode: 6037 Total reward: 8.0 Training loss: 0.3929 Explore P: 0.7083
Episode: 6038 Total reward: 11.0 Training loss: 0.2551 Explore P: 0.7083
Episode: 6039 Total reward: 24.0 Training loss: 0.4981 Explore P: 0.7083
Episode: 6040 Total reward: 9.0 Training loss: 2.8994 Explore P: 0.7083
Episode: 6041 Total reward: 10.0 Training loss: 0.3803 Explore P: 0.7083
Episode: 6042 Total reward: 13.0 Training loss: 1.0014 Explore P: 0.7083
Episode: 6043 Total reward: 20.0 Training loss: 0.0886 Explore P: 0.7082
Episode: 6044 Total reward: 66.0 Training loss: 2.2020 Explore P: 0.7081
Episode: 6045 Total reward: 12.0 Training loss: 1.4787 Explore P: 0.7081
Episode: 6046 Total reward: 17.0 Training loss: 1.2944 Explore P: 0.7081
Episode: 6047 Total reward: 13.0 Training loss: 1.3486 Explore P: 0.7081
Episode: 6048 Total reward: 72.0 Training loss: 1.8899 Explore P: 0.7080
Episode: 6049 Total reward: 43.0 Training loss: 0.0562 Explore P: 0.7079
Episode: 6050 Total reward: 11.0 Training loss: 0.3000 Explore P: 0.7079
Episode: 6051 Total reward: 31.0 Training loss: 6.1039 Explore P: 0.7079
Episode: 6052 Total reward: 26.0 Training loss: 0.0518 Explore P: 0.7078
Episode: 6053 Total reward: 24.0 Training loss: 0.0562 Explore P: 0.7078
Episode: 6054 Total reward: 19.0 Training loss: 1.0618 Explore P: 0.7078
Episode: 6055 Total reward: 16.0 Training loss: 0.0620 Explore P: 0.7077
Episode: 6056 Total reward: 24.0 Training loss: 4.7055 Explore P: 0.7077
Episode: 6057 Total reward: 17.0 Training loss: 1.5813 Explore P: 0.7077
Episode: 6058 Total reward: 9.0 Training loss: 0.3895 Explore P: 0.7077
Episode: 6059 Total reward: 19.0 Training loss: 18.4349 Explore P: 0.7076
Episode: 6060 Total reward: 15.0 Training loss: 0.1234 Explore P: 0.7076
Episode: 6061 Total reward: 19.0 Training loss: 1.6597 Explore P: 0.7076
Episode: 6062 Total reward: 12.0 Training loss: 0.0358 Explore P: 0.7076
Episode: 6063 Total reward: 56.0 Training loss: 3.1877 Explore P: 0.7075
Episode: 6064 Total reward: 27.0 Training loss: 0.0059 Explore P: 0.7075
Episode: 6065 Total reward: 17.0 Training loss: 0.8888 Explore P: 0.7074
Episode: 6066 Total reward: 14.0 Training loss: 0.1496 Explore P: 0.7074
Episode: 6067 Total reward: 13.0 Training loss: 1.0230 Explore P: 0.7074
Episode: 6068 Total reward: 8.0 Training loss: 0.4136 Explore P: 0.7074
Episode: 6069 Total reward: 17.0 Training loss: 0.1198 Explore P: 0.7074
Episode: 6070 Total reward: 15.0 Training loss: 323.2475 Explore P: 0.7073
Episode: 6071 Total reward: 9.0 Training loss: 0.1065 Explore P: 0.7073
Episode: 6072 Total reward: 25.0 Training loss: 10.4352 Explore P: 0.7073
Episode: 6073 Total reward: 24.0 Training loss: 1.7991 Explore P: 0.7073
Episode: 6074 Total reward: 24.0 Training loss: 4.4906 Explore P: 0.7072
Episode: 6075 Total reward: 13.0 Training loss: 0.0926 Explore P: 0.7072
Episode: 6076 Total reward: 32.0 Training loss: 1.6412 Explore P: 0.7072
Episode: 6077 Total reward: 27.0 Training loss: 1.3872 Explore P: 0.7071
Episode: 6078 Total reward: 21.0 Training loss: 12.3246 Explore P: 0.7071
Episode: 6079 Total reward: 27.0 Training loss: 0.5935 Explore P: 0.7071
Episode: 6080 Total reward: 27.0 Training loss: 2.3027 Explore P: 0.7070
Episode: 6081 Total reward: 20.0 Training loss: 0.0239 Explore P: 0.7070
Episode: 6082 Total reward: 12.0 Training loss: 0.3207 Explore P: 0.7070
Episode: 6083 Total reward: 12.0 Training loss: 0.4015 Explore P: 0.7070
Episode: 6084 Total reward: 16.0 Training loss: 1.5666 Explore P: 0.7069
Episode: 6085 Total reward: 16.0 Training loss: 0.1203 Explore P: 0.7069
Episode: 6086 Total reward: 11.0 Training loss: 0.4375 Explore P: 0.7069
Episode: 6087 Total reward: 14.0 Training loss: 2.8969 Explore P: 0.7069
Episode: 6088 Total reward: 15.0 Training loss: 2.3279 Explore P: 0.7069
Episode: 6089 Total reward: 27.0 Training loss: 0.2781 Explore P: 0.7068
Episode: 6090 Total reward: 18.0 Training loss: 0.0447 Explore P: 0.7068
Episode: 6091 Total reward: 15.0 Training loss: 0.0268 Explore P: 0.7068
Episode: 6092 Total reward: 17.0 Training loss: 0.0199 Explore P: 0.7068
Episode: 6093 Total reward: 11.0 Training loss: 0.5536 Explore P: 0.7067
Episode: 6094 Total reward: 22.0 Training loss: 0.8644 Explore P: 0.7067
Episode: 6095 Total reward: 17.0 Training loss: 1.4344 Explore P: 0.7067
Episode: 6096 Total reward: 21.0 Training loss: 1.4195 Explore P: 0.7067
Episode: 6097 Total reward: 14.0 Training loss: 0.0936 Explore P: 0.7066
Episode: 6098 Total reward: 12.0 Training loss: 2.4876 Explore P: 0.7066
Episode: 6099 Total reward: 23.0 Training loss: 1.4505 Explore P: 0.7066
Episode: 6100 Total reward: 13.0 Training loss: 0.4380 Explore P: 0.7066
Episode: 6101 Total reward: 17.0 Training loss: 2.5711 Explore P: 0.7065
Episode: 6102 Total reward: 53.0 Training loss: 0.2736 Explore P: 0.7065
Episode: 6103 Total reward: 24.0 Training loss: 0.0619 Explore P: 0.7064
Episode: 6104 Total reward: 19.0 Training loss: 0.3302 Explore P: 0.7064
Episode: 6105 Total reward: 17.0 Training loss: 0.1934 Explore P: 0.7064
Episode: 6106 Total reward: 32.0 Training loss: 1.8345 Explore P: 0.7063
Episode: 6107 Total reward: 12.0 Training loss: 3.4037 Explore P: 0.7063
Episode: 6108 Total reward: 9.0 Training loss: 0.2497 Explore P: 0.7063
Episode: 6109 Total reward: 23.0 Training loss: 1.7328 Explore P: 0.7063
Episode: 6110 Total reward: 14.0 Training loss: 23.6543 Explore P: 0.7063
Episode: 6111 Total reward: 13.0 Training loss: 0.0469 Explore P: 0.7062
Episode: 6112 Total reward: 25.0 Training loss: 0.0894 Explore P: 0.7062
Episode: 6113 Total reward: 9.0 Training loss: 0.6139 Explore P: 0.7062
Episode: 6114 Total reward: 69.0 Training loss: 0.7788 Explore P: 0.7061
Episode: 6115 Total reward: 26.0 Training loss: 0.9275 Explore P: 0.7061
Episode: 6116 Total reward: 29.0 Training loss: 4.5171 Explore P: 0.7060
Episode: 6117 Total reward: 27.0 Training loss: 0.5054 Explore P: 0.7060
Episode: 6118 Total reward: 10.0 Training loss: 0.2555 Explore P: 0.7060
Episode: 6119 Total reward: 46.0 Training loss: 0.0625 Explore P: 0.7059
Episode: 6120 Total reward: 21.0 Training loss: 0.1752 Explore P: 0.7059
Episode: 6121 Total reward: 48.0 Training loss: 0.1775 Explore P: 0.7058
Episode: 6122 Total reward: 13.0 Training loss: 2.6578 Explore P: 0.7058
Episode: 6123 Total reward: 35.0 Training loss: 0.6849 Explore P: 0.7057
Episode: 6124 Total reward: 25.0 Training loss: 1.0555 Explore P: 0.7057
Episode: 6125 Total reward: 21.0 Training loss: 0.1096 Explore P: 0.7057
Episode: 6126 Total reward: 27.0 Training loss: 0.1423 Explore P: 0.7056
Episode: 6127 Total reward: 12.0 Training loss: 0.1462 Explore P: 0.7056
Episode: 6128 Total reward: 16.0 Training loss: 1.2116 Explore P: 0.7056
Episode: 6129 Total reward: 12.0 Training loss: 1.0175 Explore P: 0.7056
Episode: 6130 Total reward: 14.0 Training loss: 1.6123 Explore P: 0.7056
Episode: 6131 Total reward: 28.0 Training loss: 0.8802 Explore P: 0.7055
Episode: 6132 Total reward: 8.0 Training loss: 1.1299 Explore P: 0.7055
Episode: 6133 Total reward: 18.0 Training loss: 1.7509 Explore P: 0.7055
Episode: 6134 Total reward: 15.0 Training loss: 0.0254 Explore P: 0.7055
Episode: 6135 Total reward: 51.0 Training loss: 0.5494 Explore P: 0.7054
Episode: 6136 Total reward: 10.0 Training loss: 0.0313 Explore P: 0.7054
Episode: 6137 Total reward: 10.0 Training loss: 4.8493 Explore P: 0.7054
Episode: 6138 Total reward: 26.0 Training loss: 3.0768 Explore P: 0.7053
Episode: 6139 Total reward: 11.0 Training loss: 1.4265 Explore P: 0.7053
Episode: 6140 Total reward: 14.0 Training loss: 1.0099 Explore P: 0.7053
Episode: 6141 Total reward: 18.0 Training loss: 0.0464 Explore P: 0.7053
Episode: 6142 Total reward: 12.0 Training loss: 3.4389 Explore P: 0.7053
Episode: 6143 Total reward: 32.0 Training loss: 0.8275 Explore P: 0.7052
Episode: 6144 Total reward: 35.0 Training loss: 0.0040 Explore P: 0.7052
Episode: 6145 Total reward: 15.0 Training loss: 0.2754 Explore P: 0.7051
Episode: 6146 Total reward: 15.0 Training loss: 1.2425 Explore P: 0.7051
Episode: 6147 Total reward: 30.0 Training loss: 6.1636 Explore P: 0.7051
Episode: 6148 Total reward: 12.0 Training loss: 1.5980 Explore P: 0.7051
Episode: 6149 Total reward: 53.0 Training loss: 1.9821 Explore P: 0.7050
Episode: 6150 Total reward: 17.0 Training loss: 5.1774 Explore P: 0.7050
Episode: 6151 Total reward: 28.0 Training loss: 27.3891 Explore P: 0.7049
Episode: 6152 Total reward: 36.0 Training loss: 0.6098 Explore P: 0.7049
Episode: 6153 Total reward: 22.0 Training loss: 1.7945 Explore P: 0.7049
Episode: 6154 Total reward: 12.0 Training loss: 4.0764 Explore P: 0.7048
Episode: 6155 Total reward: 14.0 Training loss: 3.3769 Explore P: 0.7048
Episode: 6156 Total reward: 17.0 Training loss: 0.0130 Explore P: 0.7048
Episode: 6157 Total reward: 14.0 Training loss: 0.0940 Explore P: 0.7048
Episode: 6158 Total reward: 19.0 Training loss: 0.0077 Explore P: 0.7047
Episode: 6159 Total reward: 42.0 Training loss: 4.1616 Explore P: 0.7047
Episode: 6160 Total reward: 14.0 Training loss: 1.7257 Explore P: 0.7047
Episode: 6161 Total reward: 9.0 Training loss: 0.2900 Explore P: 0.7047
Episode: 6162 Total reward: 22.0 Training loss: 4.2133 Explore P: 0.7046
Episode: 6163 Total reward: 19.0 Training loss: 0.0958 Explore P: 0.7046
Episode: 6164 Total reward: 17.0 Training loss: 2.1224 Explore P: 0.7046
Episode: 6165 Total reward: 19.0 Training loss: 5.6023 Explore P: 0.7046
Episode: 6166 Total reward: 11.0 Training loss: 0.2641 Explore P: 0.7045
Episode: 6167 Total reward: 20.0 Training loss: 0.1084 Explore P: 0.7045
Episode: 6168 Total reward: 17.0 Training loss: 1.6636 Explore P: 0.7045
Episode: 6169 Total reward: 12.0 Training loss: 0.0957 Explore P: 0.7045
Episode: 6170 Total reward: 9.0 Training loss: 0.0561 Explore P: 0.7045
Episode: 6171 Total reward: 16.0 Training loss: 2.1188 Explore P: 0.7044
Episode: 6172 Total reward: 28.0 Training loss: 31.1999 Explore P: 0.7044
Episode: 6173 Total reward: 61.0 Training loss: 2.1743 Explore P: 0.7043
Episode: 6174 Total reward: 13.0 Training loss: 0.9795 Explore P: 0.7043
Episode: 6175 Total reward: 16.0 Training loss: 0.0483 Explore P: 0.7043
Episode: 6176 Total reward: 18.0 Training loss: 0.0334 Explore P: 0.7042
Episode: 6177 Total reward: 29.0 Training loss: 1.3514 Explore P: 0.7042
Episode: 6178 Total reward: 25.0 Training loss: 0.0798 Explore P: 0.7042
Episode: 6179 Total reward: 28.0 Training loss: 0.7121 Explore P: 0.7041
Episode: 6180 Total reward: 62.0 Training loss: 1.5018 Explore P: 0.7040
Episode: 6181 Total reward: 21.0 Training loss: 2.1504 Explore P: 0.7040
Episode: 6182 Total reward: 23.0 Training loss: 0.7681 Explore P: 0.7040
Episode: 6183 Total reward: 21.0 Training loss: 0.0978 Explore P: 0.7040
Episode: 6184 Total reward: 12.0 Training loss: 1.6726 Explore P: 0.7039
Episode: 6185 Total reward: 22.0 Training loss: 4.6284 Explore P: 0.7039
Episode: 6186 Total reward: 42.0 Training loss: 2.9901 Explore P: 0.7038
Episode: 6187 Total reward: 13.0 Training loss: 0.5943 Explore P: 0.7038
Episode: 6188 Total reward: 10.0 Training loss: 0.7737 Explore P: 0.7038
Episode: 6189 Total reward: 33.0 Training loss: 0.2939 Explore P: 0.7038
Episode: 6190 Total reward: 27.0 Training loss: 0.1301 Explore P: 0.7037
Episode: 6191 Total reward: 17.0 Training loss: 0.1991 Explore P: 0.7037
Episode: 6192 Total reward: 12.0 Training loss: 0.0474 Explore P: 0.7037
Episode: 6193 Total reward: 21.0 Training loss: 0.0056 Explore P: 0.7037
Episode: 6194 Total reward: 17.0 Training loss: 0.6898 Explore P: 0.7036
Episode: 6195 Total reward: 9.0 Training loss: 0.0651 Explore P: 0.7036
Episode: 6196 Total reward: 27.0 Training loss: 173.0463 Explore P: 0.7036
Episode: 6197 Total reward: 11.0 Training loss: 0.3820 Explore P: 0.7036
Episode: 6198 Total reward: 12.0 Training loss: 0.0761 Explore P: 0.7036
Episode: 6199 Total reward: 13.0 Training loss: 0.1265 Explore P: 0.7035
Episode: 6200 Total reward: 9.0 Training loss: 1.3988 Explore P: 0.7035
Episode: 6201 Total reward: 16.0 Training loss: 0.1392 Explore P: 0.7035
Episode: 6202 Total reward: 13.0 Training loss: 0.8523 Explore P: 0.7035
Episode: 6203 Total reward: 12.0 Training loss: 0.0265 Explore P: 0.7035
Episode: 6204 Total reward: 17.0 Training loss: 0.8550 Explore P: 0.7034
Episode: 6205 Total reward: 12.0 Training loss: 0.0466 Explore P: 0.7034
Episode: 6206 Total reward: 21.0 Training loss: 2.5992 Explore P: 0.7034
Episode: 6207 Total reward: 19.0 Training loss: 3.4922 Explore P: 0.7034
Episode: 6208 Total reward: 13.0 Training loss: 0.0534 Explore P: 0.7034
Episode: 6209 Total reward: 16.0 Training loss: 0.4815 Explore P: 0.7033
Episode: 6210 Total reward: 9.0 Training loss: 0.3248 Explore P: 0.7033
Episode: 6211 Total reward: 20.0 Training loss: 2.7682 Explore P: 0.7033
Episode: 6212 Total reward: 18.0 Training loss: 0.3090 Explore P: 0.7033
Episode: 6213 Total reward: 20.0 Training loss: 0.0274 Explore P: 0.7032
Episode: 6214 Total reward: 24.0 Training loss: 2.6268 Explore P: 0.7032
Episode: 6215 Total reward: 19.0 Training loss: 0.0174 Explore P: 0.7032
Episode: 6216 Total reward: 14.0 Training loss: 0.1280 Explore P: 0.7032
Episode: 6217 Total reward: 14.0 Training loss: 0.2298 Explore P: 0.7031
Episode: 6218 Total reward: 14.0 Training loss: 4.1766 Explore P: 0.7031
Episode: 6219 Total reward: 18.0 Training loss: 1.7112 Explore P: 0.7031
Episode: 6220 Total reward: 29.0 Training loss: 0.0434 Explore P: 0.7031
Episode: 6221 Total reward: 14.0 Training loss: 40.5119 Explore P: 0.7030
Episode: 6222 Total reward: 16.0 Training loss: 0.0138 Explore P: 0.7030
Episode: 6223 Total reward: 20.0 Training loss: 3.5786 Explore P: 0.7030
Episode: 6224 Total reward: 13.0 Training loss: 0.8159 Explore P: 0.7030
Episode: 6225 Total reward: 13.0 Training loss: 0.1700 Explore P: 0.7030
Episode: 6226 Total reward: 19.0 Training loss: 0.7434 Explore P: 0.7029
Episode: 6227 Total reward: 29.0 Training loss: 1.1620 Explore P: 0.7029
Episode: 6228 Total reward: 15.0 Training loss: 7.3561 Explore P: 0.7029
Episode: 6229 Total reward: 12.0 Training loss: 0.5817 Explore P: 0.7028
Episode: 6230 Total reward: 25.0 Training loss: 3.9289 Explore P: 0.7028
Episode: 6231 Total reward: 44.0 Training loss: 3.0206 Explore P: 0.7028
Episode: 6232 Total reward: 14.0 Training loss: 1.1136 Explore P: 0.7027
Episode: 6233 Total reward: 30.0 Training loss: 1.1696 Explore P: 0.7027
Episode: 6234 Total reward: 54.0 Training loss: 0.6749 Explore P: 0.7026
Episode: 6235 Total reward: 60.0 Training loss: 0.0476 Explore P: 0.7025
Episode: 6236 Total reward: 16.0 Training loss: 2.4053 Explore P: 0.7025
Episode: 6237 Total reward: 11.0 Training loss: 0.6339 Explore P: 0.7025
Episode: 6238 Total reward: 10.0 Training loss: 2.0213 Explore P: 0.7025
Episode: 6239 Total reward: 15.0 Training loss: 0.0330 Explore P: 0.7025
Episode: 6240 Total reward: 12.0 Training loss: 0.1741 Explore P: 0.7024
Episode: 6241 Total reward: 26.0 Training loss: 0.0076 Explore P: 0.7024
Episode: 6242 Total reward: 9.0 Training loss: 15.8875 Explore P: 0.7024
Episode: 6243 Total reward: 12.0 Training loss: 0.4006 Explore P: 0.7024
Episode: 6244 Total reward: 26.0 Training loss: 0.0233 Explore P: 0.7023
Episode: 6245 Total reward: 20.0 Training loss: 0.0154 Explore P: 0.7023
Episode: 6246 Total reward: 15.0 Training loss: 0.0656 Explore P: 0.7023
Episode: 6247 Total reward: 24.0 Training loss: 1.2380 Explore P: 0.7023
Episode: 6248 Total reward: 25.0 Training loss: 0.0352 Explore P: 0.7022
Episode: 6249 Total reward: 18.0 Training loss: 0.2611 Explore P: 0.7022
Episode: 6250 Total reward: 13.0 Training loss: 0.0939 Explore P: 0.7022
Episode: 6251 Total reward: 18.0 Training loss: 0.0517 Explore P: 0.7022
Episode: 6252 Total reward: 13.0 Training loss: 0.0340 Explore P: 0.7021
Episode: 6253 Total reward: 46.0 Training loss: 1.3479 Explore P: 0.7021
Episode: 6254 Total reward: 14.0 Training loss: 0.0785 Explore P: 0.7021
Episode: 6255 Total reward: 16.0 Training loss: 0.0253 Explore P: 0.7020
Episode: 6256 Total reward: 28.0 Training loss: 0.7607 Explore P: 0.7020
Episode: 6257 Total reward: 9.0 Training loss: 0.1150 Explore P: 0.7020
Episode: 6258 Total reward: 9.0 Training loss: 0.0135 Explore P: 0.7020
Episode: 6259 Total reward: 19.0 Training loss: 0.1224 Explore P: 0.7019
Episode: 6260 Total reward: 8.0 Training loss: 1.0673 Explore P: 0.7019
Episode: 6261 Total reward: 17.0 Training loss: 0.0131 Explore P: 0.7019
Episode: 6262 Total reward: 20.0 Training loss: 0.2319 Explore P: 0.7019
Episode: 6263 Total reward: 30.0 Training loss: 0.8372 Explore P: 0.7018
Episode: 6264 Total reward: 10.0 Training loss: 0.0895 Explore P: 0.7018
Episode: 6265 Total reward: 27.0 Training loss: 0.3685 Explore P: 0.7018
Episode: 6266 Total reward: 12.0 Training loss: 0.8719 Explore P: 0.7018
Episode: 6267 Total reward: 25.0 Training loss: 0.8607 Explore P: 0.7017
Episode: 6268 Total reward: 14.0 Training loss: 3.0278 Explore P: 0.7017
Episode: 6269 Total reward: 51.0 Training loss: 0.1808 Explore P: 0.7017
Episode: 6270 Total reward: 41.0 Training loss: 0.1145 Explore P: 0.7016
Episode: 6271 Total reward: 14.0 Training loss: 0.0091 Explore P: 0.7016
Episode: 6272 Total reward: 17.0 Training loss: 0.3540 Explore P: 0.7016
Episode: 6273 Total reward: 20.0 Training loss: 0.7876 Explore P: 0.7015
Episode: 6274 Total reward: 34.0 Training loss: 20.8818 Explore P: 0.7015
Episode: 6275 Total reward: 9.0 Training loss: 0.0086 Explore P: 0.7015
Episode: 6276 Total reward: 22.0 Training loss: 1.7366 Explore P: 0.7014
Episode: 6277 Total reward: 13.0 Training loss: 0.3458 Explore P: 0.7014
Episode: 6278 Total reward: 21.0 Training loss: 0.4824 Explore P: 0.7014
Episode: 6279 Total reward: 10.0 Training loss: 0.4157 Explore P: 0.7014
Episode: 6280 Total reward: 18.0 Training loss: 0.3033 Explore P: 0.7013
Episode: 6281 Total reward: 14.0 Training loss: 0.0963 Explore P: 0.7013
Episode: 6282 Total reward: 16.0 Training loss: 0.1276 Explore P: 0.7013
Episode: 6283 Total reward: 26.0 Training loss: 0.1461 Explore P: 0.7013
Episode: 6284 Total reward: 15.0 Training loss: 1.6375 Explore P: 0.7013
Episode: 6285 Total reward: 20.0 Training loss: 1.0300 Explore P: 0.7012
Episode: 6286 Total reward: 20.0 Training loss: 0.9929 Explore P: 0.7012
Episode: 6287 Total reward: 30.0 Training loss: 1.3409 Explore P: 0.7012
Episode: 6288 Total reward: 18.0 Training loss: 0.3794 Explore P: 0.7011
Episode: 6289 Total reward: 15.0 Training loss: 0.5314 Explore P: 0.7011
Episode: 6290 Total reward: 19.0 Training loss: 21.5295 Explore P: 0.7011
Episode: 6291 Total reward: 15.0 Training loss: 0.8233 Explore P: 0.7011
Episode: 6292 Total reward: 20.0 Training loss: 0.0484 Explore P: 0.7010
Episode: 6293 Total reward: 13.0 Training loss: 3.3700 Explore P: 0.7010
Episode: 6294 Total reward: 83.0 Training loss: 0.0472 Explore P: 0.7009
Episode: 6295 Total reward: 14.0 Training loss: 1.3484 Explore P: 0.7009
Episode: 6296 Total reward: 30.0 Training loss: 3.5844 Explore P: 0.7008
Episode: 6297 Total reward: 20.0 Training loss: 2.9707 Explore P: 0.7008
Episode: 6298 Total reward: 19.0 Training loss: 0.8461 Explore P: 0.7008
Episode: 6299 Total reward: 17.0 Training loss: 0.0064 Explore P: 0.7008
Episode: 6300 Total reward: 19.0 Training loss: 4.0592 Explore P: 0.7007
Episode: 6301 Total reward: 17.0 Training loss: 1.9659 Explore P: 0.7007
Episode: 6302 Total reward: 28.0 Training loss: 0.2745 Explore P: 0.7007
Episode: 6303 Total reward: 21.0 Training loss: 1.7232 Explore P: 0.7006
Episode: 6304 Total reward: 9.0 Training loss: 0.2059 Explore P: 0.7006
Episode: 6305 Total reward: 22.0 Training loss: 2.6787 Explore P: 0.7006
Episode: 6306 Total reward: 37.0 Training loss: 0.1371 Explore P: 0.7006
Episode: 6307 Total reward: 50.0 Training loss: 17.7177 Explore P: 0.7005
Episode: 6308 Total reward: 25.0 Training loss: 0.4913 Explore P: 0.7004
Episode: 6309 Total reward: 49.0 Training loss: 0.0332 Explore P: 0.7004
Episode: 6310 Total reward: 17.0 Training loss: 1.2061 Explore P: 0.7004
Episode: 6311 Total reward: 66.0 Training loss: 0.1780 Explore P: 0.7003
Episode: 6312 Total reward: 11.0 Training loss: 1.4643 Explore P: 0.7003
Episode: 6313 Total reward: 20.0 Training loss: 0.3300 Explore P: 0.7002
Episode: 6314 Total reward: 20.0 Training loss: 1.3529 Explore P: 0.7002
Episode: 6315 Total reward: 15.0 Training loss: 4.0838 Explore P: 0.7002
Episode: 6316 Total reward: 12.0 Training loss: 0.1253 Explore P: 0.7002
Episode: 6317 Total reward: 14.0 Training loss: 1.0218 Explore P: 0.7001
Episode: 6318 Total reward: 17.0 Training loss: 6.0685 Explore P: 0.7001
Episode: 6319 Total reward: 17.0 Training loss: 0.5839 Explore P: 0.7001
Episode: 6320 Total reward: 9.0 Training loss: 1.3870 Explore P: 0.7001
Episode: 6321 Total reward: 19.0 Training loss: 0.4657 Explore P: 0.7001
Episode: 6322 Total reward: 27.0 Training loss: 0.9956 Explore P: 0.7000
Episode: 6323 Total reward: 15.0 Training loss: 0.4655 Explore P: 0.7000
Episode: 6324 Total reward: 13.0 Training loss: 0.1714 Explore P: 0.7000
Episode: 6325 Total reward: 14.0 Training loss: 1.1421 Explore P: 0.7000
Episode: 6326 Total reward: 11.0 Training loss: 4.3089 Explore P: 0.6999
Episode: 6327 Total reward: 9.0 Training loss: 0.1139 Explore P: 0.6999
Episode: 6328 Total reward: 20.0 Training loss: 0.1632 Explore P: 0.6999
Episode: 6329 Total reward: 11.0 Training loss: 0.2210 Explore P: 0.6999
Episode: 6330 Total reward: 10.0 Training loss: 0.0434 Explore P: 0.6999
Episode: 6331 Total reward: 31.0 Training loss: 2.5115 Explore P: 0.6998
Episode: 6332 Total reward: 21.0 Training loss: 0.0795 Explore P: 0.6998
Episode: 6333 Total reward: 10.0 Training loss: 1.2168 Explore P: 0.6998
Episode: 6334 Total reward: 13.0 Training loss: 0.6726 Explore P: 0.6998
Episode: 6335 Total reward: 12.0 Training loss: 2.7188 Explore P: 0.6998
Episode: 6336 Total reward: 9.0 Training loss: 0.1090 Explore P: 0.6997
Episode: 6337 Total reward: 24.0 Training loss: 3.0790 Explore P: 0.6997
Episode: 6338 Total reward: 22.0 Training loss: 0.0409 Explore P: 0.6997
Episode: 6339 Total reward: 18.0 Training loss: 0.4268 Explore P: 0.6997
Episode: 6340 Total reward: 27.0 Training loss: 0.0824 Explore P: 0.6996
Episode: 6341 Total reward: 10.0 Training loss: 0.1029 Explore P: 0.6996
Episode: 6342 Total reward: 26.0 Training loss: 0.1162 Explore P: 0.6996
Episode: 6343 Total reward: 20.0 Training loss: 0.7154 Explore P: 0.6995
Episode: 6344 Total reward: 10.0 Training loss: 0.6933 Explore P: 0.6995
Episode: 6345 Total reward: 14.0 Training loss: 5.9413 Explore P: 0.6995
Episode: 6346 Total reward: 43.0 Training loss: 0.8138 Explore P: 0.6994
Episode: 6347 Total reward: 19.0 Training loss: 6.4975 Explore P: 0.6994
Episode: 6348 Total reward: 11.0 Training loss: 0.0454 Explore P: 0.6994
Episode: 6349 Total reward: 27.0 Training loss: 2.7258 Explore P: 0.6994
Episode: 6350 Total reward: 18.0 Training loss: 0.3862 Explore P: 0.6993
Episode: 6351 Total reward: 34.0 Training loss: 0.5025 Explore P: 0.6993
Episode: 6352 Total reward: 15.0 Training loss: 0.0718 Explore P: 0.6993
Episode: 6353 Total reward: 14.0 Training loss: 0.0882 Explore P: 0.6993
Episode: 6354 Total reward: 23.0 Training loss: 2.5056 Explore P: 0.6992
Episode: 6355 Total reward: 9.0 Training loss: 1.0397 Explore P: 0.6992
Episode: 6356 Total reward: 56.0 Training loss: 0.1622 Explore P: 0.6991
Episode: 6357 Total reward: 19.0 Training loss: 0.1701 Explore P: 0.6991
Episode: 6358 Total reward: 21.0 Training loss: 47.2011 Explore P: 0.6991
Episode: 6359 Total reward: 48.0 Training loss: 2.4664 Explore P: 0.6990
Episode: 6360 Total reward: 26.0 Training loss: 0.6248 Explore P: 0.6990
Episode: 6361 Total reward: 15.0 Training loss: 0.1004 Explore P: 0.6990
Episode: 6362 Total reward: 20.0 Training loss: 0.6886 Explore P: 0.6989
Episode: 6363 Total reward: 9.0 Training loss: 0.0669 Explore P: 0.6989
Episode: 6364 Total reward: 22.0 Training loss: 6.7765 Explore P: 0.6989
Episode: 6365 Total reward: 11.0 Training loss: 0.2457 Explore P: 0.6989
Episode: 6366 Total reward: 21.0 Training loss: 0.2644 Explore P: 0.6988
Episode: 6367 Total reward: 63.0 Training loss: 0.0745 Explore P: 0.6988
Episode: 6368 Total reward: 29.0 Training loss: 0.0159 Explore P: 0.6987
Episode: 6369 Total reward: 24.0 Training loss: 1.9372 Explore P: 0.6987
Episode: 6370 Total reward: 14.0 Training loss: 0.0831 Explore P: 0.6987
Episode: 6371 Total reward: 13.0 Training loss: 1.3896 Explore P: 0.6986
Episode: 6372 Total reward: 20.0 Training loss: 1.8773 Explore P: 0.6986
Episode: 6373 Total reward: 25.0 Training loss: 18.2469 Explore P: 0.6986
Episode: 6374 Total reward: 12.0 Training loss: 1.7798 Explore P: 0.6986
Episode: 6375 Total reward: 28.0 Training loss: 0.4810 Explore P: 0.6985
Episode: 6376 Total reward: 20.0 Training loss: 0.4026 Explore P: 0.6985
Episode: 6377 Total reward: 24.0 Training loss: 0.1013 Explore P: 0.6985
Episode: 6378 Total reward: 12.0 Training loss: 0.0236 Explore P: 0.6985
Episode: 6379 Total reward: 20.0 Training loss: 0.3214 Explore P: 0.6984
Episode: 6380 Total reward: 19.0 Training loss: 0.0206 Explore P: 0.6984
Episode: 6381 Total reward: 23.0 Training loss: 2.6180 Explore P: 0.6984
Episode: 6382 Total reward: 29.0 Training loss: 2.0604 Explore P: 0.6983
Episode: 6383 Total reward: 34.0 Training loss: 1.3644 Explore P: 0.6983
Episode: 6384 Total reward: 7.0 Training loss: 0.2199 Explore P: 0.6983
Episode: 6385 Total reward: 11.0 Training loss: 1.9165 Explore P: 0.6983
Episode: 6386 Total reward: 10.0 Training loss: 3.7606 Explore P: 0.6982
Episode: 6387 Total reward: 11.0 Training loss: 1.0635 Explore P: 0.6982
Episode: 6388 Total reward: 32.0 Training loss: 0.3030 Explore P: 0.6982
Episode: 6389 Total reward: 42.0 Training loss: 0.5977 Explore P: 0.6981
Episode: 6390 Total reward: 37.0 Training loss: 0.2513 Explore P: 0.6981
Episode: 6391 Total reward: 25.0 Training loss: 0.0867 Explore P: 0.6980
Episode: 6392 Total reward: 16.0 Training loss: 5.4647 Explore P: 0.6980
Episode: 6393 Total reward: 10.0 Training loss: 0.3900 Explore P: 0.6980
Episode: 6394 Total reward: 37.0 Training loss: 0.7089 Explore P: 0.6980
Episode: 6395 Total reward: 19.0 Training loss: 0.1010 Explore P: 0.6979
Episode: 6396 Total reward: 26.0 Training loss: 0.0764 Explore P: 0.6979
Episode: 6397 Total reward: 15.0 Training loss: 0.0266 Explore P: 0.6979
Episode: 6398 Total reward: 8.0 Training loss: 0.0213 Explore P: 0.6979
Episode: 6399 Total reward: 10.0 Training loss: 0.1109 Explore P: 0.6978
Episode: 6400 Total reward: 12.0 Training loss: 0.7048 Explore P: 0.6978
Episode: 6401 Total reward: 27.0 Training loss: 1.0848 Explore P: 0.6978
Episode: 6402 Total reward: 25.0 Training loss: 0.0469 Explore P: 0.6978
Episode: 6403 Total reward: 25.0 Training loss: 7.9451 Explore P: 0.6977
Episode: 6404 Total reward: 27.0 Training loss: 0.2521 Explore P: 0.6977
Episode: 6405 Total reward: 17.0 Training loss: 0.0564 Explore P: 0.6977
Episode: 6406 Total reward: 12.0 Training loss: 0.1110 Explore P: 0.6976
Episode: 6407 Total reward: 37.0 Training loss: 0.0948 Explore P: 0.6976
Episode: 6408 Total reward: 22.0 Training loss: 0.0576 Explore P: 0.6976
Episode: 6409 Total reward: 16.0 Training loss: 0.0472 Explore P: 0.6975
Episode: 6410 Total reward: 38.0 Training loss: 2.8317 Explore P: 0.6975
Episode: 6411 Total reward: 23.0 Training loss: 0.1741 Explore P: 0.6975
Episode: 6412 Total reward: 10.0 Training loss: 1.6134 Explore P: 0.6974
Episode: 6413 Total reward: 12.0 Training loss: 35.4183 Explore P: 0.6974
Episode: 6414 Total reward: 15.0 Training loss: 2.6342 Explore P: 0.6974
Episode: 6415 Total reward: 29.0 Training loss: 0.1251 Explore P: 0.6974
Episode: 6416 Total reward: 25.0 Training loss: 0.2201 Explore P: 0.6973
Episode: 6417 Total reward: 32.0 Training loss: 0.0491 Explore P: 0.6973
Episode: 6418 Total reward: 10.0 Training loss: 3.5240 Explore P: 0.6973
Episode: 6419 Total reward: 15.0 Training loss: 0.0103 Explore P: 0.6973
Episode: 6420 Total reward: 15.0 Training loss: 4.5063 Explore P: 0.6972
Episode: 6421 Total reward: 15.0 Training loss: 0.0405 Explore P: 0.6972
Episode: 6422 Total reward: 24.0 Training loss: 0.9801 Explore P: 0.6972
Episode: 6423 Total reward: 17.0 Training loss: 1.4469 Explore P: 0.6972
Episode: 6424 Total reward: 19.0 Training loss: 0.0110 Explore P: 0.6971
Episode: 6425 Total reward: 18.0 Training loss: 0.6340 Explore P: 0.6971
Episode: 6426 Total reward: 16.0 Training loss: 0.0625 Explore P: 0.6971
Episode: 6427 Total reward: 9.0 Training loss: 0.0803 Explore P: 0.6971
Episode: 6428 Total reward: 23.0 Training loss: 0.0735 Explore P: 0.6970
Episode: 6429 Total reward: 31.0 Training loss: 0.1177 Explore P: 0.6970
Episode: 6430 Total reward: 12.0 Training loss: 1.9741 Explore P: 0.6970
Episode: 6431 Total reward: 45.0 Training loss: 0.9300 Explore P: 0.6969
Episode: 6432 Total reward: 23.0 Training loss: 0.6295 Explore P: 0.6969
Episode: 6433 Total reward: 13.0 Training loss: 0.0547 Explore P: 0.6969
Episode: 6434 Total reward: 33.0 Training loss: 1.0082 Explore P: 0.6968
Episode: 6435 Total reward: 8.0 Training loss: 0.4146 Explore P: 0.6968
Episode: 6436 Total reward: 16.0 Training loss: 1.0370 Explore P: 0.6968
Episode: 6437 Total reward: 16.0 Training loss: 0.0482 Explore P: 0.6968
Episode: 6438 Total reward: 9.0 Training loss: 0.0146 Explore P: 0.6968
Episode: 6439 Total reward: 14.0 Training loss: 0.7043 Explore P: 0.6967
Episode: 6440 Total reward: 13.0 Training loss: 0.2075 Explore P: 0.6967
Episode: 6441 Total reward: 8.0 Training loss: 5.2285 Explore P: 0.6967
Episode: 6442 Total reward: 15.0 Training loss: 0.2823 Explore P: 0.6967
Episode: 6443 Total reward: 17.0 Training loss: 1.0263 Explore P: 0.6967
Episode: 6444 Total reward: 20.0 Training loss: 3.9551 Explore P: 0.6966
Episode: 6445 Total reward: 16.0 Training loss: 1.7574 Explore P: 0.6966
Episode: 6446 Total reward: 26.0 Training loss: 0.6266 Explore P: 0.6966
Episode: 6447 Total reward: 8.0 Training loss: 0.1436 Explore P: 0.6966
Episode: 6448 Total reward: 27.0 Training loss: 0.3748 Explore P: 0.6965
Episode: 6449 Total reward: 9.0 Training loss: 0.9687 Explore P: 0.6965
Episode: 6450 Total reward: 9.0 Training loss: 0.8122 Explore P: 0.6965
Episode: 6451 Total reward: 12.0 Training loss: 0.6166 Explore P: 0.6965
Episode: 6452 Total reward: 19.0 Training loss: 0.2313 Explore P: 0.6965
Episode: 6453 Total reward: 16.0 Training loss: 2.5776 Explore P: 0.6964
Episode: 6454 Total reward: 20.0 Training loss: 0.7653 Explore P: 0.6964
Episode: 6455 Total reward: 28.0 Training loss: 0.0260 Explore P: 0.6964
Episode: 6456 Total reward: 17.0 Training loss: 0.2788 Explore P: 0.6964
Episode: 6457 Total reward: 14.0 Training loss: 1.6661 Explore P: 0.6963
Episode: 6458 Total reward: 8.0 Training loss: 1.7586 Explore P: 0.6963
Episode: 6459 Total reward: 51.0 Training loss: 2.8188 Explore P: 0.6963
Episode: 6460 Total reward: 22.0 Training loss: 0.7669 Explore P: 0.6962
Episode: 6461 Total reward: 46.0 Training loss: 0.0027 Explore P: 0.6962
Episode: 6462 Total reward: 37.0 Training loss: 0.4188 Explore P: 0.6961
Episode: 6463 Total reward: 15.0 Training loss: 1.1818 Explore P: 0.6961
Episode: 6464 Total reward: 9.0 Training loss: 10.3753 Explore P: 0.6961
Episode: 6465 Total reward: 9.0 Training loss: 0.3291 Explore P: 0.6961
Episode: 6466 Total reward: 9.0 Training loss: 1.8354 Explore P: 0.6961
Episode: 6467 Total reward: 26.0 Training loss: 1.2323 Explore P: 0.6960
Episode: 6468 Total reward: 10.0 Training loss: 0.0655 Explore P: 0.6960
Episode: 6469 Total reward: 31.0 Training loss: 0.4215 Explore P: 0.6960
Episode: 6470 Total reward: 13.0 Training loss: 0.1107 Explore P: 0.6959
Episode: 6471 Total reward: 8.0 Training loss: 1.7201 Explore P: 0.6959
Episode: 6472 Total reward: 20.0 Training loss: 0.0550 Explore P: 0.6959
Episode: 6473 Total reward: 18.0 Training loss: 0.0266 Explore P: 0.6959
Episode: 6474 Total reward: 17.0 Training loss: 0.5831 Explore P: 0.6959
Episode: 6475 Total reward: 33.0 Training loss: 0.9116 Explore P: 0.6958
Episode: 6476 Total reward: 31.0 Training loss: 2.1044 Explore P: 0.6958
Episode: 6477 Total reward: 43.0 Training loss: 2.0336 Explore P: 0.6957
Episode: 6478 Total reward: 12.0 Training loss: 1.5084 Explore P: 0.6957
Episode: 6479 Total reward: 7.0 Training loss: 0.0611 Explore P: 0.6957
Episode: 6480 Total reward: 12.0 Training loss: 0.0457 Explore P: 0.6957
Episode: 6481 Total reward: 11.0 Training loss: 1.4810 Explore P: 0.6957
Episode: 6482 Total reward: 9.0 Training loss: 1.9156 Explore P: 0.6956
Episode: 6483 Total reward: 19.0 Training loss: 0.1242 Explore P: 0.6956
Episode: 6484 Total reward: 10.0 Training loss: 0.0908 Explore P: 0.6956
Episode: 6485 Total reward: 28.0 Training loss: 0.0302 Explore P: 0.6956
Episode: 6486 Total reward: 18.0 Training loss: 2.2652 Explore P: 0.6955
Episode: 6487 Total reward: 25.0 Training loss: 1.0753 Explore P: 0.6955
Episode: 6488 Total reward: 13.0 Training loss: 0.2085 Explore P: 0.6955
Episode: 6489 Total reward: 21.0 Training loss: 0.0737 Explore P: 0.6955
Episode: 6490 Total reward: 32.0 Training loss: 0.1164 Explore P: 0.6954
Episode: 6491 Total reward: 30.0 Training loss: 0.0278 Explore P: 0.6954
Episode: 6492 Total reward: 29.0 Training loss: 1.5504 Explore P: 0.6953
Episode: 6493 Total reward: 16.0 Training loss: 2.6740 Explore P: 0.6953
Episode: 6494 Total reward: 50.0 Training loss: 0.2845 Explore P: 0.6952
Episode: 6495 Total reward: 41.0 Training loss: 1.1468 Explore P: 0.6952
Episode: 6496 Total reward: 24.0 Training loss: 1.9201 Explore P: 0.6952
Episode: 6497 Total reward: 35.0 Training loss: 0.0674 Explore P: 0.6951
Episode: 6498 Total reward: 20.0 Training loss: 0.2736 Explore P: 0.6951
Episode: 6499 Total reward: 37.0 Training loss: 0.1377 Explore P: 0.6950
Episode: 6500 Total reward: 17.0 Training loss: 0.0831 Explore P: 0.6950
Episode: 6501 Total reward: 66.0 Training loss: 0.8671 Explore P: 0.6949
Episode: 6502 Total reward: 19.0 Training loss: 0.0607 Explore P: 0.6949
Episode: 6503 Total reward: 15.0 Training loss: 2.6822 Explore P: 0.6949
Episode: 6504 Total reward: 47.0 Training loss: 0.5422 Explore P: 0.6948
Episode: 6505 Total reward: 12.0 Training loss: 0.6505 Explore P: 0.6948
Episode: 6506 Total reward: 9.0 Training loss: 0.2130 Explore P: 0.6948
Episode: 6507 Total reward: 11.0 Training loss: 1.4060 Explore P: 0.6948
Episode: 6508 Total reward: 30.0 Training loss: 3.0759 Explore P: 0.6947
Episode: 6509 Total reward: 10.0 Training loss: 1.4610 Explore P: 0.6947
Episode: 6510 Total reward: 15.0 Training loss: 0.1874 Explore P: 0.6947
Episode: 6511 Total reward: 8.0 Training loss: 0.5790 Explore P: 0.6947
Episode: 6512 Total reward: 22.0 Training loss: 0.2110 Explore P: 0.6946
Episode: 6513 Total reward: 24.0 Training loss: 0.2463 Explore P: 0.6946
Episode: 6514 Total reward: 18.0 Training loss: 0.0149 Explore P: 0.6946
Episode: 6515 Total reward: 46.0 Training loss: 0.7537 Explore P: 0.6945
Episode: 6516 Total reward: 16.0 Training loss: 0.2202 Explore P: 0.6945
Episode: 6517 Total reward: 15.0 Training loss: 1.8877 Explore P: 0.6945
Episode: 6518 Total reward: 10.0 Training loss: 5.4760 Explore P: 0.6945
Episode: 6519 Total reward: 9.0 Training loss: 1.4621 Explore P: 0.6945
Episode: 6520 Total reward: 31.0 Training loss: 0.9906 Explore P: 0.6944
Episode: 6521 Total reward: 18.0 Training loss: 0.0847 Explore P: 0.6944
Episode: 6522 Total reward: 26.0 Training loss: 2.5769 Explore P: 0.6943
Episode: 6523 Total reward: 36.0 Training loss: 0.0925 Explore P: 0.6943
Episode: 6524 Total reward: 19.0 Training loss: 0.0641 Explore P: 0.6943
Episode: 6525 Total reward: 23.0 Training loss: 0.0741 Explore P: 0.6942
Episode: 6526 Total reward: 36.0 Training loss: 10.2538 Explore P: 0.6942
Episode: 6527 Total reward: 32.0 Training loss: 0.0124 Explore P: 0.6941
Episode: 6528 Total reward: 13.0 Training loss: 7.1346 Explore P: 0.6941
Episode: 6529 Total reward: 14.0 Training loss: 0.8663 Explore P: 0.6941
Episode: 6530 Total reward: 29.0 Training loss: 0.0109 Explore P: 0.6941
Episode: 6531 Total reward: 38.0 Training loss: 2.3368 Explore P: 0.6940
Episode: 6532 Total reward: 8.0 Training loss: 0.6122 Explore P: 0.6940
Episode: 6533 Total reward: 22.0 Training loss: 0.0498 Explore P: 0.6940
Episode: 6534 Total reward: 11.0 Training loss: 1.2892 Explore P: 0.6940
Episode: 6535 Total reward: 34.0 Training loss: 2.3990 Explore P: 0.6939
Episode: 6536 Total reward: 34.0 Training loss: 0.1768 Explore P: 0.6939
Episode: 6537 Total reward: 18.0 Training loss: 0.0212 Explore P: 0.6938
Episode: 6538 Total reward: 13.0 Training loss: 0.0220 Explore P: 0.6938
Episode: 6539 Total reward: 30.0 Training loss: 0.4307 Explore P: 0.6938
Episode: 6540 Total reward: 27.0 Training loss: 0.5822 Explore P: 0.6938
Episode: 6541 Total reward: 21.0 Training loss: 6.0987 Explore P: 0.6937
Episode: 6542 Total reward: 9.0 Training loss: 0.4407 Explore P: 0.6937
Episode: 6543 Total reward: 11.0 Training loss: 0.5260 Explore P: 0.6937
Episode: 6544 Total reward: 16.0 Training loss: 0.1407 Explore P: 0.6937
Episode: 6545 Total reward: 29.0 Training loss: 0.0413 Explore P: 0.6936
Episode: 6546 Total reward: 11.0 Training loss: 4.3104 Explore P: 0.6936
Episode: 6547 Total reward: 19.0 Training loss: 0.0660 Explore P: 0.6936
Episode: 6548 Total reward: 12.0 Training loss: 3.2494 Explore P: 0.6936
Episode: 6549 Total reward: 32.0 Training loss: 0.0111 Explore P: 0.6935
Episode: 6550 Total reward: 15.0 Training loss: 0.1737 Explore P: 0.6935
Episode: 6551 Total reward: 21.0 Training loss: 0.1086 Explore P: 0.6935
Episode: 6552 Total reward: 13.0 Training loss: 0.0091 Explore P: 0.6935
Episode: 6553 Total reward: 19.0 Training loss: 5.7918 Explore P: 0.6934
Episode: 6554 Total reward: 23.0 Training loss: 6.5984 Explore P: 0.6934
Episode: 6555 Total reward: 11.0 Training loss: 0.4480 Explore P: 0.6934
Episode: 6556 Total reward: 20.0 Training loss: 0.1479 Explore P: 0.6934
Episode: 6557 Total reward: 16.0 Training loss: 0.0792 Explore P: 0.6933
Episode: 6558 Total reward: 13.0 Training loss: 0.3751 Explore P: 0.6933
Episode: 6559 Total reward: 12.0 Training loss: 0.9753 Explore P: 0.6933
Episode: 6560 Total reward: 13.0 Training loss: 0.0236 Explore P: 0.6933
Episode: 6561 Total reward: 9.0 Training loss: 0.4490 Explore P: 0.6933
Episode: 6562 Total reward: 16.0 Training loss: 0.1810 Explore P: 0.6933
Episode: 6563 Total reward: 37.0 Training loss: 0.0059 Explore P: 0.6932
Episode: 6564 Total reward: 16.0 Training loss: 0.2634 Explore P: 0.6932
Episode: 6565 Total reward: 21.0 Training loss: 0.2525 Explore P: 0.6932
Episode: 6566 Total reward: 39.0 Training loss: 0.8400 Explore P: 0.6931
Episode: 6567 Total reward: 15.0 Training loss: 0.0652 Explore P: 0.6931
Episode: 6568 Total reward: 21.0 Training loss: 0.5509 Explore P: 0.6931
Episode: 6569 Total reward: 12.0 Training loss: 0.1099 Explore P: 0.6930
Episode: 6570 Total reward: 19.0 Training loss: 0.9753 Explore P: 0.6930
Episode: 6571 Total reward: 18.0 Training loss: 0.7256 Explore P: 0.6930
Episode: 6572 Total reward: 10.0 Training loss: 0.3486 Explore P: 0.6930
Episode: 6573 Total reward: 8.0 Training loss: 1.3345 Explore P: 0.6930
Episode: 6574 Total reward: 20.0 Training loss: 0.0825 Explore P: 0.6929
Episode: 6575 Total reward: 16.0 Training loss: 2.1195 Explore P: 0.6929
Episode: 6576 Total reward: 16.0 Training loss: 0.0673 Explore P: 0.6929
Episode: 6577 Total reward: 12.0 Training loss: 1.1379 Explore P: 0.6929
Episode: 6578 Total reward: 19.0 Training loss: 0.1820 Explore P: 0.6928
Episode: 6579 Total reward: 28.0 Training loss: 1.6005 Explore P: 0.6928
Episode: 6580 Total reward: 17.0 Training loss: 0.0403 Explore P: 0.6928
Episode: 6581 Total reward: 37.0 Training loss: 0.0785 Explore P: 0.6927
Episode: 6582 Total reward: 53.0 Training loss: 0.5253 Explore P: 0.6927
Episode: 6583 Total reward: 11.0 Training loss: 0.6594 Explore P: 0.6926
Episode: 6584 Total reward: 22.0 Training loss: 0.9537 Explore P: 0.6926
Episode: 6585 Total reward: 19.0 Training loss: 4.9413 Explore P: 0.6926
Episode: 6586 Total reward: 12.0 Training loss: 1.0427 Explore P: 0.6926
Episode: 6587 Total reward: 24.0 Training loss: 0.3544 Explore P: 0.6925
Episode: 6588 Total reward: 44.0 Training loss: 2.0557 Explore P: 0.6925
Episode: 6589 Total reward: 12.0 Training loss: 0.0589 Explore P: 0.6925
Episode: 6590 Total reward: 23.0 Training loss: 0.2633 Explore P: 0.6924
Episode: 6591 Total reward: 9.0 Training loss: 3.4772 Explore P: 0.6924
Episode: 6592 Total reward: 24.0 Training loss: 0.6627 Explore P: 0.6924
Episode: 6593 Total reward: 13.0 Training loss: 0.4864 Explore P: 0.6924
Episode: 6594 Total reward: 12.0 Training loss: 0.3716 Explore P: 0.6924
Episode: 6595 Total reward: 18.0 Training loss: 0.0870 Explore P: 0.6923
Episode: 6596 Total reward: 44.0 Training loss: 1.3299 Explore P: 0.6923
Episode: 6597 Total reward: 9.0 Training loss: 11.8390 Explore P: 0.6923
Episode: 6598 Total reward: 20.0 Training loss: 0.0532 Explore P: 0.6922
Episode: 6599 Total reward: 19.0 Training loss: 0.2156 Explore P: 0.6922
Episode: 6600 Total reward: 30.0 Training loss: 0.5637 Explore P: 0.6922
Episode: 6601 Total reward: 11.0 Training loss: 3.1074 Explore P: 0.6922
Episode: 6602 Total reward: 11.0 Training loss: 0.4255 Explore P: 0.6921
Episode: 6603 Total reward: 15.0 Training loss: 0.1326 Explore P: 0.6921
Episode: 6604 Total reward: 36.0 Training loss: 0.1738 Explore P: 0.6921
Episode: 6605 Total reward: 20.0 Training loss: 0.2198 Explore P: 0.6920
Episode: 6606 Total reward: 61.0 Training loss: 12.6959 Explore P: 0.6920
Episode: 6607 Total reward: 23.0 Training loss: 0.0228 Explore P: 0.6919
Episode: 6608 Total reward: 22.0 Training loss: 0.0286 Explore P: 0.6919
Episode: 6609 Total reward: 21.0 Training loss: 0.1376 Explore P: 0.6919
Episode: 6610 Total reward: 12.0 Training loss: 0.2512 Explore P: 0.6918
Episode: 6611 Total reward: 18.0 Training loss: 0.0444 Explore P: 0.6918
Episode: 6612 Total reward: 33.0 Training loss: 2.5240 Explore P: 0.6918
Episode: 6613 Total reward: 21.0 Training loss: 1.2829 Explore P: 0.6918
Episode: 6614 Total reward: 22.0 Training loss: 0.0103 Explore P: 0.6917
Episode: 6615 Total reward: 41.0 Training loss: 0.7148 Explore P: 0.6917
Episode: 6616 Total reward: 19.0 Training loss: 0.1161 Explore P: 0.6916
Episode: 6617 Total reward: 14.0 Training loss: 0.0497 Explore P: 0.6916
Episode: 6618 Total reward: 28.0 Training loss: 0.1517 Explore P: 0.6916
Episode: 6619 Total reward: 69.0 Training loss: 0.1609 Explore P: 0.6915
Episode: 6620 Total reward: 19.0 Training loss: 1.1559 Explore P: 0.6915
Episode: 6621 Total reward: 15.0 Training loss: 0.5831 Explore P: 0.6914
Episode: 6622 Total reward: 37.0 Training loss: 0.0866 Explore P: 0.6914
Episode: 6623 Total reward: 19.0 Training loss: 1.7622 Explore P: 0.6914
Episode: 6624 Total reward: 11.0 Training loss: 0.0166 Explore P: 0.6914
Episode: 6625 Total reward: 24.0 Training loss: 3.7863 Explore P: 0.6913
Episode: 6626 Total reward: 45.0 Training loss: 2.1996 Explore P: 0.6913
Episode: 6627 Total reward: 17.0 Training loss: 15.3848 Explore P: 0.6912
Episode: 6628 Total reward: 15.0 Training loss: 24.9158 Explore P: 0.6912
Episode: 6629 Total reward: 15.0 Training loss: 15.5132 Explore P: 0.6912
Episode: 6630 Total reward: 14.0 Training loss: 0.0439 Explore P: 0.6912
Episode: 6631 Total reward: 14.0 Training loss: 0.3541 Explore P: 0.6912
Episode: 6632 Total reward: 20.0 Training loss: 2.3115 Explore P: 0.6911
Episode: 6633 Total reward: 20.0 Training loss: 2.0505 Explore P: 0.6911
Episode: 6634 Total reward: 9.0 Training loss: 0.0455 Explore P: 0.6911
Episode: 6635 Total reward: 28.0 Training loss: 8.2008 Explore P: 0.6910
Episode: 6636 Total reward: 11.0 Training loss: 4.0753 Explore P: 0.6910
Episode: 6637 Total reward: 31.0 Training loss: 0.6947 Explore P: 0.6910
Episode: 6638 Total reward: 27.0 Training loss: 1.2527 Explore P: 0.6910
Episode: 6639 Total reward: 41.0 Training loss: 2.5385 Explore P: 0.6909
Episode: 6640 Total reward: 17.0 Training loss: 0.0179 Explore P: 0.6909
Episode: 6641 Total reward: 19.0 Training loss: 0.0597 Explore P: 0.6909
Episode: 6642 Total reward: 15.0 Training loss: 2.3855 Explore P: 0.6908
Episode: 6643 Total reward: 13.0 Training loss: 0.0668 Explore P: 0.6908
Episode: 6644 Total reward: 28.0 Training loss: 0.3066 Explore P: 0.6908
Episode: 6645 Total reward: 16.0 Training loss: 0.6964 Explore P: 0.6908
Episode: 6646 Total reward: 50.0 Training loss: 1.1101 Explore P: 0.6907
Episode: 6647 Total reward: 23.0 Training loss: 0.0526 Explore P: 0.6907
Episode: 6648 Total reward: 18.0 Training loss: 0.5173 Explore P: 0.6906
Episode: 6649 Total reward: 13.0 Training loss: 0.9823 Explore P: 0.6906
Episode: 6650 Total reward: 13.0 Training loss: 0.0925 Explore P: 0.6906
Episode: 6651 Total reward: 24.0 Training loss: 1.9435 Explore P: 0.6906
Episode: 6652 Total reward: 15.0 Training loss: 0.1052 Explore P: 0.6905
Episode: 6653 Total reward: 13.0 Training loss: 0.0591 Explore P: 0.6905
Episode: 6654 Total reward: 18.0 Training loss: 1.1441 Explore P: 0.6905
Episode: 6655 Total reward: 14.0 Training loss: 0.1854 Explore P: 0.6905
Episode: 6656 Total reward: 30.0 Training loss: 1.2716 Explore P: 0.6904
Episode: 6657 Total reward: 9.0 Training loss: 0.0858 Explore P: 0.6904
Episode: 6658 Total reward: 18.0 Training loss: 0.4347 Explore P: 0.6904
Episode: 6659 Total reward: 25.0 Training loss: 0.1027 Explore P: 0.6904
Episode: 6660 Total reward: 27.0 Training loss: 3.0542 Explore P: 0.6903
Episode: 6661 Total reward: 16.0 Training loss: 0.1457 Explore P: 0.6903
Episode: 6662 Total reward: 19.0 Training loss: 7.0415 Explore P: 0.6903
Episode: 6663 Total reward: 14.0 Training loss: 0.0908 Explore P: 0.6903
Episode: 6664 Total reward: 10.0 Training loss: 0.3479 Explore P: 0.6903
Episode: 6665 Total reward: 19.0 Training loss: 0.4756 Explore P: 0.6902
Episode: 6666 Total reward: 17.0 Training loss: 1.0440 Explore P: 0.6902
Episode: 6667 Total reward: 22.0 Training loss: 0.0455 Explore P: 0.6902
Episode: 6668 Total reward: 20.0 Training loss: 4.0393 Explore P: 0.6901
Episode: 6669 Total reward: 22.0 Training loss: 0.3291 Explore P: 0.6901
Episode: 6670 Total reward: 15.0 Training loss: 0.0571 Explore P: 0.6901
Episode: 6671 Total reward: 24.0 Training loss: 0.4189 Explore P: 0.6901
Episode: 6672 Total reward: 8.0 Training loss: 0.1589 Explore P: 0.6901
Episode: 6673 Total reward: 28.0 Training loss: 2.0541 Explore P: 0.6900
Episode: 6674 Total reward: 15.0 Training loss: 0.0817 Explore P: 0.6900
Episode: 6675 Total reward: 31.0 Training loss: 0.0750 Explore P: 0.6900
Episode: 6676 Total reward: 16.0 Training loss: 0.1284 Explore P: 0.6899
Episode: 6677 Total reward: 16.0 Training loss: 1.0068 Explore P: 0.6899
Episode: 6678 Total reward: 24.0 Training loss: 0.0657 Explore P: 0.6899
Episode: 6679 Total reward: 32.0 Training loss: 0.0996 Explore P: 0.6898
Episode: 6680 Total reward: 13.0 Training loss: 0.6237 Explore P: 0.6898
Episode: 6681 Total reward: 13.0 Training loss: 3.8952 Explore P: 0.6898
Episode: 6682 Total reward: 16.0 Training loss: 0.0505 Explore P: 0.6898
Episode: 6683 Total reward: 26.0 Training loss: 0.3230 Explore P: 0.6897
Episode: 6684 Total reward: 13.0 Training loss: 0.5361 Explore P: 0.6897
Episode: 6685 Total reward: 17.0 Training loss: 0.2573 Explore P: 0.6897
Episode: 6686 Total reward: 14.0 Training loss: 0.1031 Explore P: 0.6897
Episode: 6687 Total reward: 14.0 Training loss: 0.2612 Explore P: 0.6897
Episode: 6688 Total reward: 8.0 Training loss: 0.0988 Explore P: 0.6896
Episode: 6689 Total reward: 20.0 Training loss: 3.4952 Explore P: 0.6896
Episode: 6690 Total reward: 23.0 Training loss: 1.0411 Explore P: 0.6896
Episode: 6691 Total reward: 15.0 Training loss: 0.0505 Explore P: 0.6896
Episode: 6692 Total reward: 18.0 Training loss: 1.3381 Explore P: 0.6895
Episode: 6693 Total reward: 34.0 Training loss: 1.9117 Explore P: 0.6895
Episode: 6694 Total reward: 16.0 Training loss: 0.3515 Explore P: 0.6895
Episode: 6695 Total reward: 14.0 Training loss: 0.0912 Explore P: 0.6895
Episode: 6696 Total reward: 17.0 Training loss: 0.0886 Explore P: 0.6894
Episode: 6697 Total reward: 14.0 Training loss: 0.0874 Explore P: 0.6894
Episode: 6698 Total reward: 12.0 Training loss: 0.4547 Explore P: 0.6894
Episode: 6699 Total reward: 20.0 Training loss: 5.5137 Explore P: 0.6894
Episode: 6700 Total reward: 48.0 Training loss: 1.0819 Explore P: 0.6893
Episode: 6701 Total reward: 35.0 Training loss: 3.0743 Explore P: 0.6893
Episode: 6702 Total reward: 28.0 Training loss: 1.0696 Explore P: 0.6892
Episode: 6703 Total reward: 13.0 Training loss: 0.9703 Explore P: 0.6892
Episode: 6704 Total reward: 41.0 Training loss: 0.5082 Explore P: 0.6891
Episode: 6705 Total reward: 18.0 Training loss: 0.3358 Explore P: 0.6891
Episode: 6706 Total reward: 16.0 Training loss: 1.7244 Explore P: 0.6891
Episode: 6707 Total reward: 24.0 Training loss: 0.0035 Explore P: 0.6891
Episode: 6708 Total reward: 21.0 Training loss: 0.2252 Explore P: 0.6890
Episode: 6709 Total reward: 11.0 Training loss: 1.8582 Explore P: 0.6890
Episode: 6710 Total reward: 13.0 Training loss: 1.2182 Explore P: 0.6890
Episode: 6711 Total reward: 12.0 Training loss: 1.4286 Explore P: 0.6890
Episode: 6712 Total reward: 30.0 Training loss: 0.2558 Explore P: 0.6890
Episode: 6713 Total reward: 9.0 Training loss: 1.1472 Explore P: 0.6889
Episode: 6714 Total reward: 41.0 Training loss: 0.2208 Explore P: 0.6889
Episode: 6715 Total reward: 87.0 Training loss: 4.9035 Explore P: 0.6888
Episode: 6716 Total reward: 46.0 Training loss: 0.0286 Explore P: 0.6887
Episode: 6717 Total reward: 16.0 Training loss: 0.4041 Explore P: 0.6887
Episode: 6718 Total reward: 12.0 Training loss: 0.0307 Explore P: 0.6887
Episode: 6719 Total reward: 18.0 Training loss: 0.0493 Explore P: 0.6886
Episode: 6720 Total reward: 23.0 Training loss: 2.0681 Explore P: 0.6886
Episode: 6721 Total reward: 15.0 Training loss: 0.0517 Explore P: 0.6886
Episode: 6722 Total reward: 15.0 Training loss: 0.7258 Explore P: 0.6886
Episode: 6723 Total reward: 10.0 Training loss: 0.0996 Explore P: 0.6886
Episode: 6724 Total reward: 34.0 Training loss: 0.2722 Explore P: 0.6885
Episode: 6725 Total reward: 15.0 Training loss: 0.3317 Explore P: 0.6885
Episode: 6726 Total reward: 18.0 Training loss: 0.5551 Explore P: 0.6885
Episode: 6727 Total reward: 29.0 Training loss: 0.0305 Explore P: 0.6884
Episode: 6728 Total reward: 18.0 Training loss: 6.2748 Explore P: 0.6884
Episode: 6729 Total reward: 15.0 Training loss: 0.3974 Explore P: 0.6884
Episode: 6730 Total reward: 62.0 Training loss: 2.1272 Explore P: 0.6883
Episode: 6731 Total reward: 10.0 Training loss: 0.1700 Explore P: 0.6883
Episode: 6732 Total reward: 18.0 Training loss: 2.3625 Explore P: 0.6883
Episode: 6733 Total reward: 28.0 Training loss: 0.5169 Explore P: 0.6882
Episode: 6734 Total reward: 26.0 Training loss: 0.0392 Explore P: 0.6882
Episode: 6735 Total reward: 14.0 Training loss: 0.3365 Explore P: 0.6882
Episode: 6736 Total reward: 12.0 Training loss: 2.3679 Explore P: 0.6881
Episode: 6737 Total reward: 18.0 Training loss: 0.0230 Explore P: 0.6881
Episode: 6738 Total reward: 34.0 Training loss: 3.5251 Explore P: 0.6881
Episode: 6739 Total reward: 15.0 Training loss: 0.3120 Explore P: 0.6881
Episode: 6740 Total reward: 26.0 Training loss: 0.0073 Explore P: 0.6880
Episode: 6741 Total reward: 12.0 Training loss: 0.0489 Explore P: 0.6880
Episode: 6742 Total reward: 13.0 Training loss: 0.0598 Explore P: 0.6880
Episode: 6743 Total reward: 20.0 Training loss: 0.0158 Explore P: 0.6880
Episode: 6744 Total reward: 12.0 Training loss: 0.0496 Explore P: 0.6879
Episode: 6745 Total reward: 9.0 Training loss: 0.0316 Explore P: 0.6879
Episode: 6746 Total reward: 14.0 Training loss: 1.7659 Explore P: 0.6879
Episode: 6747 Total reward: 17.0 Training loss: 0.1045 Explore P: 0.6879
Episode: 6748 Total reward: 16.0 Training loss: 1.3717 Explore P: 0.6879
Episode: 6749 Total reward: 21.0 Training loss: 0.4511 Explore P: 0.6878
Episode: 6750 Total reward: 11.0 Training loss: 0.9307 Explore P: 0.6878
Episode: 6751 Total reward: 12.0 Training loss: 0.0151 Explore P: 0.6878
Episode: 6752 Total reward: 19.0 Training loss: 2.3005 Explore P: 0.6878
Episode: 6753 Total reward: 20.0 Training loss: 16.3492 Explore P: 0.6878
Episode: 6754 Total reward: 33.0 Training loss: 0.2517 Explore P: 0.6877
Episode: 6755 Total reward: 27.0 Training loss: 0.0498 Explore P: 0.6877
Episode: 6756 Total reward: 44.0 Training loss: 0.3345 Explore P: 0.6876
Episode: 6757 Total reward: 8.0 Training loss: 0.0182 Explore P: 0.6876
Episode: 6758 Total reward: 20.0 Training loss: 0.7440 Explore P: 0.6876
Episode: 6759 Total reward: 9.0 Training loss: 0.0074 Explore P: 0.6876
Episode: 6760 Total reward: 17.0 Training loss: 0.9581 Explore P: 0.6875
Episode: 6761 Total reward: 16.0 Training loss: 0.0109 Explore P: 0.6875
Episode: 6762 Total reward: 24.0 Training loss: 1.0123 Explore P: 0.6875
Episode: 6763 Total reward: 15.0 Training loss: 1.1776 Explore P: 0.6875
Episode: 6764 Total reward: 15.0 Training loss: 0.1789 Explore P: 0.6874
Episode: 6765 Total reward: 44.0 Training loss: 2.2271 Explore P: 0.6874
Episode: 6766 Total reward: 11.0 Training loss: 0.3350 Explore P: 0.6874
Episode: 6767 Total reward: 9.0 Training loss: 0.0226 Explore P: 0.6874
Episode: 6768 Total reward: 27.0 Training loss: 0.0051 Explore P: 0.6873
Episode: 6769 Total reward: 45.0 Training loss: 0.0259 Explore P: 0.6873
Episode: 6770 Total reward: 20.0 Training loss: 0.3065 Explore P: 0.6872
Episode: 6771 Total reward: 15.0 Training loss: 0.0997 Explore P: 0.6872
Episode: 6772 Total reward: 22.0 Training loss: 1.6949 Explore P: 0.6872
Episode: 6773 Total reward: 17.0 Training loss: 0.1558 Explore P: 0.6872
Episode: 6774 Total reward: 20.0 Training loss: 0.4511 Explore P: 0.6871
Episode: 6775 Total reward: 26.0 Training loss: 0.1078 Explore P: 0.6871
Episode: 6776 Total reward: 11.0 Training loss: 0.0219 Explore P: 0.6871
Episode: 6777 Total reward: 17.0 Training loss: 0.2012 Explore P: 0.6871
Episode: 6778 Total reward: 29.0 Training loss: 1.3433 Explore P: 0.6870
Episode: 6779 Total reward: 8.0 Training loss: 11.5145 Explore P: 0.6870
Episode: 6780 Total reward: 33.0 Training loss: 0.0187 Explore P: 0.6870
Episode: 6781 Total reward: 22.0 Training loss: 0.1234 Explore P: 0.6869
Episode: 6782 Total reward: 45.0 Training loss: 0.6649 Explore P: 0.6869
Episode: 6783 Total reward: 12.0 Training loss: 0.3148 Explore P: 0.6869
Episode: 6784 Total reward: 8.0 Training loss: 0.0727 Explore P: 0.6869
Episode: 6785 Total reward: 31.0 Training loss: 0.0204 Explore P: 0.6868
Episode: 6786 Total reward: 26.0 Training loss: 0.1984 Explore P: 0.6868
Episode: 6787 Total reward: 35.0 Training loss: 0.0465 Explore P: 0.6867
Episode: 6788 Total reward: 13.0 Training loss: 0.0495 Explore P: 0.6867
Episode: 6789 Total reward: 13.0 Training loss: 1.8692 Explore P: 0.6867
Episode: 6790 Total reward: 18.0 Training loss: 0.0633 Explore P: 0.6867
Episode: 6791 Total reward: 74.0 Training loss: 1.1925 Explore P: 0.6866
Episode: 6792 Total reward: 15.0 Training loss: 4.3610 Explore P: 0.6865
Episode: 6793 Total reward: 47.0 Training loss: 2.3812 Explore P: 0.6865
Episode: 6794 Total reward: 14.0 Training loss: 8.2831 Explore P: 0.6865
Episode: 6795 Total reward: 21.0 Training loss: 3.7005 Explore P: 0.6864
Episode: 6796 Total reward: 10.0 Training loss: 0.0555 Explore P: 0.6864
Episode: 6797 Total reward: 23.0 Training loss: 6.0547 Explore P: 0.6864
Episode: 6798 Total reward: 12.0 Training loss: 0.0174 Explore P: 0.6864
Episode: 6799 Total reward: 16.0 Training loss: 0.3165 Explore P: 0.6864
Episode: 6800 Total reward: 10.0 Training loss: 0.0591 Explore P: 0.6863
Episode: 6801 Total reward: 14.0 Training loss: 0.1718 Explore P: 0.6863
Episode: 6802 Total reward: 56.0 Training loss: 0.7198 Explore P: 0.6862
Episode: 6803 Total reward: 16.0 Training loss: 0.2837 Explore P: 0.6862
Episode: 6804 Total reward: 9.0 Training loss: 1.4283 Explore P: 0.6862
Episode: 6805 Total reward: 37.0 Training loss: 0.0533 Explore P: 0.6862
Episode: 6806 Total reward: 10.0 Training loss: 0.6033 Explore P: 0.6861
Episode: 6807 Total reward: 15.0 Training loss: 1.7386 Explore P: 0.6861
Episode: 6808 Total reward: 13.0 Training loss: 0.3488 Explore P: 0.6861
Episode: 6809 Total reward: 13.0 Training loss: 0.8057 Explore P: 0.6861
Episode: 6810 Total reward: 21.0 Training loss: 2.1133 Explore P: 0.6861
Episode: 6811 Total reward: 29.0 Training loss: 1.8211 Explore P: 0.6860
Episode: 6812 Total reward: 34.0 Training loss: 0.5607 Explore P: 0.6860
Episode: 6813 Total reward: 14.0 Training loss: 46.9999 Explore P: 0.6860
Episode: 6814 Total reward: 16.0 Training loss: 0.2984 Explore P: 0.6859
Episode: 6815 Total reward: 18.0 Training loss: 0.0287 Explore P: 0.6859
Episode: 6816 Total reward: 23.0 Training loss: 2.4450 Explore P: 0.6859
Episode: 6817 Total reward: 12.0 Training loss: 0.5569 Explore P: 0.6859
Episode: 6818 Total reward: 21.0 Training loss: 2.8250 Explore P: 0.6858
Episode: 6819 Total reward: 14.0 Training loss: 1.8267 Explore P: 0.6858
Episode: 6820 Total reward: 11.0 Training loss: 0.0157 Explore P: 0.6858
Episode: 6821 Total reward: 17.0 Training loss: 0.0599 Explore P: 0.6858
Episode: 6822 Total reward: 27.0 Training loss: 0.3624 Explore P: 0.6857
Episode: 6823 Total reward: 12.0 Training loss: 0.1969 Explore P: 0.6857
Episode: 6824 Total reward: 13.0 Training loss: 0.3414 Explore P: 0.6857
Episode: 6825 Total reward: 26.0 Training loss: 0.2308 Explore P: 0.6857
Episode: 6826 Total reward: 13.0 Training loss: 16.7752 Explore P: 0.6857
Episode: 6827 Total reward: 14.0 Training loss: 0.8899 Explore P: 0.6856
Episode: 6828 Total reward: 14.0 Training loss: 34.0421 Explore P: 0.6856
Episode: 6829 Total reward: 17.0 Training loss: 1.8546 Explore P: 0.6856
Episode: 6830 Total reward: 48.0 Training loss: 0.0276 Explore P: 0.6855
Episode: 6831 Total reward: 8.0 Training loss: 0.0595 Explore P: 0.6855
Episode: 6832 Total reward: 31.0 Training loss: 0.0256 Explore P: 0.6855
Episode: 6833 Total reward: 19.0 Training loss: 3.0356 Explore P: 0.6855
Episode: 6834 Total reward: 27.0 Training loss: 0.0298 Explore P: 0.6854
Episode: 6835 Total reward: 23.0 Training loss: 0.0079 Explore P: 0.6854
Episode: 6836 Total reward: 13.0 Training loss: 0.0420 Explore P: 0.6854
Episode: 6837 Total reward: 14.0 Training loss: 0.0046 Explore P: 0.6854
Episode: 6838 Total reward: 22.0 Training loss: 0.0059 Explore P: 0.6853
Episode: 6839 Total reward: 22.0 Training loss: 0.7504 Explore P: 0.6853
Episode: 6840 Total reward: 14.0 Training loss: 0.0638 Explore P: 0.6853
Episode: 6841 Total reward: 50.0 Training loss: 0.0235 Explore P: 0.6852
Episode: 6842 Total reward: 26.0 Training loss: 3.0033 Explore P: 0.6852
Episode: 6843 Total reward: 12.0 Training loss: 0.0256 Explore P: 0.6852
Episode: 6844 Total reward: 18.0 Training loss: 0.6899 Explore P: 0.6851
Episode: 6845 Total reward: 38.0 Training loss: 0.0233 Explore P: 0.6851
Episode: 6846 Total reward: 21.0 Training loss: 0.0508 Explore P: 0.6850
Episode: 6847 Total reward: 17.0 Training loss: 0.3300 Explore P: 0.6850
Episode: 6848 Total reward: 17.0 Training loss: 0.2989 Explore P: 0.6850
Episode: 6849 Total reward: 12.0 Training loss: 0.0382 Explore P: 0.6850
Episode: 6850 Total reward: 18.0 Training loss: 0.6150 Explore P: 0.6850
Episode: 6851 Total reward: 12.0 Training loss: 0.4186 Explore P: 0.6849
Episode: 6852 Total reward: 17.0 Training loss: 0.0401 Explore P: 0.6849
Episode: 6853 Total reward: 22.0 Training loss: 0.1132 Explore P: 0.6849
Episode: 6854 Total reward: 18.0 Training loss: 3.8798 Explore P: 0.6849
Episode: 6855 Total reward: 20.0 Training loss: 0.4680 Explore P: 0.6848
Episode: 6856 Total reward: 9.0 Training loss: 0.0821 Explore P: 0.6848
Episode: 6857 Total reward: 13.0 Training loss: 0.3077 Explore P: 0.6848
Episode: 6858 Total reward: 39.0 Training loss: 5.1715 Explore P: 0.6848
Episode: 6859 Total reward: 17.0 Training loss: 1.4438 Explore P: 0.6847
Episode: 6860 Total reward: 7.0 Training loss: 0.0239 Explore P: 0.6847
Episode: 6861 Total reward: 18.0 Training loss: 0.9177 Explore P: 0.6847
Episode: 6862 Total reward: 10.0 Training loss: 0.0955 Explore P: 0.6847
Episode: 6863 Total reward: 17.0 Training loss: 0.1584 Explore P: 0.6847
Episode: 6864 Total reward: 24.0 Training loss: 0.0457 Explore P: 0.6846
Episode: 6865 Total reward: 24.0 Training loss: 2.7499 Explore P: 0.6846
Episode: 6866 Total reward: 19.0 Training loss: 0.0071 Explore P: 0.6846
Episode: 6867 Total reward: 27.0 Training loss: 0.0356 Explore P: 0.6845
Episode: 6868 Total reward: 12.0 Training loss: 0.8744 Explore P: 0.6845
Episode: 6869 Total reward: 13.0 Training loss: 0.0323 Explore P: 0.6845
Episode: 6870 Total reward: 13.0 Training loss: 0.0307 Explore P: 0.6845
Episode: 6871 Total reward: 28.0 Training loss: 1.5432 Explore P: 0.6845
Episode: 6872 Total reward: 21.0 Training loss: 0.5414 Explore P: 0.6844
Episode: 6873 Total reward: 48.0 Training loss: 1.5151 Explore P: 0.6844
Episode: 6874 Total reward: 39.0 Training loss: 0.1596 Explore P: 0.6843
Episode: 6875 Total reward: 34.0 Training loss: 0.0066 Explore P: 0.6843
Episode: 6876 Total reward: 32.0 Training loss: 2.3337 Explore P: 0.6842
Episode: 6877 Total reward: 20.0 Training loss: 0.4921 Explore P: 0.6842
Episode: 6878 Total reward: 20.0 Training loss: 0.1877 Explore P: 0.6842
Episode: 6879 Total reward: 13.0 Training loss: 0.1248 Explore P: 0.6841
Episode: 6880 Total reward: 21.0 Training loss: 4.5328 Explore P: 0.6841
Episode: 6881 Total reward: 17.0 Training loss: 0.7052 Explore P: 0.6841
Episode: 6882 Total reward: 38.0 Training loss: 0.4741 Explore P: 0.6840
Episode: 6883 Total reward: 13.0 Training loss: 1.3420 Explore P: 0.6840
Episode: 6884 Total reward: 56.0 Training loss: 0.0879 Explore P: 0.6839
Episode: 6885 Total reward: 11.0 Training loss: 0.4386 Explore P: 0.6839
Episode: 6886 Total reward: 23.0 Training loss: 0.0497 Explore P: 0.6839
Episode: 6887 Total reward: 11.0 Training loss: 0.0404 Explore P: 0.6839
Episode: 6888 Total reward: 21.0 Training loss: 0.6030 Explore P: 0.6839
Episode: 6889 Total reward: 30.0 Training loss: 0.3674 Explore P: 0.6838
Episode: 6890 Total reward: 12.0 Training loss: 1.3555 Explore P: 0.6838
Episode: 6891 Total reward: 20.0 Training loss: 0.1084 Explore P: 0.6838
Episode: 6892 Total reward: 25.0 Training loss: 5.1583 Explore P: 0.6837
Episode: 6893 Total reward: 11.0 Training loss: 1.3718 Explore P: 0.6837
Episode: 6894 Total reward: 19.0 Training loss: 0.0235 Explore P: 0.6837
Episode: 6895 Total reward: 9.0 Training loss: 0.0566 Explore P: 0.6837
Episode: 6896 Total reward: 7.0 Training loss: 0.5124 Explore P: 0.6837
Episode: 6897 Total reward: 13.0 Training loss: 0.9203 Explore P: 0.6837
Episode: 6898 Total reward: 31.0 Training loss: 0.0039 Explore P: 0.6836
Episode: 6899 Total reward: 10.0 Training loss: 0.0214 Explore P: 0.6836
Episode: 6900 Total reward: 15.0 Training loss: 177.1404 Explore P: 0.6836
Episode: 6901 Total reward: 60.0 Training loss: 0.0176 Explore P: 0.6835
Episode: 6902 Total reward: 16.0 Training loss: 0.0737 Explore P: 0.6835
Episode: 6903 Total reward: 15.0 Training loss: 0.4305 Explore P: 0.6835
Episode: 6904 Total reward: 17.0 Training loss: 0.1195 Explore P: 0.6834
Episode: 6905 Total reward: 14.0 Training loss: 1.4293 Explore P: 0.6834
Episode: 6906 Total reward: 49.0 Training loss: 2.1213 Explore P: 0.6834
Episode: 6907 Total reward: 28.0 Training loss: 0.0769 Explore P: 0.6833
Episode: 6908 Total reward: 8.0 Training loss: 0.3742 Explore P: 0.6833
Episode: 6909 Total reward: 19.0 Training loss: 0.1031 Explore P: 0.6833
Episode: 6910 Total reward: 17.0 Training loss: 0.1466 Explore P: 0.6833
Episode: 6911 Total reward: 18.0 Training loss: 0.5583 Explore P: 0.6832
Episode: 6912 Total reward: 14.0 Training loss: 0.1094 Explore P: 0.6832
Episode: 6913 Total reward: 24.0 Training loss: 0.2268 Explore P: 0.6832
Episode: 6914 Total reward: 14.0 Training loss: 1.8451 Explore P: 0.6832
Episode: 6915 Total reward: 18.0 Training loss: 0.3684 Explore P: 0.6831
Episode: 6916 Total reward: 19.0 Training loss: 0.0379 Explore P: 0.6831
Episode: 6917 Total reward: 19.0 Training loss: 0.1288 Explore P: 0.6831
Episode: 6918 Total reward: 14.0 Training loss: 0.0561 Explore P: 0.6831
Episode: 6919 Total reward: 22.0 Training loss: 0.6802 Explore P: 0.6830
Episode: 6920 Total reward: 53.0 Training loss: 0.1444 Explore P: 0.6830
Episode: 6921 Total reward: 30.0 Training loss: 0.0963 Explore P: 0.6829
Episode: 6922 Total reward: 36.0 Training loss: 0.1404 Explore P: 0.6829
Episode: 6923 Total reward: 8.0 Training loss: 0.3285 Explore P: 0.6829
Episode: 6924 Total reward: 10.0 Training loss: 0.0489 Explore P: 0.6829
Episode: 6925 Total reward: 37.0 Training loss: 0.1231 Explore P: 0.6828
Episode: 6926 Total reward: 19.0 Training loss: 0.3849 Explore P: 0.6828
Episode: 6927 Total reward: 42.0 Training loss: 1.1590 Explore P: 0.6827
Episode: 6928 Total reward: 8.0 Training loss: 1.1873 Explore P: 0.6827
Episode: 6929 Total reward: 37.0 Training loss: 0.0998 Explore P: 0.6827
Episode: 6930 Total reward: 12.0 Training loss: 0.7252 Explore P: 0.6827
Episode: 6931 Total reward: 12.0 Training loss: 1.3005 Explore P: 0.6826
Episode: 6932 Total reward: 13.0 Training loss: 0.6779 Explore P: 0.6826
Episode: 6933 Total reward: 17.0 Training loss: 0.0271 Explore P: 0.6826
Episode: 6934 Total reward: 13.0 Training loss: 0.9095 Explore P: 0.6826
Episode: 6935 Total reward: 19.0 Training loss: 0.7149 Explore P: 0.6826
Episode: 6936 Total reward: 38.0 Training loss: 0.2434 Explore P: 0.6825
Episode: 6937 Total reward: 18.0 Training loss: 0.0544 Explore P: 0.6825
Episode: 6938 Total reward: 21.0 Training loss: 0.4400 Explore P: 0.6824
Episode: 6939 Total reward: 33.0 Training loss: 0.3005 Explore P: 0.6824
Episode: 6940 Total reward: 15.0 Training loss: 0.8380 Explore P: 0.6824
Episode: 6941 Total reward: 10.0 Training loss: 0.0349 Explore P: 0.6824
Episode: 6942 Total reward: 18.0 Training loss: 0.8668 Explore P: 0.6823
Episode: 6943 Total reward: 19.0 Training loss: 0.0646 Explore P: 0.6823
Episode: 6944 Total reward: 34.0 Training loss: 0.0396 Explore P: 0.6823
Episode: 6945 Total reward: 19.0 Training loss: 0.4557 Explore P: 0.6822
Episode: 6946 Total reward: 13.0 Training loss: 1.3205 Explore P: 0.6822
Episode: 6947 Total reward: 28.0 Training loss: 0.8217 Explore P: 0.6822
Episode: 6948 Total reward: 24.0 Training loss: 1.0224 Explore P: 0.6822
Episode: 6949 Total reward: 19.0 Training loss: 0.2014 Explore P: 0.6821
Episode: 6950 Total reward: 16.0 Training loss: 1.5188 Explore P: 0.6821
Episode: 6951 Total reward: 33.0 Training loss: 2.8797 Explore P: 0.6821
Episode: 6952 Total reward: 18.0 Training loss: 0.1163 Explore P: 0.6820
Episode: 6953 Total reward: 29.0 Training loss: 0.2644 Explore P: 0.6820
Episode: 6954 Total reward: 65.0 Training loss: 3.6617 Explore P: 0.6819
Episode: 6955 Total reward: 24.0 Training loss: 0.0212 Explore P: 0.6819
Episode: 6956 Total reward: 24.0 Training loss: 0.2270 Explore P: 0.6819
Episode: 6957 Total reward: 21.0 Training loss: 2.1413 Explore P: 0.6818
Episode: 6958 Total reward: 12.0 Training loss: 0.5267 Explore P: 0.6818
Episode: 6959 Total reward: 34.0 Training loss: 1.2948 Explore P: 0.6818
Episode: 6960 Total reward: 20.0 Training loss: 0.8034 Explore P: 0.6817
Episode: 6961 Total reward: 14.0 Training loss: 0.0302 Explore P: 0.6817
Episode: 6962 Total reward: 8.0 Training loss: 0.1661 Explore P: 0.6817
Episode: 6963 Total reward: 27.0 Training loss: 0.0116 Explore P: 0.6817
Episode: 6964 Total reward: 27.0 Training loss: 0.0688 Explore P: 0.6816
Episode: 6965 Total reward: 13.0 Training loss: 1.1263 Explore P: 0.6816
Episode: 6966 Total reward: 16.0 Training loss: 0.4291 Explore P: 0.6816
Episode: 6967 Total reward: 15.0 Training loss: 1.6623 Explore P: 0.6816
Episode: 6968 Total reward: 24.0 Training loss: 0.6887 Explore P: 0.6815
Episode: 6969 Total reward: 20.0 Training loss: 0.2051 Explore P: 0.6815
Episode: 6970 Total reward: 29.0 Training loss: 0.1094 Explore P: 0.6815
Episode: 6971 Total reward: 11.0 Training loss: 0.0203 Explore P: 0.6815
Episode: 6972 Total reward: 21.0 Training loss: 0.5253 Explore P: 0.6814
Episode: 6973 Total reward: 44.0 Training loss: 0.0674 Explore P: 0.6814
Episode: 6974 Total reward: 15.0 Training loss: 0.2220 Explore P: 0.6814
Episode: 6975 Total reward: 43.0 Training loss: 0.0749 Explore P: 0.6813
Episode: 6976 Total reward: 27.0 Training loss: 0.0101 Explore P: 0.6813
Episode: 6977 Total reward: 23.0 Training loss: 0.0477 Explore P: 0.6812
Episode: 6978 Total reward: 14.0 Training loss: 0.0257 Explore P: 0.6812
Episode: 6979 Total reward: 12.0 Training loss: 1.4946 Explore P: 0.6812
Episode: 6980 Total reward: 33.0 Training loss: 0.1123 Explore P: 0.6812
Episode: 6981 Total reward: 20.0 Training loss: 0.0596 Explore P: 0.6811
Episode: 6982 Total reward: 20.0 Training loss: 0.2459 Explore P: 0.6811
Episode: 6983 Total reward: 25.0 Training loss: 0.9372 Explore P: 0.6811
Episode: 6984 Total reward: 25.0 Training loss: 0.5357 Explore P: 0.6810
Episode: 6985 Total reward: 48.0 Training loss: 0.2963 Explore P: 0.6810
Episode: 6986 Total reward: 14.0 Training loss: 0.2396 Explore P: 0.6809
Episode: 6987 Total reward: 73.0 Training loss: 0.3070 Explore P: 0.6808
Episode: 6988 Total reward: 13.0 Training loss: 0.3601 Explore P: 0.6808
Episode: 6989 Total reward: 20.0 Training loss: 0.0206 Explore P: 0.6808
Episode: 6990 Total reward: 26.0 Training loss: 0.5470 Explore P: 0.6808
Episode: 6991 Total reward: 19.0 Training loss: 0.9096 Explore P: 0.6807
Episode: 6992 Total reward: 35.0 Training loss: 0.0779 Explore P: 0.6807
Episode: 6993 Total reward: 13.0 Training loss: 0.0838 Explore P: 0.6807
Episode: 6994 Total reward: 37.0 Training loss: 0.4350 Explore P: 0.6806
Episode: 6995 Total reward: 18.0 Training loss: 11.7233 Explore P: 0.6806
Episode: 6996 Total reward: 17.0 Training loss: 0.7703 Explore P: 0.6806
Episode: 6997 Total reward: 17.0 Training loss: 0.2643 Explore P: 0.6806
Episode: 6998 Total reward: 11.0 Training loss: 0.1840 Explore P: 0.6805
Episode: 6999 Total reward: 16.0 Training loss: 0.3288 Explore P: 0.6805
Episode: 7000 Total reward: 9.0 Training loss: 0.0302 Explore P: 0.6805
Episode: 7001 Total reward: 42.0 Training loss: 1.0467 Explore P: 0.6805
Episode: 7002 Total reward: 18.0 Training loss: 0.0035 Explore P: 0.6804
Episode: 7003 Total reward: 11.0 Training loss: 0.3555 Explore P: 0.6804
Episode: 7004 Total reward: 41.0 Training loss: 0.9195 Explore P: 0.6804
Episode: 7005 Total reward: 38.0 Training loss: 0.0562 Explore P: 0.6803
Episode: 7006 Total reward: 27.0 Training loss: 0.4505 Explore P: 0.6803
Episode: 7007 Total reward: 21.0 Training loss: 0.4024 Explore P: 0.6802
Episode: 7008 Total reward: 33.0 Training loss: 0.0145 Explore P: 0.6802
Episode: 7009 Total reward: 19.0 Training loss: 1.6940 Explore P: 0.6802
Episode: 7010 Total reward: 12.0 Training loss: 0.0042 Explore P: 0.6802
Episode: 7011 Total reward: 19.0 Training loss: 0.1973 Explore P: 0.6801
Episode: 7012 Total reward: 19.0 Training loss: 0.0726 Explore P: 0.6801
Episode: 7013 Total reward: 46.0 Training loss: 1.3256 Explore P: 0.6800
Episode: 7014 Total reward: 10.0 Training loss: 1.3638 Explore P: 0.6800
Episode: 7015 Total reward: 21.0 Training loss: 1.2012 Explore P: 0.6800
Episode: 7016 Total reward: 41.0 Training loss: 0.0257 Explore P: 0.6800
Episode: 7017 Total reward: 21.0 Training loss: 0.0686 Explore P: 0.6799
Episode: 7018 Total reward: 17.0 Training loss: 1.3649 Explore P: 0.6799
Episode: 7019 Total reward: 22.0 Training loss: 0.6688 Explore P: 0.6799
Episode: 7020 Total reward: 55.0 Training loss: 1.2203 Explore P: 0.6798
Episode: 7021 Total reward: 31.0 Training loss: 0.2422 Explore P: 0.6798
Episode: 7022 Total reward: 26.0 Training loss: 0.6459 Explore P: 0.6797
Episode: 7023 Total reward: 9.0 Training loss: 0.1307 Explore P: 0.6797
Episode: 7024 Total reward: 40.0 Training loss: 0.4286 Explore P: 0.6797
Episode: 7025 Total reward: 25.0 Training loss: 0.0651 Explore P: 0.6796
Episode: 7026 Total reward: 13.0 Training loss: 0.8581 Explore P: 0.6796
Episode: 7027 Total reward: 16.0 Training loss: 1.7837 Explore P: 0.6796
Episode: 7028 Total reward: 30.0 Training loss: 0.5166 Explore P: 0.6795
Episode: 7029 Total reward: 18.0 Training loss: 0.0089 Explore P: 0.6795
Episode: 7030 Total reward: 23.0 Training loss: 0.0641 Explore P: 0.6795
Episode: 7031 Total reward: 20.0 Training loss: 8.9659 Explore P: 0.6795
Episode: 7032 Total reward: 21.0 Training loss: 0.2067 Explore P: 0.6794
Episode: 7033 Total reward: 63.0 Training loss: 0.5446 Explore P: 0.6794
Episode: 7034 Total reward: 46.0 Training loss: 0.7654 Explore P: 0.6793
Episode: 7035 Total reward: 21.0 Training loss: 0.3619 Explore P: 0.6793
Episode: 7036 Total reward: 9.0 Training loss: 0.3423 Explore P: 0.6792
Episode: 7037 Total reward: 34.0 Training loss: 0.1876 Explore P: 0.6792
Episode: 7038 Total reward: 26.0 Training loss: 0.5260 Explore P: 0.6792
Episode: 7039 Total reward: 31.0 Training loss: 0.0662 Explore P: 0.6791
Episode: 7040 Total reward: 19.0 Training loss: 1.0996 Explore P: 0.6791
Episode: 7041 Total reward: 7.0 Training loss: 1.2204 Explore P: 0.6791
Episode: 7042 Total reward: 22.0 Training loss: 0.1960 Explore P: 0.6791
Episode: 7043 Total reward: 18.0 Training loss: 0.2909 Explore P: 0.6790
Episode: 7044 Total reward: 16.0 Training loss: 0.1273 Explore P: 0.6790
Episode: 7045 Total reward: 17.0 Training loss: 0.9933 Explore P: 0.6790
Episode: 7046 Total reward: 16.0 Training loss: 0.7454 Explore P: 0.6790
Episode: 7047 Total reward: 33.0 Training loss: 0.0738 Explore P: 0.6789
Episode: 7048 Total reward: 12.0 Training loss: 0.0888 Explore P: 0.6789
Episode: 7049 Total reward: 9.0 Training loss: 10.3738 Explore P: 0.6789
Episode: 7050 Total reward: 34.0 Training loss: 0.1581 Explore P: 0.6789
Episode: 7051 Total reward: 10.0 Training loss: 1.3392 Explore P: 0.6788
Episode: 7052 Total reward: 40.0 Training loss: 0.3109 Explore P: 0.6788
Episode: 7053 Total reward: 25.0 Training loss: 0.8165 Explore P: 0.6788
Episode: 7054 Total reward: 13.0 Training loss: 0.1424 Explore P: 0.6787
Episode: 7055 Total reward: 31.0 Training loss: 0.0793 Explore P: 0.6787
Episode: 7056 Total reward: 23.0 Training loss: 0.6492 Explore P: 0.6787
Episode: 7057 Total reward: 28.0 Training loss: 0.3024 Explore P: 0.6786
Episode: 7058 Total reward: 18.0 Training loss: 0.2356 Explore P: 0.6786
Episode: 7059 Total reward: 36.0 Training loss: 1.1884 Explore P: 0.6786
Episode: 7060 Total reward: 19.0 Training loss: 0.4306 Explore P: 0.6785
Episode: 7061 Total reward: 22.0 Training loss: 0.0923 Explore P: 0.6785
Episode: 7062 Total reward: 15.0 Training loss: 6.5840 Explore P: 0.6785
Episode: 7063 Total reward: 7.0 Training loss: 0.0517 Explore P: 0.6785
Episode: 7064 Total reward: 21.0 Training loss: 0.1027 Explore P: 0.6784
Episode: 7065 Total reward: 19.0 Training loss: 0.0064 Explore P: 0.6784
Episode: 7066 Total reward: 13.0 Training loss: 0.6498 Explore P: 0.6784
Episode: 7067 Total reward: 27.0 Training loss: 0.6864 Explore P: 0.6784
Episode: 7068 Total reward: 20.0 Training loss: 0.3036 Explore P: 0.6783
Episode: 7069 Total reward: 19.0 Training loss: 0.7621 Explore P: 0.6783
Episode: 7070 Total reward: 39.0 Training loss: 0.3189 Explore P: 0.6783
Episode: 7071 Total reward: 18.0 Training loss: 0.3508 Explore P: 0.6782
Episode: 7072 Total reward: 15.0 Training loss: 0.0698 Explore P: 0.6782
Episode: 7073 Total reward: 16.0 Training loss: 0.6476 Explore P: 0.6782
Episode: 7074 Total reward: 18.0 Training loss: 0.5780 Explore P: 0.6782
Episode: 7075 Total reward: 14.0 Training loss: 1.3225 Explore P: 0.6782
Episode: 7076 Total reward: 13.0 Training loss: 0.6393 Explore P: 0.6781
Episode: 7077 Total reward: 20.0 Training loss: 0.6018 Explore P: 0.6781
Episode: 7078 Total reward: 21.0 Training loss: 10.4331 Explore P: 0.6781
Episode: 7079 Total reward: 26.0 Training loss: 0.1731 Explore P: 0.6780
Episode: 7080 Total reward: 27.0 Training loss: 0.1874 Explore P: 0.6780
Episode: 7081 Total reward: 18.0 Training loss: 0.9887 Explore P: 0.6780
Episode: 7082 Total reward: 27.0 Training loss: 0.1538 Explore P: 0.6779
Episode: 7083 Total reward: 40.0 Training loss: 0.4846 Explore P: 0.6779
Episode: 7084 Total reward: 35.0 Training loss: 1.8862 Explore P: 0.6778
Episode: 7085 Total reward: 34.0 Training loss: 0.2239 Explore P: 0.6778
Episode: 7086 Total reward: 41.0 Training loss: 0.2700 Explore P: 0.6777
Episode: 7087 Total reward: 32.0 Training loss: 0.3671 Explore P: 0.6777
Episode: 7088 Total reward: 42.0 Training loss: 1.6991 Explore P: 0.6776
Episode: 7089 Total reward: 19.0 Training loss: 0.0048 Explore P: 0.6776
Episode: 7090 Total reward: 22.0 Training loss: 1.6486 Explore P: 0.6776
Episode: 7091 Total reward: 11.0 Training loss: 0.0310 Explore P: 0.6776
Episode: 7092 Total reward: 28.0 Training loss: 0.2383 Explore P: 0.6775
Episode: 7093 Total reward: 12.0 Training loss: 1.3655 Explore P: 0.6775
Episode: 7094 Total reward: 14.0 Training loss: 0.0809 Explore P: 0.6775
Episode: 7095 Total reward: 25.0 Training loss: 5.5597 Explore P: 0.6775
Episode: 7096 Total reward: 20.0 Training loss: 0.4071 Explore P: 0.6774
Episode: 7097 Total reward: 27.0 Training loss: 0.0544 Explore P: 0.6774
Episode: 7098 Total reward: 13.0 Training loss: 4.4931 Explore P: 0.6774
Episode: 7099 Total reward: 28.0 Training loss: 1.5538 Explore P: 0.6774
Episode: 7100 Total reward: 18.0 Training loss: 0.8565 Explore P: 0.6773
Episode: 7101 Total reward: 10.0 Training loss: 0.3799 Explore P: 0.6773
Episode: 7102 Total reward: 16.0 Training loss: 0.0457 Explore P: 0.6773
Episode: 7103 Total reward: 48.0 Training loss: 1.6254 Explore P: 0.6772
Episode: 7104 Total reward: 30.0 Training loss: 1.1026 Explore P: 0.6772
Episode: 7105 Total reward: 27.0 Training loss: 0.9718 Explore P: 0.6772
Episode: 7106 Total reward: 29.0 Training loss: 0.2543 Explore P: 0.6771
Episode: 7107 Total reward: 32.0 Training loss: 1.1271 Explore P: 0.6771
Episode: 7108 Total reward: 31.0 Training loss: 1.4982 Explore P: 0.6770
Episode: 7109 Total reward: 13.0 Training loss: 0.2727 Explore P: 0.6770
Episode: 7110 Total reward: 36.0 Training loss: 25.8698 Explore P: 0.6770
Episode: 7111 Total reward: 43.0 Training loss: 0.1174 Explore P: 0.6769
Episode: 7112 Total reward: 18.0 Training loss: 0.1067 Explore P: 0.6769
Episode: 7113 Total reward: 16.0 Training loss: 0.1669 Explore P: 0.6769
Episode: 7114 Total reward: 9.0 Training loss: 1.2578 Explore P: 0.6769
Episode: 7115 Total reward: 22.0 Training loss: 0.3007 Explore P: 0.6768
Episode: 7116 Total reward: 16.0 Training loss: 0.2583 Explore P: 0.6768
Episode: 7117 Total reward: 33.0 Training loss: 0.4177 Explore P: 0.6768
Episode: 7118 Total reward: 17.0 Training loss: 0.3779 Explore P: 0.6767
Episode: 7119 Total reward: 11.0 Training loss: 0.2546 Explore P: 0.6767
Episode: 7120 Total reward: 27.0 Training loss: 0.9538 Explore P: 0.6767
Episode: 7121 Total reward: 10.0 Training loss: 0.3161 Explore P: 0.6767
Episode: 7122 Total reward: 18.0 Training loss: 0.7898 Explore P: 0.6767
Episode: 7123 Total reward: 28.0 Training loss: 14.9417 Explore P: 0.6766
Episode: 7124 Total reward: 15.0 Training loss: 0.5349 Explore P: 0.6766
Episode: 7125 Total reward: 26.0 Training loss: 0.1265 Explore P: 0.6766
Episode: 7126 Total reward: 30.0 Training loss: 0.0081 Explore P: 0.6765
Episode: 7127 Total reward: 15.0 Training loss: 2.5829 Explore P: 0.6765
Episode: 7128 Total reward: 21.0 Training loss: 0.0073 Explore P: 0.6765
Episode: 7129 Total reward: 9.0 Training loss: 0.3746 Explore P: 0.6765
Episode: 7130 Total reward: 18.0 Training loss: 0.0521 Explore P: 0.6764
Episode: 7131 Total reward: 36.0 Training loss: 0.9827 Explore P: 0.6764
Episode: 7132 Total reward: 16.0 Training loss: 0.3919 Explore P: 0.6764
Episode: 7133 Total reward: 32.0 Training loss: 0.1999 Explore P: 0.6763
Episode: 7134 Total reward: 23.0 Training loss: 1.5472 Explore P: 0.6763
Episode: 7135 Total reward: 8.0 Training loss: 0.5644 Explore P: 0.6763
Episode: 7136 Total reward: 23.0 Training loss: 0.3008 Explore P: 0.6763
Episode: 7137 Total reward: 13.0 Training loss: 0.0738 Explore P: 0.6762
Episode: 7138 Total reward: 23.0 Training loss: 0.5368 Explore P: 0.6762
Episode: 7139 Total reward: 13.0 Training loss: 1.6261 Explore P: 0.6762
Episode: 7140 Total reward: 13.0 Training loss: 0.6813 Explore P: 0.6762
Episode: 7141 Total reward: 35.0 Training loss: 0.8367 Explore P: 0.6761
Episode: 7142 Total reward: 23.0 Training loss: 3.0766 Explore P: 0.6761
Episode: 7143 Total reward: 10.0 Training loss: 0.4034 Explore P: 0.6761
Episode: 7144 Total reward: 44.0 Training loss: 6.8257 Explore P: 0.6760
Episode: 7145 Total reward: 28.0 Training loss: 0.6862 Explore P: 0.6760
Episode: 7146 Total reward: 25.0 Training loss: 1.4221 Explore P: 0.6759
Episode: 7147 Total reward: 59.0 Training loss: 0.5710 Explore P: 0.6759
Episode: 7148 Total reward: 27.0 Training loss: 0.2989 Explore P: 0.6758
Episode: 7149 Total reward: 19.0 Training loss: 0.4331 Explore P: 0.6758
Episode: 7150 Total reward: 13.0 Training loss: 0.2051 Explore P: 0.6758
Episode: 7151 Total reward: 24.0 Training loss: 0.0916 Explore P: 0.6758
Episode: 7152 Total reward: 19.0 Training loss: 0.0100 Explore P: 0.6757
Episode: 7153 Total reward: 19.0 Training loss: 0.1149 Explore P: 0.6757
Episode: 7154 Total reward: 22.0 Training loss: 0.1620 Explore P: 0.6757
Episode: 7155 Total reward: 13.0 Training loss: 0.1545 Explore P: 0.6757
Episode: 7156 Total reward: 22.0 Training loss: 1.4389 Explore P: 0.6756
Episode: 7157 Total reward: 38.0 Training loss: 0.0113 Explore P: 0.6756
Episode: 7158 Total reward: 51.0 Training loss: 0.0766 Explore P: 0.6755
Episode: 7159 Total reward: 14.0 Training loss: 1.4708 Explore P: 0.6755
Episode: 7160 Total reward: 20.0 Training loss: 0.1075 Explore P: 0.6755
Episode: 7161 Total reward: 17.0 Training loss: 0.0272 Explore P: 0.6754
Episode: 7162 Total reward: 20.0 Training loss: 0.0049 Explore P: 0.6754
Episode: 7163 Total reward: 14.0 Training loss: 0.3266 Explore P: 0.6754
Episode: 7164 Total reward: 50.0 Training loss: 0.0605 Explore P: 0.6753
Episode: 7165 Total reward: 19.0 Training loss: 0.3173 Explore P: 0.6753
Episode: 7166 Total reward: 36.0 Training loss: 0.2927 Explore P: 0.6753
Episode: 7167 Total reward: 20.0 Training loss: 0.0081 Explore P: 0.6752
Episode: 7168 Total reward: 31.0 Training loss: 0.0535 Explore P: 0.6752
Episode: 7169 Total reward: 38.0 Training loss: 5.9965 Explore P: 0.6751
Episode: 7170 Total reward: 14.0 Training loss: 0.0859 Explore P: 0.6751
Episode: 7171 Total reward: 10.0 Training loss: 0.4534 Explore P: 0.6751
Episode: 7172 Total reward: 23.0 Training loss: 0.0160 Explore P: 0.6751
Episode: 7173 Total reward: 37.0 Training loss: 1.6489 Explore P: 0.6750
Episode: 7174 Total reward: 23.0 Training loss: 0.1960 Explore P: 0.6750
Episode: 7175 Total reward: 10.0 Training loss: 1.8181 Explore P: 0.6750
Episode: 7176 Total reward: 15.0 Training loss: 0.2157 Explore P: 0.6750
Episode: 7177 Total reward: 35.0 Training loss: 0.0128 Explore P: 0.6749
Episode: 7178 Total reward: 13.0 Training loss: 0.2394 Explore P: 0.6749
Episode: 7179 Total reward: 18.0 Training loss: 199.5759 Explore P: 0.6749
Episode: 7180 Total reward: 46.0 Training loss: 32.5776 Explore P: 0.6748
Episode: 7181 Total reward: 21.0 Training loss: 0.5105 Explore P: 0.6748
Episode: 7182 Total reward: 26.0 Training loss: 0.0056 Explore P: 0.6748
Episode: 7183 Total reward: 11.0 Training loss: 0.0747 Explore P: 0.6747
Episode: 7184 Total reward: 21.0 Training loss: 0.0027 Explore P: 0.6747
Episode: 7185 Total reward: 28.0 Training loss: 0.6246 Explore P: 0.6747
Episode: 7186 Total reward: 17.0 Training loss: 0.3337 Explore P: 0.6747
Episode: 7187 Total reward: 23.0 Training loss: 0.1099 Explore P: 0.6746
Episode: 7188 Total reward: 22.0 Training loss: 0.0167 Explore P: 0.6746
Episode: 7189 Total reward: 27.0 Training loss: 0.0622 Explore P: 0.6746
Episode: 7190 Total reward: 14.0 Training loss: 0.1296 Explore P: 0.6745
Episode: 7191 Total reward: 28.0 Training loss: 6.0339 Explore P: 0.6745
Episode: 7192 Total reward: 54.0 Training loss: 0.6422 Explore P: 0.6744
Episode: 7193 Total reward: 52.0 Training loss: 0.0509 Explore P: 0.6744
Episode: 7194 Total reward: 65.0 Training loss: 0.0479 Explore P: 0.6743
Episode: 7195 Total reward: 16.0 Training loss: 0.0882 Explore P: 0.6743
Episode: 7196 Total reward: 10.0 Training loss: 3.0822 Explore P: 0.6742
Episode: 7197 Total reward: 14.0 Training loss: 0.5515 Explore P: 0.6742
Episode: 7198 Total reward: 18.0 Training loss: 0.2930 Explore P: 0.6742
Episode: 7199 Total reward: 19.0 Training loss: 0.0860 Explore P: 0.6742
Episode: 7200 Total reward: 12.0 Training loss: 1.5757 Explore P: 0.6742
Episode: 7201 Total reward: 20.0 Training loss: 0.0406 Explore P: 0.6741
Episode: 7202 Total reward: 37.0 Training loss: 2.7510 Explore P: 0.6741
Episode: 7203 Total reward: 11.0 Training loss: 0.0444 Explore P: 0.6741
Episode: 7204 Total reward: 12.0 Training loss: 4.1402 Explore P: 0.6741
Episode: 7205 Total reward: 15.0 Training loss: 0.1031 Explore P: 0.6740
Episode: 7206 Total reward: 41.0 Training loss: 0.4862 Explore P: 0.6740
Episode: 7207 Total reward: 12.0 Training loss: 0.0197 Explore P: 0.6740
Episode: 7208 Total reward: 26.0 Training loss: 0.0820 Explore P: 0.6739
Episode: 7209 Total reward: 16.0 Training loss: 0.1320 Explore P: 0.6739
Episode: 7210 Total reward: 12.0 Training loss: 3.5353 Explore P: 0.6739
Episode: 7211 Total reward: 19.0 Training loss: 0.0644 Explore P: 0.6739
Episode: 7212 Total reward: 20.0 Training loss: 0.5238 Explore P: 0.6738
Episode: 7213 Total reward: 13.0 Training loss: 0.0059 Explore P: 0.6738
Episode: 7214 Total reward: 31.0 Training loss: 0.0394 Explore P: 0.6738
Episode: 7215 Total reward: 45.0 Training loss: 0.3951 Explore P: 0.6737
Episode: 7216 Total reward: 16.0 Training loss: 0.7394 Explore P: 0.6737
Episode: 7217 Total reward: 9.0 Training loss: 0.5574 Explore P: 0.6737
Episode: 7218 Total reward: 26.0 Training loss: 0.3214 Explore P: 0.6737
Episode: 7219 Total reward: 15.0 Training loss: 0.0312 Explore P: 0.6736
Episode: 7220 Total reward: 41.0 Training loss: 1.9008 Explore P: 0.6736
Episode: 7221 Total reward: 10.0 Training loss: 0.7725 Explore P: 0.6736
Episode: 7222 Total reward: 15.0 Training loss: 1.4238 Explore P: 0.6735
Episode: 7223 Total reward: 15.0 Training loss: 0.0092 Explore P: 0.6735
Episode: 7224 Total reward: 28.0 Training loss: 0.1491 Explore P: 0.6735
Episode: 7225 Total reward: 26.0 Training loss: 0.0452 Explore P: 0.6735
Episode: 7226 Total reward: 16.0 Training loss: 0.0729 Explore P: 0.6734
Episode: 7227 Total reward: 79.0 Training loss: 0.0639 Explore P: 0.6733
Episode: 7228 Total reward: 32.0 Training loss: 0.3244 Explore P: 0.6733
Episode: 7229 Total reward: 33.0 Training loss: 0.4191 Explore P: 0.6732
Episode: 7230 Total reward: 18.0 Training loss: 0.1492 Explore P: 0.6732
Episode: 7231 Total reward: 20.0 Training loss: 6.5116 Explore P: 0.6732
Episode: 7232 Total reward: 19.0 Training loss: 0.8463 Explore P: 0.6732
Episode: 7233 Total reward: 19.0 Training loss: 0.0395 Explore P: 0.6731
Episode: 7234 Total reward: 29.0 Training loss: 0.0391 Explore P: 0.6731
Episode: 7235 Total reward: 22.0 Training loss: 0.0672 Explore P: 0.6731
Episode: 7236 Total reward: 11.0 Training loss: 0.0142 Explore P: 0.6731
Episode: 7237 Total reward: 14.0 Training loss: 0.8463 Explore P: 0.6730
Episode: 7238 Total reward: 23.0 Training loss: 0.0353 Explore P: 0.6730
Episode: 7239 Total reward: 10.0 Training loss: 0.0650 Explore P: 0.6730
Episode: 7240 Total reward: 8.0 Training loss: 0.1141 Explore P: 0.6730
Episode: 7241 Total reward: 32.0 Training loss: 221.5686 Explore P: 0.6729
Episode: 7242 Total reward: 18.0 Training loss: 0.0432 Explore P: 0.6729
Episode: 7243 Total reward: 24.0 Training loss: 0.0195 Explore P: 0.6729
Episode: 7244 Total reward: 17.0 Training loss: 0.1080 Explore P: 0.6729
Episode: 7245 Total reward: 17.0 Training loss: 83.7400 Explore P: 0.6728
Episode: 7246 Total reward: 17.0 Training loss: 0.2155 Explore P: 0.6728
Episode: 7247 Total reward: 31.0 Training loss: 0.1051 Explore P: 0.6728
Episode: 7248 Total reward: 15.0 Training loss: 0.2331 Explore P: 0.6728
Episode: 7249 Total reward: 8.0 Training loss: 1.4306 Explore P: 0.6727
Episode: 7250 Total reward: 19.0 Training loss: 2.2867 Explore P: 0.6727
Episode: 7251 Total reward: 66.0 Training loss: 0.2706 Explore P: 0.6726
Episode: 7252 Total reward: 33.0 Training loss: 0.2256 Explore P: 0.6726
Episode: 7253 Total reward: 14.0 Training loss: 0.0873 Explore P: 0.6726
Episode: 7254 Total reward: 26.0 Training loss: 0.1450 Explore P: 0.6725
Episode: 7255 Total reward: 15.0 Training loss: 0.1169 Explore P: 0.6725
Episode: 7256 Total reward: 28.0 Training loss: 1.8414 Explore P: 0.6725
Episode: 7257 Total reward: 14.0 Training loss: 0.5759 Explore P: 0.6725
Episode: 7258 Total reward: 13.0 Training loss: 0.2479 Explore P: 0.6724
Episode: 7259 Total reward: 41.0 Training loss: 8.7686 Explore P: 0.6724
Episode: 7260 Total reward: 12.0 Training loss: 0.2324 Explore P: 0.6724
Episode: 7261 Total reward: 49.0 Training loss: 0.4265 Explore P: 0.6723
Episode: 7262 Total reward: 24.0 Training loss: 88.8000 Explore P: 0.6723
Episode: 7263 Total reward: 9.0 Training loss: 15.4611 Explore P: 0.6723
Episode: 7264 Total reward: 16.0 Training loss: 0.0398 Explore P: 0.6722
Episode: 7265 Total reward: 16.0 Training loss: 0.0042 Explore P: 0.6722
Episode: 7266 Total reward: 20.0 Training loss: 0.3445 Explore P: 0.6722
Episode: 7267 Total reward: 34.0 Training loss: 0.0959 Explore P: 0.6722
Episode: 7268 Total reward: 22.0 Training loss: 1.5667 Explore P: 0.6721
Episode: 7269 Total reward: 9.0 Training loss: 1.2558 Explore P: 0.6721
Episode: 7270 Total reward: 15.0 Training loss: 0.3184 Explore P: 0.6721
Episode: 7271 Total reward: 36.0 Training loss: 0.7451 Explore P: 0.6720
Episode: 7272 Total reward: 16.0 Training loss: 0.2885 Explore P: 0.6720
Episode: 7273 Total reward: 10.0 Training loss: 0.1157 Explore P: 0.6720
Episode: 7274 Total reward: 22.0 Training loss: 0.1034 Explore P: 0.6720
Episode: 7275 Total reward: 21.0 Training loss: 0.0126 Explore P: 0.6720
Episode: 7276 Total reward: 20.0 Training loss: 0.0363 Explore P: 0.6719
Episode: 7277 Total reward: 38.0 Training loss: 0.1615 Explore P: 0.6719
Episode: 7278 Total reward: 27.0 Training loss: 0.3097 Explore P: 0.6718
Episode: 7279 Total reward: 15.0 Training loss: 0.2355 Explore P: 0.6718
Episode: 7280 Total reward: 35.0 Training loss: 0.0225 Explore P: 0.6718
Episode: 7281 Total reward: 34.0 Training loss: 0.2855 Explore P: 0.6717
Episode: 7282 Total reward: 13.0 Training loss: 0.1272 Explore P: 0.6717
Episode: 7283 Total reward: 10.0 Training loss: 0.1224 Explore P: 0.6717
Episode: 7284 Total reward: 17.0 Training loss: 1.6055 Explore P: 0.6717
Episode: 7285 Total reward: 28.0 Training loss: 0.8712 Explore P: 0.6716
Episode: 7286 Total reward: 10.0 Training loss: 0.2932 Explore P: 0.6716
Episode: 7287 Total reward: 14.0 Training loss: 3.9228 Explore P: 0.6716
Episode: 7288 Total reward: 15.0 Training loss: 0.7787 Explore P: 0.6716
Episode: 7289 Total reward: 10.0 Training loss: 20.5049 Explore P: 0.6716
Episode: 7290 Total reward: 47.0 Training loss: 0.5945 Explore P: 0.6715
Episode: 7291 Total reward: 23.0 Training loss: 0.2252 Explore P: 0.6715
Episode: 7292 Total reward: 15.0 Training loss: 0.1350 Explore P: 0.6715
Episode: 7293 Total reward: 24.0 Training loss: 0.2578 Explore P: 0.6714
Episode: 7294 Total reward: 14.0 Training loss: 0.2945 Explore P: 0.6714
Episode: 7295 Total reward: 23.0 Training loss: 0.1296 Explore P: 0.6714
Episode: 7296 Total reward: 37.0 Training loss: 0.0517 Explore P: 0.6713
Episode: 7297 Total reward: 15.0 Training loss: 0.0151 Explore P: 0.6713
Episode: 7298 Total reward: 30.0 Training loss: 0.6641 Explore P: 0.6713
Episode: 7299 Total reward: 26.0 Training loss: 0.0243 Explore P: 0.6712
Episode: 7300 Total reward: 22.0 Training loss: 0.0479 Explore P: 0.6712
Episode: 7301 Total reward: 8.0 Training loss: 0.2674 Explore P: 0.6712
Episode: 7302 Total reward: 12.0 Training loss: 0.0113 Explore P: 0.6712
Episode: 7303 Total reward: 9.0 Training loss: 0.6435 Explore P: 0.6712
Episode: 7304 Total reward: 19.0 Training loss: 1.3645 Explore P: 0.6711
Episode: 7305 Total reward: 15.0 Training loss: 1.3961 Explore P: 0.6711
Episode: 7306 Total reward: 17.0 Training loss: 0.6214 Explore P: 0.6711
Episode: 7307 Total reward: 9.0 Training loss: 0.6257 Explore P: 0.6711
Episode: 7308 Total reward: 10.0 Training loss: 0.4177 Explore P: 0.6711
Episode: 7309 Total reward: 12.0 Training loss: 0.2869 Explore P: 0.6711
Episode: 7310 Total reward: 26.0 Training loss: 0.0517 Explore P: 0.6710
Episode: 7311 Total reward: 34.0 Training loss: 0.0219 Explore P: 0.6710
Episode: 7312 Total reward: 12.0 Training loss: 0.3941 Explore P: 0.6710
Episode: 7313 Total reward: 14.0 Training loss: 0.8210 Explore P: 0.6709
Episode: 7314 Total reward: 15.0 Training loss: 0.1574 Explore P: 0.6709
Episode: 7315 Total reward: 13.0 Training loss: 0.3019 Explore P: 0.6709
Episode: 7316 Total reward: 22.0 Training loss: 0.4099 Explore P: 0.6709
Episode: 7317 Total reward: 52.0 Training loss: 0.7306 Explore P: 0.6708
Episode: 7318 Total reward: 19.0 Training loss: 0.0773 Explore P: 0.6708
Episode: 7319 Total reward: 8.0 Training loss: 0.1046 Explore P: 0.6708
Episode: 7320 Total reward: 12.0 Training loss: 0.0807 Explore P: 0.6708
Episode: 7321 Total reward: 21.0 Training loss: 1.2399 Explore P: 0.6707
Episode: 7322 Total reward: 12.0 Training loss: 0.1876 Explore P: 0.6707
Episode: 7323 Total reward: 11.0 Training loss: 0.1763 Explore P: 0.6707
Episode: 7324 Total reward: 39.0 Training loss: 0.0218 Explore P: 0.6707
Episode: 7325 Total reward: 12.0 Training loss: 100.8335 Explore P: 0.6706
Episode: 7326 Total reward: 22.0 Training loss: 0.0426 Explore P: 0.6706
Episode: 7327 Total reward: 15.0 Training loss: 0.9541 Explore P: 0.6706
Episode: 7328 Total reward: 19.0 Training loss: 0.0557 Explore P: 0.6706
Episode: 7329 Total reward: 11.0 Training loss: 0.5575 Explore P: 0.6705
Episode: 7330 Total reward: 12.0 Training loss: 2.1545 Explore P: 0.6705
Episode: 7331 Total reward: 18.0 Training loss: 3.4477 Explore P: 0.6705
Episode: 7332 Total reward: 18.0 Training loss: 0.3351 Explore P: 0.6705
Episode: 7333 Total reward: 25.0 Training loss: 1.3605 Explore P: 0.6705
Episode: 7334 Total reward: 17.0 Training loss: 0.5123 Explore P: 0.6704
Episode: 7335 Total reward: 19.0 Training loss: 0.0371 Explore P: 0.6704
Episode: 7336 Total reward: 21.0 Training loss: 4.7357 Explore P: 0.6704
Episode: 7337 Total reward: 14.0 Training loss: 0.0063 Explore P: 0.6704
Episode: 7338 Total reward: 56.0 Training loss: 0.0680 Explore P: 0.6703
Episode: 7339 Total reward: 17.0 Training loss: 0.1092 Explore P: 0.6703
Episode: 7340 Total reward: 9.0 Training loss: 0.0165 Explore P: 0.6702
Episode: 7341 Total reward: 16.0 Training loss: 0.4339 Explore P: 0.6702
Episode: 7342 Total reward: 18.0 Training loss: 0.4243 Explore P: 0.6702
Episode: 7343 Total reward: 15.0 Training loss: 0.2082 Explore P: 0.6702
Episode: 7344 Total reward: 18.0 Training loss: 1.4149 Explore P: 0.6702
Episode: 7345 Total reward: 12.0 Training loss: 9.5882 Explore P: 0.6701
Episode: 7346 Total reward: 30.0 Training loss: 0.2285 Explore P: 0.6701
Episode: 7347 Total reward: 47.0 Training loss: 0.0276 Explore P: 0.6700
Episode: 7348 Total reward: 27.0 Training loss: 0.0696 Explore P: 0.6700
Episode: 7349 Total reward: 17.0 Training loss: 0.1090 Explore P: 0.6700
Episode: 7350 Total reward: 22.0 Training loss: 1.0363 Explore P: 0.6700
Episode: 7351 Total reward: 43.0 Training loss: 0.8502 Explore P: 0.6699
Episode: 7352 Total reward: 12.0 Training loss: 0.5725 Explore P: 0.6699
Episode: 7353 Total reward: 36.0 Training loss: 0.5388 Explore P: 0.6698
Episode: 7354 Total reward: 12.0 Training loss: 0.2316 Explore P: 0.6698
Episode: 7355 Total reward: 66.0 Training loss: 0.1893 Explore P: 0.6697
Episode: 7356 Total reward: 29.0 Training loss: 6.2410 Explore P: 0.6697
Episode: 7357 Total reward: 20.0 Training loss: 0.3427 Explore P: 0.6697
Episode: 7358 Total reward: 34.0 Training loss: 0.3439 Explore P: 0.6696
Episode: 7359 Total reward: 13.0 Training loss: 0.4293 Explore P: 0.6696
Episode: 7360 Total reward: 21.0 Training loss: 0.0111 Explore P: 0.6696
Episode: 7361 Total reward: 39.0 Training loss: 0.0518 Explore P: 0.6695
Episode: 7362 Total reward: 19.0 Training loss: 0.0159 Explore P: 0.6695
Episode: 7363 Total reward: 20.0 Training loss: 0.0988 Explore P: 0.6695
Episode: 7364 Total reward: 14.0 Training loss: 1.3013 Explore P: 0.6695
Episode: 7365 Total reward: 22.0 Training loss: 0.0522 Explore P: 0.6694
Episode: 7366 Total reward: 28.0 Training loss: 1.1946 Explore P: 0.6694
Episode: 7367 Total reward: 25.0 Training loss: 1.9407 Explore P: 0.6694
Episode: 7368 Total reward: 13.0 Training loss: 24.5305 Explore P: 0.6693
Episode: 7369 Total reward: 15.0 Training loss: 1.9818 Explore P: 0.6693
Episode: 7370 Total reward: 27.0 Training loss: 0.8484 Explore P: 0.6693
Episode: 7371 Total reward: 17.0 Training loss: 0.1808 Explore P: 0.6693
Episode: 7372 Total reward: 11.0 Training loss: 0.1268 Explore P: 0.6692
Episode: 7373 Total reward: 15.0 Training loss: 0.0558 Explore P: 0.6692
Episode: 7374 Total reward: 55.0 Training loss: 0.0174 Explore P: 0.6692
Episode: 7375 Total reward: 26.0 Training loss: 0.2002 Explore P: 0.6691
Episode: 7376 Total reward: 11.0 Training loss: 1.1230 Explore P: 0.6691
Episode: 7377 Total reward: 19.0 Training loss: 0.0285 Explore P: 0.6691
Episode: 7378 Total reward: 34.0 Training loss: 0.5274 Explore P: 0.6690
Episode: 7379 Total reward: 13.0 Training loss: 0.0778 Explore P: 0.6690
Episode: 7380 Total reward: 8.0 Training loss: 0.0942 Explore P: 0.6690
Episode: 7381 Total reward: 42.0 Training loss: 0.6170 Explore P: 0.6690
Episode: 7382 Total reward: 12.0 Training loss: 0.0372 Explore P: 0.6689
Episode: 7383 Total reward: 10.0 Training loss: 0.9119 Explore P: 0.6689
Episode: 7384 Total reward: 16.0 Training loss: 0.0340 Explore P: 0.6689
Episode: 7385 Total reward: 14.0 Training loss: 0.1420 Explore P: 0.6689
Episode: 7386 Total reward: 20.0 Training loss: 0.1963 Explore P: 0.6689
Episode: 7387 Total reward: 16.0 Training loss: 0.0498 Explore P: 0.6688
Episode: 7388 Total reward: 19.0 Training loss: 0.4622 Explore P: 0.6688
Episode: 7389 Total reward: 21.0 Training loss: 0.0433 Explore P: 0.6688
Episode: 7390 Total reward: 29.0 Training loss: 0.7007 Explore P: 0.6687
Episode: 7391 Total reward: 31.0 Training loss: 0.1823 Explore P: 0.6687
Episode: 7392 Total reward: 28.0 Training loss: 0.5037 Explore P: 0.6687
Episode: 7393 Total reward: 17.0 Training loss: 0.0936 Explore P: 0.6686
Episode: 7394 Total reward: 20.0 Training loss: 0.0979 Explore P: 0.6686
Episode: 7395 Total reward: 25.0 Training loss: 0.4119 Explore P: 0.6686
Episode: 7396 Total reward: 9.0 Training loss: 4.9675 Explore P: 0.6686
Episode: 7397 Total reward: 26.0 Training loss: 1.0074 Explore P: 0.6685
Episode: 7398 Total reward: 25.0 Training loss: 0.2035 Explore P: 0.6685
Episode: 7399 Total reward: 17.0 Training loss: 0.0437 Explore P: 0.6685
Episode: 7400 Total reward: 17.0 Training loss: 28.4479 Explore P: 0.6685
Episode: 7401 Total reward: 46.0 Training loss: 0.2615 Explore P: 0.6684
Episode: 7402 Total reward: 41.0 Training loss: 0.2572 Explore P: 0.6683
Episode: 7403 Total reward: 14.0 Training loss: 0.0568 Explore P: 0.6683
Episode: 7404 Total reward: 16.0 Training loss: 0.0103 Explore P: 0.6683
Episode: 7405 Total reward: 10.0 Training loss: 0.4401 Explore P: 0.6683
Episode: 7406 Total reward: 27.0 Training loss: 0.5413 Explore P: 0.6683
Episode: 7407 Total reward: 15.0 Training loss: 0.0278 Explore P: 0.6682
Episode: 7408 Total reward: 64.0 Training loss: 0.2499 Explore P: 0.6682
Episode: 7409 Total reward: 12.0 Training loss: 0.0314 Explore P: 0.6681
Episode: 7410 Total reward: 33.0 Training loss: 0.0721 Explore P: 0.6681
Episode: 7411 Total reward: 35.0 Training loss: 1.8556 Explore P: 0.6681
Episode: 7412 Total reward: 18.0 Training loss: 0.0992 Explore P: 0.6680
Episode: 7413 Total reward: 19.0 Training loss: 1.5944 Explore P: 0.6680
Episode: 7414 Total reward: 13.0 Training loss: 0.0353 Explore P: 0.6680
Episode: 7415 Total reward: 20.0 Training loss: 0.3079 Explore P: 0.6680
Episode: 7416 Total reward: 40.0 Training loss: 13.4595 Explore P: 0.6679
Episode: 7417 Total reward: 16.0 Training loss: 0.2589 Explore P: 0.6679
Episode: 7418 Total reward: 25.0 Training loss: 0.1586 Explore P: 0.6679
Episode: 7419 Total reward: 45.0 Training loss: 0.2593 Explore P: 0.6678
Episode: 7420 Total reward: 22.0 Training loss: 0.0251 Explore P: 0.6678
Episode: 7421 Total reward: 16.0 Training loss: 1.1571 Explore P: 0.6677
Episode: 7422 Total reward: 20.0 Training loss: 0.1844 Explore P: 0.6677
Episode: 7423 Total reward: 16.0 Training loss: 0.9601 Explore P: 0.6677
Episode: 7424 Total reward: 27.0 Training loss: 1.0294 Explore P: 0.6677
Episode: 7425 Total reward: 10.0 Training loss: 0.1952 Explore P: 0.6676
Episode: 7426 Total reward: 33.0 Training loss: 0.0266 Explore P: 0.6676
Episode: 7427 Total reward: 38.0 Training loss: 0.4470 Explore P: 0.6676
Episode: 7428 Total reward: 38.0 Training loss: 1.0658 Explore P: 0.6675
Episode: 7429 Total reward: 54.0 Training loss: 0.0180 Explore P: 0.6674
Episode: 7430 Total reward: 9.0 Training loss: 0.3628 Explore P: 0.6674
Episode: 7431 Total reward: 23.0 Training loss: 0.2515 Explore P: 0.6674
Episode: 7432 Total reward: 12.0 Training loss: 0.0501 Explore P: 0.6674
Episode: 7433 Total reward: 24.0 Training loss: 0.2065 Explore P: 0.6673
Episode: 7434 Total reward: 39.0 Training loss: 0.0623 Explore P: 0.6673
Episode: 7435 Total reward: 54.0 Training loss: 1.0359 Explore P: 0.6672
Episode: 7436 Total reward: 18.0 Training loss: 0.0310 Explore P: 0.6672
Episode: 7437 Total reward: 16.0 Training loss: 405.1144 Explore P: 0.6672
Episode: 7438 Total reward: 25.0 Training loss: 0.3128 Explore P: 0.6671
Episode: 7439 Total reward: 22.0 Training loss: 0.0224 Explore P: 0.6671
Episode: 7440 Total reward: 28.0 Training loss: 0.6036 Explore P: 0.6671
Episode: 7441 Total reward: 13.0 Training loss: 1.2606 Explore P: 0.6671
Episode: 7442 Total reward: 8.0 Training loss: 0.1903 Explore P: 0.6671
Episode: 7443 Total reward: 8.0 Training loss: 0.7702 Explore P: 0.6670
Episode: 7444 Total reward: 15.0 Training loss: 0.1278 Explore P: 0.6670
Episode: 7445 Total reward: 19.0 Training loss: 2.1507 Explore P: 0.6670
Episode: 7446 Total reward: 12.0 Training loss: 1.8136 Explore P: 0.6670
Episode: 7447 Total reward: 19.0 Training loss: 1.2439 Explore P: 0.6670
Episode: 7448 Total reward: 20.0 Training loss: 0.0637 Explore P: 0.6669
Episode: 7449 Total reward: 8.0 Training loss: 0.0288 Explore P: 0.6669
Episode: 7450 Total reward: 17.0 Training loss: 0.0133 Explore P: 0.6669
Episode: 7451 Total reward: 13.0 Training loss: 0.8862 Explore P: 0.6669
Episode: 7452 Total reward: 37.0 Training loss: 0.0368 Explore P: 0.6668
Episode: 7453 Total reward: 11.0 Training loss: 0.5950 Explore P: 0.6668
Episode: 7454 Total reward: 20.0 Training loss: 8.4946 Explore P: 0.6668
Episode: 7455 Total reward: 17.0 Training loss: 0.4517 Explore P: 0.6668
Episode: 7456 Total reward: 20.0 Training loss: 2.2012 Explore P: 0.6667
Episode: 7457 Total reward: 37.0 Training loss: 0.0494 Explore P: 0.6667
Episode: 7458 Total reward: 20.0 Training loss: 2.4663 Explore P: 0.6667
Episode: 7459 Total reward: 13.0 Training loss: 0.0041 Explore P: 0.6666
Episode: 7460 Total reward: 34.0 Training loss: 0.5451 Explore P: 0.6666
Episode: 7461 Total reward: 23.0 Training loss: 0.4865 Explore P: 0.6666
Episode: 7462 Total reward: 78.0 Training loss: 0.0638 Explore P: 0.6665
Episode: 7463 Total reward: 32.0 Training loss: 0.0281 Explore P: 0.6664
Episode: 7464 Total reward: 10.0 Training loss: 0.8938 Explore P: 0.6664
Episode: 7465 Total reward: 25.0 Training loss: 0.0088 Explore P: 0.6664
Episode: 7466 Total reward: 27.0 Training loss: 0.1647 Explore P: 0.6663
Episode: 7467 Total reward: 18.0 Training loss: 0.5982 Explore P: 0.6663
Episode: 7468 Total reward: 32.0 Training loss: 0.0644 Explore P: 0.6663
Episode: 7469 Total reward: 22.0 Training loss: 0.1755 Explore P: 0.6663
Episode: 7470 Total reward: 9.0 Training loss: 0.9807 Explore P: 0.6662
Episode: 7471 Total reward: 13.0 Training loss: 0.0651 Explore P: 0.6662
Episode: 7472 Total reward: 17.0 Training loss: 1.5290 Explore P: 0.6662
Episode: 7473 Total reward: 42.0 Training loss: 0.0229 Explore P: 0.6661
Episode: 7474 Total reward: 17.0 Training loss: 0.0069 Explore P: 0.6661
Episode: 7475 Total reward: 41.0 Training loss: 0.1319 Explore P: 0.6661
Episode: 7476 Total reward: 34.0 Training loss: 0.1958 Explore P: 0.6660
Episode: 7477 Total reward: 49.0 Training loss: 0.0168 Explore P: 0.6660
Episode: 7478 Total reward: 19.0 Training loss: 0.0647 Explore P: 0.6659
Episode: 7479 Total reward: 10.0 Training loss: 0.0108 Explore P: 0.6659
Episode: 7480 Total reward: 14.0 Training loss: 1.2917 Explore P: 0.6659
Episode: 7481 Total reward: 15.0 Training loss: 0.0064 Explore P: 0.6659
Episode: 7482 Total reward: 10.0 Training loss: 0.0297 Explore P: 0.6659
Episode: 7483 Total reward: 10.0 Training loss: 0.1191 Explore P: 0.6659
Episode: 7484 Total reward: 26.0 Training loss: 0.0588 Explore P: 0.6658
Episode: 7485 Total reward: 32.0 Training loss: 0.0165 Explore P: 0.6658
Episode: 7486 Total reward: 29.0 Training loss: 1.0715 Explore P: 0.6657
Episode: 7487 Total reward: 15.0 Training loss: 0.2232 Explore P: 0.6657
Episode: 7488 Total reward: 22.0 Training loss: 0.2577 Explore P: 0.6657
Episode: 7489 Total reward: 12.0 Training loss: 0.5421 Explore P: 0.6657
Episode: 7490 Total reward: 37.0 Training loss: 0.4925 Explore P: 0.6656
Episode: 7491 Total reward: 26.0 Training loss: 1.1229 Explore P: 0.6656
Episode: 7492 Total reward: 32.0 Training loss: 1.0261 Explore P: 0.6656
Episode: 7493 Total reward: 16.0 Training loss: 5.9271 Explore P: 0.6655
Episode: 7494 Total reward: 9.0 Training loss: 71.8353 Explore P: 0.6655
Episode: 7495 Total reward: 9.0 Training loss: 0.0188 Explore P: 0.6655
Episode: 7496 Total reward: 10.0 Training loss: 0.0738 Explore P: 0.6655
Episode: 7497 Total reward: 18.0 Training loss: 0.2832 Explore P: 0.6655
Episode: 7498 Total reward: 18.0 Training loss: 0.0028 Explore P: 0.6655
Episode: 7499 Total reward: 8.0 Training loss: 0.0214 Explore P: 0.6654
Episode: 7500 Total reward: 25.0 Training loss: 1.0221 Explore P: 0.6654
Episode: 7501 Total reward: 37.0 Training loss: 3.1241 Explore P: 0.6654
Episode: 7502 Total reward: 25.0 Training loss: 0.0873 Explore P: 0.6653
Episode: 7503 Total reward: 9.0 Training loss: 0.2483 Explore P: 0.6653
Episode: 7504 Total reward: 16.0 Training loss: 0.9433 Explore P: 0.6653
Episode: 7505 Total reward: 27.0 Training loss: 0.1419 Explore P: 0.6653
Episode: 7506 Total reward: 11.0 Training loss: 0.0664 Explore P: 0.6652
Episode: 7507 Total reward: 29.0 Training loss: 0.1394 Explore P: 0.6652
Episode: 7508 Total reward: 21.0 Training loss: 0.0292 Explore P: 0.6652
Episode: 7509 Total reward: 13.0 Training loss: 0.3429 Explore P: 0.6652
Episode: 7510 Total reward: 22.0 Training loss: 0.0321 Explore P: 0.6651
Episode: 7511 Total reward: 37.0 Training loss: 0.0708 Explore P: 0.6651
Episode: 7512 Total reward: 17.0 Training loss: 8.1282 Explore P: 0.6651
Episode: 7513 Total reward: 15.0 Training loss: 0.4698 Explore P: 0.6650
Episode: 7514 Total reward: 32.0 Training loss: 0.7684 Explore P: 0.6650
Episode: 7515 Total reward: 45.0 Training loss: 2.3063 Explore P: 0.6649
Episode: 7516 Total reward: 14.0 Training loss: 1.9683 Explore P: 0.6649
Episode: 7517 Total reward: 28.0 Training loss: 0.0203 Explore P: 0.6649
Episode: 7518 Total reward: 22.0 Training loss: 6.6168 Explore P: 0.6649
Episode: 7519 Total reward: 49.0 Training loss: 0.9600 Explore P: 0.6648
Episode: 7520 Total reward: 9.0 Training loss: 0.6706 Explore P: 0.6648
Episode: 7521 Total reward: 24.0 Training loss: 0.0302 Explore P: 0.6648
Episode: 7522 Total reward: 26.0 Training loss: 0.4449 Explore P: 0.6647
Episode: 7523 Total reward: 15.0 Training loss: 1.0904 Explore P: 0.6647
Episode: 7524 Total reward: 13.0 Training loss: 1.6381 Explore P: 0.6647
Episode: 7525 Total reward: 19.0 Training loss: 0.5530 Explore P: 0.6647
Episode: 7526 Total reward: 17.0 Training loss: 1.4517 Explore P: 0.6646
Episode: 7527 Total reward: 23.0 Training loss: 7.2825 Explore P: 0.6646
Episode: 7528 Total reward: 22.0 Training loss: 0.9361 Explore P: 0.6646
Episode: 7529 Total reward: 12.0 Training loss: 0.0447 Explore P: 0.6646
Episode: 7530 Total reward: 15.0 Training loss: 13.9546 Explore P: 0.6645
Episode: 7531 Total reward: 28.0 Training loss: 0.0127 Explore P: 0.6645
Episode: 7532 Total reward: 21.0 Training loss: 0.6570 Explore P: 0.6645
Episode: 7533 Total reward: 30.0 Training loss: 0.1895 Explore P: 0.6644
Episode: 7534 Total reward: 15.0 Training loss: 0.4523 Explore P: 0.6644
Episode: 7535 Total reward: 13.0 Training loss: 0.0320 Explore P: 0.6644
Episode: 7536 Total reward: 17.0 Training loss: 0.1455 Explore P: 0.6644
Episode: 7537 Total reward: 23.0 Training loss: 0.1307 Explore P: 0.6643
Episode: 7538 Total reward: 20.0 Training loss: 0.1180 Explore P: 0.6643
Episode: 7539 Total reward: 36.0 Training loss: 0.2538 Explore P: 0.6643
Episode: 7540 Total reward: 18.0 Training loss: 0.0869 Explore P: 0.6642
Episode: 7541 Total reward: 41.0 Training loss: 0.0551 Explore P: 0.6642
Episode: 7542 Total reward: 21.0 Training loss: 0.3112 Explore P: 0.6642
Episode: 7543 Total reward: 21.0 Training loss: 1.5871 Explore P: 0.6641
Episode: 7544 Total reward: 10.0 Training loss: 0.8136 Explore P: 0.6641
Episode: 7545 Total reward: 17.0 Training loss: 0.9847 Explore P: 0.6641
Episode: 7546 Total reward: 10.0 Training loss: 0.7437 Explore P: 0.6641
Episode: 7547 Total reward: 17.0 Training loss: 0.0440 Explore P: 0.6641
Episode: 7548 Total reward: 17.0 Training loss: 0.6899 Explore P: 0.6640
Episode: 7549 Total reward: 24.0 Training loss: 0.3320 Explore P: 0.6640
Episode: 7550 Total reward: 12.0 Training loss: 0.3404 Explore P: 0.6640
Episode: 7551 Total reward: 22.0 Training loss: 1.2156 Explore P: 0.6640
Episode: 7552 Total reward: 48.0 Training loss: 0.0195 Explore P: 0.6639
Episode: 7553 Total reward: 60.0 Training loss: 0.1535 Explore P: 0.6638
Episode: 7554 Total reward: 68.0 Training loss: 0.0369 Explore P: 0.6637
Episode: 7555 Total reward: 11.0 Training loss: 0.2903 Explore P: 0.6637
Episode: 7556 Total reward: 19.0 Training loss: 0.0880 Explore P: 0.6637
Episode: 7557 Total reward: 20.0 Training loss: 0.5739 Explore P: 0.6637
Episode: 7558 Total reward: 15.0 Training loss: 0.4886 Explore P: 0.6637
Episode: 7559 Total reward: 19.0 Training loss: 0.2719 Explore P: 0.6636
Episode: 7560 Total reward: 43.0 Training loss: 0.1014 Explore P: 0.6636
Episode: 7561 Total reward: 10.0 Training loss: 1.0073 Explore P: 0.6636
Episode: 7562 Total reward: 13.0 Training loss: 0.1207 Explore P: 0.6635
Episode: 7563 Total reward: 33.0 Training loss: 0.2600 Explore P: 0.6635
Episode: 7564 Total reward: 19.0 Training loss: 0.0066 Explore P: 0.6635
Episode: 7565 Total reward: 29.0 Training loss: 0.0084 Explore P: 0.6634
Episode: 7566 Total reward: 27.0 Training loss: 0.0264 Explore P: 0.6634
Episode: 7567 Total reward: 21.0 Training loss: 0.2643 Explore P: 0.6634
Episode: 7568 Total reward: 14.0 Training loss: 1.7349 Explore P: 0.6634
Episode: 7569 Total reward: 43.0 Training loss: 0.1335 Explore P: 0.6633
Episode: 7570 Total reward: 33.0 Training loss: 0.3777 Explore P: 0.6633
Episode: 7571 Total reward: 11.0 Training loss: 0.4364 Explore P: 0.6632
Episode: 7572 Total reward: 15.0 Training loss: 0.3430 Explore P: 0.6632
Episode: 7573 Total reward: 34.0 Training loss: 0.0402 Explore P: 0.6632
Episode: 7574 Total reward: 19.0 Training loss: 0.4418 Explore P: 0.6632
Episode: 7575 Total reward: 9.0 Training loss: 0.6512 Explore P: 0.6631
Episode: 7576 Total reward: 28.0 Training loss: 0.2521 Explore P: 0.6631
Episode: 7577 Total reward: 27.0 Training loss: 0.7490 Explore P: 0.6631
Episode: 7578 Total reward: 15.0 Training loss: 0.0091 Explore P: 0.6631
Episode: 7579 Total reward: 38.0 Training loss: 0.1811 Explore P: 0.6630
Episode: 7580 Total reward: 10.0 Training loss: 0.2413 Explore P: 0.6630
Episode: 7581 Total reward: 14.0 Training loss: 0.2415 Explore P: 0.6630
Episode: 7582 Total reward: 13.0 Training loss: 0.2854 Explore P: 0.6630
Episode: 7583 Total reward: 21.0 Training loss: 0.1656 Explore P: 0.6629
Episode: 7584 Total reward: 25.0 Training loss: 0.5586 Explore P: 0.6629
Episode: 7585 Total reward: 19.0 Training loss: 0.3935 Explore P: 0.6629
Episode: 7586 Total reward: 28.0 Training loss: 0.0527 Explore P: 0.6628
Episode: 7587 Total reward: 21.0 Training loss: 1.9363 Explore P: 0.6628
Episode: 7588 Total reward: 12.0 Training loss: 1.3094 Explore P: 0.6628
Episode: 7589 Total reward: 24.0 Training loss: 0.4259 Explore P: 0.6628
Episode: 7590 Total reward: 38.0 Training loss: 0.2779 Explore P: 0.6627
Episode: 7591 Total reward: 40.0 Training loss: 0.0641 Explore P: 0.6627
Episode: 7592 Total reward: 24.0 Training loss: 0.0103 Explore P: 0.6626
Episode: 7593 Total reward: 22.0 Training loss: 0.1287 Explore P: 0.6626
Episode: 7594 Total reward: 35.0 Training loss: 0.1119 Explore P: 0.6626
Episode: 7595 Total reward: 27.0 Training loss: 0.7309 Explore P: 0.6625
Episode: 7596 Total reward: 27.0 Training loss: 0.0630 Explore P: 0.6625
Episode: 7597 Total reward: 36.0 Training loss: 0.0498 Explore P: 0.6624
Episode: 7598 Total reward: 24.0 Training loss: 0.1624 Explore P: 0.6624
Episode: 7599 Total reward: 15.0 Training loss: 0.2210 Explore P: 0.6624
Episode: 7600 Total reward: 30.0 Training loss: 0.2833 Explore P: 0.6623
Episode: 7601 Total reward: 12.0 Training loss: 0.6224 Explore P: 0.6623
Episode: 7602 Total reward: 23.0 Training loss: 0.0637 Explore P: 0.6623
Episode: 7603 Total reward: 20.0 Training loss: 0.1121 Explore P: 0.6623
Episode: 7604 Total reward: 30.0 Training loss: 0.0173 Explore P: 0.6622
Episode: 7605 Total reward: 17.0 Training loss: 0.0755 Explore P: 0.6622
Episode: 7606 Total reward: 31.0 Training loss: 0.2363 Explore P: 0.6622
Episode: 7607 Total reward: 11.0 Training loss: 0.2950 Explore P: 0.6622
Episode: 7608 Total reward: 44.0 Training loss: 0.0862 Explore P: 0.6621
Episode: 7609 Total reward: 26.0 Training loss: 0.0555 Explore P: 0.6621
Episode: 7610 Total reward: 44.0 Training loss: 0.2672 Explore P: 0.6620
Episode: 7611 Total reward: 13.0 Training loss: 0.4279 Explore P: 0.6620
Episode: 7612 Total reward: 18.0 Training loss: 0.6351 Explore P: 0.6620
Episode: 7613 Total reward: 17.0 Training loss: 0.2695 Explore P: 0.6619
Episode: 7614 Total reward: 16.0 Training loss: 0.1129 Explore P: 0.6619
Episode: 7615 Total reward: 21.0 Training loss: 0.2289 Explore P: 0.6619
Episode: 7616 Total reward: 10.0 Training loss: 0.0271 Explore P: 0.6619
Episode: 7617 Total reward: 20.0 Training loss: 0.1984 Explore P: 0.6619
Episode: 7618 Total reward: 50.0 Training loss: 0.1818 Explore P: 0.6618
Episode: 7619 Total reward: 20.0 Training loss: 0.0304 Explore P: 0.6618
Episode: 7620 Total reward: 54.0 Training loss: 0.9337 Explore P: 0.6617
Episode: 7621 Total reward: 16.0 Training loss: 0.0334 Explore P: 0.6617
Episode: 7622 Total reward: 23.0 Training loss: 0.7373 Explore P: 0.6616
Episode: 7623 Total reward: 14.0 Training loss: 5.7685 Explore P: 0.6616
Episode: 7624 Total reward: 12.0 Training loss: 0.0756 Explore P: 0.6616
Episode: 7625 Total reward: 37.0 Training loss: 0.0827 Explore P: 0.6616
Episode: 7626 Total reward: 9.0 Training loss: 0.3989 Explore P: 0.6616
Episode: 7627 Total reward: 19.0 Training loss: 0.0138 Explore P: 0.6615
Episode: 7628 Total reward: 21.0 Training loss: 0.1990 Explore P: 0.6615
Episode: 7629 Total reward: 31.0 Training loss: 0.1773 Explore P: 0.6615
Episode: 7630 Total reward: 19.0 Training loss: 0.3458 Explore P: 0.6614
Episode: 7631 Total reward: 17.0 Training loss: 0.0031 Explore P: 0.6614
Episode: 7632 Total reward: 28.0 Training loss: 0.0194 Explore P: 0.6614
Episode: 7633 Total reward: 37.0 Training loss: 0.1466 Explore P: 0.6613
Episode: 7634 Total reward: 27.0 Training loss: 0.0737 Explore P: 0.6613
Episode: 7635 Total reward: 20.0 Training loss: 0.0109 Explore P: 0.6613
Episode: 7636 Total reward: 12.0 Training loss: 11.3404 Explore P: 0.6613
Episode: 7637 Total reward: 21.0 Training loss: 0.1055 Explore P: 0.6612
Episode: 7638 Total reward: 34.0 Training loss: 0.1645 Explore P: 0.6612
Episode: 7639 Total reward: 14.0 Training loss: 1.1022 Explore P: 0.6612
Episode: 7640 Total reward: 21.0 Training loss: 0.5393 Explore P: 0.6611
Episode: 7641 Total reward: 7.0 Training loss: 0.0414 Explore P: 0.6611
Episode: 7642 Total reward: 22.0 Training loss: 0.2883 Explore P: 0.6611
Episode: 7643 Total reward: 16.0 Training loss: 0.2319 Explore P: 0.6611
Episode: 7644 Total reward: 36.0 Training loss: 0.1518 Explore P: 0.6610
Episode: 7645 Total reward: 40.0 Training loss: 0.0312 Explore P: 0.6610
Episode: 7646 Total reward: 42.0 Training loss: 0.0988 Explore P: 0.6609
Episode: 7647 Total reward: 20.0 Training loss: 0.0417 Explore P: 0.6609
Episode: 7648 Total reward: 15.0 Training loss: 0.3734 Explore P: 0.6609
Episode: 7649 Total reward: 35.0 Training loss: 0.0503 Explore P: 0.6608
Episode: 7650 Total reward: 35.0 Training loss: 0.0831 Explore P: 0.6608
Episode: 7651 Total reward: 11.0 Training loss: 0.0689 Explore P: 0.6608
Episode: 7652 Total reward: 18.0 Training loss: 0.0038 Explore P: 0.6607
Episode: 7653 Total reward: 10.0 Training loss: 0.3180 Explore P: 0.6607
Episode: 7654 Total reward: 25.0 Training loss: 4.2566 Explore P: 0.6607
Episode: 7655 Total reward: 28.0 Training loss: 0.7906 Explore P: 0.6607
Episode: 7656 Total reward: 26.0 Training loss: 0.0900 Explore P: 0.6606
Episode: 7657 Total reward: 15.0 Training loss: 0.0398 Explore P: 0.6606
Episode: 7658 Total reward: 31.0 Training loss: 0.0091 Explore P: 0.6606
Episode: 7659 Total reward: 14.0 Training loss: 0.1039 Explore P: 0.6606
Episode: 7660 Total reward: 20.0 Training loss: 0.3651 Explore P: 0.6605
Episode: 7661 Total reward: 14.0 Training loss: 0.0661 Explore P: 0.6605
Episode: 7662 Total reward: 23.0 Training loss: 0.0227 Explore P: 0.6605
Episode: 7663 Total reward: 34.0 Training loss: 0.0841 Explore P: 0.6604
Episode: 7664 Total reward: 10.0 Training loss: 0.1931 Explore P: 0.6604
Episode: 7665 Total reward: 15.0 Training loss: 0.0518 Explore P: 0.6604
Episode: 7666 Total reward: 12.0 Training loss: 0.0570 Explore P: 0.6604
Episode: 7667 Total reward: 33.0 Training loss: 10.8491 Explore P: 0.6603
Episode: 7668 Total reward: 13.0 Training loss: 0.9789 Explore P: 0.6603
Episode: 7669 Total reward: 23.0 Training loss: 0.3232 Explore P: 0.6603
Episode: 7670 Total reward: 15.0 Training loss: 1.7919 Explore P: 0.6603
Episode: 7671 Total reward: 20.0 Training loss: 0.0526 Explore P: 0.6603
Episode: 7672 Total reward: 17.0 Training loss: 0.0096 Explore P: 0.6602
Episode: 7673 Total reward: 14.0 Training loss: 0.2205 Explore P: 0.6602
Episode: 7674 Total reward: 20.0 Training loss: 0.0363 Explore P: 0.6602
Episode: 7675 Total reward: 13.0 Training loss: 0.0811 Explore P: 0.6602
Episode: 7676 Total reward: 30.0 Training loss: 0.3290 Explore P: 0.6601
Episode: 7677 Total reward: 22.0 Training loss: 0.2540 Explore P: 0.6601
Episode: 7678 Total reward: 76.0 Training loss: 0.0919 Explore P: 0.6600
Episode: 7679 Total reward: 23.0 Training loss: 4.4393 Explore P: 0.6600
Episode: 7680 Total reward: 24.0 Training loss: 0.8416 Explore P: 0.6599
Episode: 7681 Total reward: 17.0 Training loss: 0.1327 Explore P: 0.6599
Episode: 7682 Total reward: 24.0 Training loss: 0.0241 Explore P: 0.6599
Episode: 7683 Total reward: 21.0 Training loss: 0.0243 Explore P: 0.6599
Episode: 7684 Total reward: 51.0 Training loss: 0.0050 Explore P: 0.6598
Episode: 7685 Total reward: 27.0 Training loss: 0.0380 Explore P: 0.6598
Episode: 7686 Total reward: 7.0 Training loss: 0.0123 Explore P: 0.6597
Episode: 7687 Total reward: 14.0 Training loss: 0.2231 Explore P: 0.6597
Episode: 7688 Total reward: 13.0 Training loss: 0.0526 Explore P: 0.6597
Episode: 7689 Total reward: 15.0 Training loss: 0.1628 Explore P: 0.6597
Episode: 7690 Total reward: 17.0 Training loss: 0.0281 Explore P: 0.6597
Episode: 7691 Total reward: 28.0 Training loss: 0.3591 Explore P: 0.6596
Episode: 7692 Total reward: 20.0 Training loss: 0.0701 Explore P: 0.6596
Episode: 7693 Total reward: 44.0 Training loss: 0.3113 Explore P: 0.6596
Episode: 7694 Total reward: 44.0 Training loss: 0.1740 Explore P: 0.6595
Episode: 7695 Total reward: 42.0 Training loss: 0.1075 Explore P: 0.6594
Episode: 7696 Total reward: 13.0 Training loss: 0.0373 Explore P: 0.6594
Episode: 7697 Total reward: 14.0 Training loss: 0.2947 Explore P: 0.6594
Episode: 7698 Total reward: 28.0 Training loss: 0.0193 Explore P: 0.6594
Episode: 7699 Total reward: 25.0 Training loss: 0.0911 Explore P: 0.6593
Episode: 7700 Total reward: 22.0 Training loss: 0.3879 Explore P: 0.6593
Episode: 7701 Total reward: 17.0 Training loss: 0.6160 Explore P: 0.6593
Episode: 7702 Total reward: 20.0 Training loss: 0.2381 Explore P: 0.6593
Episode: 7703 Total reward: 25.0 Training loss: 1.2074 Explore P: 0.6592
Episode: 7704 Total reward: 22.0 Training loss: 9.1191 Explore P: 0.6592
Episode: 7705 Total reward: 12.0 Training loss: 0.7477 Explore P: 0.6592
Episode: 7706 Total reward: 13.0 Training loss: 0.0753 Explore P: 0.6592
Episode: 7707 Total reward: 8.0 Training loss: 0.0422 Explore P: 0.6592
Episode: 7708 Total reward: 22.0 Training loss: 0.0856 Explore P: 0.6591
Episode: 7709 Total reward: 9.0 Training loss: 0.4891 Explore P: 0.6591
Episode: 7710 Total reward: 10.0 Training loss: 2.1118 Explore P: 0.6591
Episode: 7711 Total reward: 15.0 Training loss: 0.0455 Explore P: 0.6591
Episode: 7712 Total reward: 10.0 Training loss: 0.9457 Explore P: 0.6591
Episode: 7713 Total reward: 10.0 Training loss: 0.6266 Explore P: 0.6591
Episode: 7714 Total reward: 22.0 Training loss: 0.5453 Explore P: 0.6590
Episode: 7715 Total reward: 15.0 Training loss: 0.1071 Explore P: 0.6590
Episode: 7716 Total reward: 23.0 Training loss: 0.0555 Explore P: 0.6590
Episode: 7717 Total reward: 17.0 Training loss: 0.0222 Explore P: 0.6590
Episode: 7718 Total reward: 12.0 Training loss: 6.6712 Explore P: 0.6589
Episode: 7719 Total reward: 9.0 Training loss: 1.0614 Explore P: 0.6589
Episode: 7720 Total reward: 35.0 Training loss: 0.3179 Explore P: 0.6589
Episode: 7721 Total reward: 18.0 Training loss: 0.8189 Explore P: 0.6589
Episode: 7722 Total reward: 24.0 Training loss: 0.0084 Explore P: 0.6588
Episode: 7723 Total reward: 41.0 Training loss: 0.0300 Explore P: 0.6588
Episode: 7724 Total reward: 43.0 Training loss: 0.0683 Explore P: 0.6587
Episode: 7725 Total reward: 47.0 Training loss: 0.0028 Explore P: 0.6587
Episode: 7726 Total reward: 9.0 Training loss: 0.5291 Explore P: 0.6587
Episode: 7727 Total reward: 23.0 Training loss: 0.1401 Explore P: 0.6586
Episode: 7728 Total reward: 8.0 Training loss: 0.0779 Explore P: 0.6586
Episode: 7729 Total reward: 24.0 Training loss: 0.2739 Explore P: 0.6586
Episode: 7730 Total reward: 12.0 Training loss: 0.1871 Explore P: 0.6586
Episode: 7731 Total reward: 18.0 Training loss: 0.0645 Explore P: 0.6585
Episode: 7732 Total reward: 19.0 Training loss: 1.4200 Explore P: 0.6585
Episode: 7733 Total reward: 39.0 Training loss: 0.4981 Explore P: 0.6585
Episode: 7734 Total reward: 11.0 Training loss: 0.0192 Explore P: 0.6585
Episode: 7735 Total reward: 14.0 Training loss: 0.0819 Explore P: 0.6584
Episode: 7736 Total reward: 18.0 Training loss: 0.2176 Explore P: 0.6584
Episode: 7737 Total reward: 20.0 Training loss: 0.0136 Explore P: 0.6584
Episode: 7738 Total reward: 21.0 Training loss: 0.0168 Explore P: 0.6584
Episode: 7739 Total reward: 27.0 Training loss: 0.6965 Explore P: 0.6583
Episode: 7740 Total reward: 9.0 Training loss: 0.4863 Explore P: 0.6583
Episode: 7741 Total reward: 35.0 Training loss: 0.5833 Explore P: 0.6583
Episode: 7742 Total reward: 36.0 Training loss: 1.2546 Explore P: 0.6582
Episode: 7743 Total reward: 23.0 Training loss: 0.0103 Explore P: 0.6582
Episode: 7744 Total reward: 28.0 Training loss: 0.1642 Explore P: 0.6582
Episode: 7745 Total reward: 19.0 Training loss: 0.4626 Explore P: 0.6581
Episode: 7746 Total reward: 15.0 Training loss: 0.5069 Explore P: 0.6581
Episode: 7747 Total reward: 16.0 Training loss: 0.0896 Explore P: 0.6581
Episode: 7748 Total reward: 37.0 Training loss: 0.0682 Explore P: 0.6580
Episode: 7749 Total reward: 14.0 Training loss: 0.2478 Explore P: 0.6580
Episode: 7750 Total reward: 58.0 Training loss: 1.0745 Explore P: 0.6579
Episode: 7751 Total reward: 41.0 Training loss: 0.6858 Explore P: 0.6579
Episode: 7752 Total reward: 31.0 Training loss: 0.0127 Explore P: 0.6579
Episode: 7753 Total reward: 25.0 Training loss: 1.7419 Explore P: 0.6578
Episode: 7754 Total reward: 65.0 Training loss: 0.0961 Explore P: 0.6577
Episode: 7755 Total reward: 23.0 Training loss: 0.0053 Explore P: 0.6577
Episode: 7756 Total reward: 28.0 Training loss: 0.0971 Explore P: 0.6577
Episode: 7757 Total reward: 32.0 Training loss: 0.0044 Explore P: 0.6576
Episode: 7758 Total reward: 20.0 Training loss: 0.5699 Explore P: 0.6576
Episode: 7759 Total reward: 32.0 Training loss: 0.0298 Explore P: 0.6576
Episode: 7760 Total reward: 11.0 Training loss: 0.4711 Explore P: 0.6575
Episode: 7761 Total reward: 24.0 Training loss: 0.4107 Explore P: 0.6575
Episode: 7762 Total reward: 18.0 Training loss: 2.1116 Explore P: 0.6575
Episode: 7763 Total reward: 11.0 Training loss: 0.1861 Explore P: 0.6575
Episode: 7764 Total reward: 32.0 Training loss: 0.2579 Explore P: 0.6574
Episode: 7765 Total reward: 35.0 Training loss: 0.3248 Explore P: 0.6574
Episode: 7766 Total reward: 20.0 Training loss: 0.5779 Explore P: 0.6574
Episode: 7767 Total reward: 18.0 Training loss: 0.0655 Explore P: 0.6573
Episode: 7768 Total reward: 46.0 Training loss: 0.0356 Explore P: 0.6573
Episode: 7769 Total reward: 21.0 Training loss: 0.0732 Explore P: 0.6573
Episode: 7770 Total reward: 19.0 Training loss: 0.0286 Explore P: 0.6572
Episode: 7771 Total reward: 32.0 Training loss: 3.2019 Explore P: 0.6572
Episode: 7772 Total reward: 14.0 Training loss: 0.0698 Explore P: 0.6572
Episode: 7773 Total reward: 8.0 Training loss: 0.0903 Explore P: 0.6572
Episode: 7774 Total reward: 22.0 Training loss: 1.0071 Explore P: 0.6571
Episode: 7775 Total reward: 20.0 Training loss: 0.0507 Explore P: 0.6571
Episode: 7776 Total reward: 16.0 Training loss: 0.1033 Explore P: 0.6571
Episode: 7777 Total reward: 10.0 Training loss: 0.0074 Explore P: 0.6571
Episode: 7778 Total reward: 25.0 Training loss: 1.2522 Explore P: 0.6570
Episode: 7779 Total reward: 17.0 Training loss: 0.0212 Explore P: 0.6570
Episode: 7780 Total reward: 22.0 Training loss: 0.1133 Explore P: 0.6570
Episode: 7781 Total reward: 10.0 Training loss: 0.0680 Explore P: 0.6570
Episode: 7782 Total reward: 27.0 Training loss: 0.0749 Explore P: 0.6569
Episode: 7783 Total reward: 23.0 Training loss: 0.4524 Explore P: 0.6569
Episode: 7784 Total reward: 28.0 Training loss: 0.3626 Explore P: 0.6569
Episode: 7785 Total reward: 11.0 Training loss: 0.6962 Explore P: 0.6569
Episode: 7786 Total reward: 41.0 Training loss: 0.4273 Explore P: 0.6568
Episode: 7787 Total reward: 18.0 Training loss: 0.1958 Explore P: 0.6568
Episode: 7788 Total reward: 14.0 Training loss: 0.1962 Explore P: 0.6568
Episode: 7789 Total reward: 17.0 Training loss: 0.1845 Explore P: 0.6567
Episode: 7790 Total reward: 15.0 Training loss: 0.0067 Explore P: 0.6567
Episode: 7791 Total reward: 14.0 Training loss: 0.0416 Explore P: 0.6567
Episode: 7792 Total reward: 13.0 Training loss: 0.5324 Explore P: 0.6567
Episode: 7793 Total reward: 8.0 Training loss: 1.1183 Explore P: 0.6567
Episode: 7794 Total reward: 25.0 Training loss: 1.6270 Explore P: 0.6566
Episode: 7795 Total reward: 37.0 Training loss: 0.2414 Explore P: 0.6566
Episode: 7796 Total reward: 31.0 Training loss: 0.2033 Explore P: 0.6566
Episode: 7797 Total reward: 34.0 Training loss: 0.0028 Explore P: 0.6565
Episode: 7798 Total reward: 23.0 Training loss: 0.2357 Explore P: 0.6565
Episode: 7799 Total reward: 22.0 Training loss: 0.0048 Explore P: 0.6565
Episode: 7800 Total reward: 25.0 Training loss: 8.4878 Explore P: 0.6564
Episode: 7801 Total reward: 14.0 Training loss: 0.1369 Explore P: 0.6564
Episode: 7802 Total reward: 26.0 Training loss: 0.6108 Explore P: 0.6564
Episode: 7803 Total reward: 23.0 Training loss: 0.0852 Explore P: 0.6563
Episode: 7804 Total reward: 17.0 Training loss: 1.1112 Explore P: 0.6563
Episode: 7805 Total reward: 33.0 Training loss: 0.1976 Explore P: 0.6563
Episode: 7806 Total reward: 27.0 Training loss: 4.3925 Explore P: 0.6562
Episode: 7807 Total reward: 14.0 Training loss: 0.3126 Explore P: 0.6562
Episode: 7808 Total reward: 28.0 Training loss: 0.0068 Explore P: 0.6562
Episode: 7809 Total reward: 16.0 Training loss: 1.2384 Explore P: 0.6562
Episode: 7810 Total reward: 25.0 Training loss: 0.1051 Explore P: 0.6561
Episode: 7811 Total reward: 25.0 Training loss: 0.0468 Explore P: 0.6561
Episode: 7812 Total reward: 26.0 Training loss: 0.1705 Explore P: 0.6561
Episode: 7813 Total reward: 12.0 Training loss: 1.7623 Explore P: 0.6561
Episode: 7814 Total reward: 33.0 Training loss: 1.2912 Explore P: 0.6560
Episode: 7815 Total reward: 22.0 Training loss: 0.5243 Explore P: 0.6560
Episode: 7816 Total reward: 11.0 Training loss: 0.0221 Explore P: 0.6560
Episode: 7817 Total reward: 15.0 Training loss: 0.0444 Explore P: 0.6560
Episode: 7818 Total reward: 19.0 Training loss: 0.4267 Explore P: 0.6559
Episode: 7819 Total reward: 47.0 Training loss: 1.6247 Explore P: 0.6559
Episode: 7820 Total reward: 37.0 Training loss: 0.0102 Explore P: 0.6558
Episode: 7821 Total reward: 10.0 Training loss: 0.2759 Explore P: 0.6558
Episode: 7822 Total reward: 18.0 Training loss: 0.0678 Explore P: 0.6558
Episode: 7823 Total reward: 13.0 Training loss: 0.0060 Explore P: 0.6558
Episode: 7824 Total reward: 12.0 Training loss: 0.0800 Explore P: 0.6557
Episode: 7825 Total reward: 34.0 Training loss: 1.6590 Explore P: 0.6557
Episode: 7826 Total reward: 11.0 Training loss: 0.0917 Explore P: 0.6557
Episode: 7827 Total reward: 22.0 Training loss: 0.2121 Explore P: 0.6557
Episode: 7828 Total reward: 41.0 Training loss: 4.3638 Explore P: 0.6556
Episode: 7829 Total reward: 9.0 Training loss: 0.0953 Explore P: 0.6556
Episode: 7830 Total reward: 20.0 Training loss: 0.1501 Explore P: 0.6556
Episode: 7831 Total reward: 17.0 Training loss: 1.6063 Explore P: 0.6556
Episode: 7832 Total reward: 20.0 Training loss: 0.1707 Explore P: 0.6555
Episode: 7833 Total reward: 20.0 Training loss: 4.6055 Explore P: 0.6555
Episode: 7834 Total reward: 24.0 Training loss: 0.0328 Explore P: 0.6555
Episode: 7835 Total reward: 11.0 Training loss: 110.5438 Explore P: 0.6555
Episode: 7836 Total reward: 25.0 Training loss: 0.0269 Explore P: 0.6554
Episode: 7837 Total reward: 24.0 Training loss: 0.0700 Explore P: 0.6554
Episode: 7838 Total reward: 14.0 Training loss: 3.4291 Explore P: 0.6554
Episode: 7839 Total reward: 27.0 Training loss: 0.3015 Explore P: 0.6553
Episode: 7840 Total reward: 48.0 Training loss: 0.1054 Explore P: 0.6553
Episode: 7841 Total reward: 22.0 Training loss: 1.9011 Explore P: 0.6552
Episode: 7842 Total reward: 15.0 Training loss: 0.0702 Explore P: 0.6552
Episode: 7843 Total reward: 12.0 Training loss: 0.0358 Explore P: 0.6552
Episode: 7844 Total reward: 13.0 Training loss: 0.1382 Explore P: 0.6552
Episode: 7845 Total reward: 27.0 Training loss: 0.0144 Explore P: 0.6552
Episode: 7846 Total reward: 26.0 Training loss: 1.7921 Explore P: 0.6551
Episode: 7847 Total reward: 12.0 Training loss: 0.2424 Explore P: 0.6551
Episode: 7848 Total reward: 25.0 Training loss: 0.5254 Explore P: 0.6551
Episode: 7849 Total reward: 22.0 Training loss: 0.7692 Explore P: 0.6551
Episode: 7850 Total reward: 20.0 Training loss: 0.0384 Explore P: 0.6550
Episode: 7851 Total reward: 22.0 Training loss: 0.0326 Explore P: 0.6550
Episode: 7852 Total reward: 21.0 Training loss: 0.1915 Explore P: 0.6550
Episode: 7853 Total reward: 17.0 Training loss: 0.1227 Explore P: 0.6549
Episode: 7854 Total reward: 22.0 Training loss: 0.0874 Explore P: 0.6549
Episode: 7855 Total reward: 46.0 Training loss: 16.3583 Explore P: 0.6549
Episode: 7856 Total reward: 33.0 Training loss: 0.0194 Explore P: 0.6548
Episode: 7857 Total reward: 19.0 Training loss: 4.1534 Explore P: 0.6548
Episode: 7858 Total reward: 15.0 Training loss: 0.0169 Explore P: 0.6548
Episode: 7859 Total reward: 25.0 Training loss: 1.5511 Explore P: 0.6547
Episode: 7860 Total reward: 19.0 Training loss: 0.2226 Explore P: 0.6547
Episode: 7861 Total reward: 22.0 Training loss: 0.0271 Explore P: 0.6547
Episode: 7862 Total reward: 26.0 Training loss: 0.1334 Explore P: 0.6547
Episode: 7863 Total reward: 18.0 Training loss: 2.0244 Explore P: 0.6546
Episode: 7864 Total reward: 35.0 Training loss: 1.1239 Explore P: 0.6546
Episode: 7865 Total reward: 13.0 Training loss: 0.0107 Explore P: 0.6546
Episode: 7866 Total reward: 26.0 Training loss: 1.0559 Explore P: 0.6545
Episode: 7867 Total reward: 25.0 Training loss: 0.0718 Explore P: 0.6545
Episode: 7868 Total reward: 9.0 Training loss: 0.0108 Explore P: 0.6545
Episode: 7869 Total reward: 16.0 Training loss: 0.0046 Explore P: 0.6545
Episode: 7870 Total reward: 34.0 Training loss: 0.8715 Explore P: 0.6544
Episode: 7871 Total reward: 19.0 Training loss: 0.2352 Explore P: 0.6544
Episode: 7872 Total reward: 12.0 Training loss: 0.1910 Explore P: 0.6544
Episode: 7873 Total reward: 11.0 Training loss: 0.1981 Explore P: 0.6544
Episode: 7874 Total reward: 53.0 Training loss: 0.7775 Explore P: 0.6543
Episode: 7875 Total reward: 22.0 Training loss: 1.0927 Explore P: 0.6543
Episode: 7876 Total reward: 23.0 Training loss: 0.0788 Explore P: 0.6542
Episode: 7877 Total reward: 29.0 Training loss: 0.6406 Explore P: 0.6542
Episode: 7878 Total reward: 22.0 Training loss: 0.1189 Explore P: 0.6542
Episode: 7879 Total reward: 18.0 Training loss: 0.0412 Explore P: 0.6542
Episode: 7880 Total reward: 11.0 Training loss: 0.2017 Explore P: 0.6541
Episode: 7881 Total reward: 10.0 Training loss: 0.0721 Explore P: 0.6541
Episode: 7882 Total reward: 10.0 Training loss: 1.1497 Explore P: 0.6541
Episode: 7883 Total reward: 16.0 Training loss: 0.2833 Explore P: 0.6541
Episode: 7884 Total reward: 20.0 Training loss: 0.1284 Explore P: 0.6541
Episode: 7885 Total reward: 18.0 Training loss: 1.2454 Explore P: 0.6540
Episode: 7886 Total reward: 71.0 Training loss: 0.3453 Explore P: 0.6540
Episode: 7887 Total reward: 17.0 Training loss: 0.2599 Explore P: 0.6539
Episode: 7888 Total reward: 17.0 Training loss: 0.5375 Explore P: 0.6539
Episode: 7889 Total reward: 139.0 Training loss: 0.0294 Explore P: 0.6537
Episode: 7890 Total reward: 23.0 Training loss: 0.0098 Explore P: 0.6537
Episode: 7891 Total reward: 15.0 Training loss: 0.2029 Explore P: 0.6537
Episode: 7892 Total reward: 30.0 Training loss: 0.1073 Explore P: 0.6536
Episode: 7893 Total reward: 24.0 Training loss: 0.1494 Explore P: 0.6536
Episode: 7894 Total reward: 46.0 Training loss: 0.4039 Explore P: 0.6536
Episode: 7895 Total reward: 14.0 Training loss: 0.2071 Explore P: 0.6535
Episode: 7896 Total reward: 17.0 Training loss: 1.0290 Explore P: 0.6535
Episode: 7897 Total reward: 14.0 Training loss: 0.1193 Explore P: 0.6535
Episode: 7898 Total reward: 17.0 Training loss: 1.3910 Explore P: 0.6535
Episode: 7899 Total reward: 12.0 Training loss: 0.3963 Explore P: 0.6535
Episode: 7900 Total reward: 18.0 Training loss: 0.6978 Explore P: 0.6534
Episode: 7901 Total reward: 17.0 Training loss: 0.1209 Explore P: 0.6534
Episode: 7902 Total reward: 44.0 Training loss: 0.0338 Explore P: 0.6534
Episode: 7903 Total reward: 43.0 Training loss: 2.4163 Explore P: 0.6533
Episode: 7904 Total reward: 27.0 Training loss: 0.1130 Explore P: 0.6533
Episode: 7905 Total reward: 21.0 Training loss: 0.0201 Explore P: 0.6532
Episode: 7906 Total reward: 11.0 Training loss: 0.1733 Explore P: 0.6532
Episode: 7907 Total reward: 24.0 Training loss: 0.0658 Explore P: 0.6532
Episode: 7908 Total reward: 17.0 Training loss: 0.6103 Explore P: 0.6532
Episode: 7909 Total reward: 20.0 Training loss: 0.0238 Explore P: 0.6532
Episode: 7910 Total reward: 24.0 Training loss: 4.8325 Explore P: 0.6531
Episode: 7911 Total reward: 13.0 Training loss: 0.2033 Explore P: 0.6531
Episode: 7912 Total reward: 23.0 Training loss: 1.1569 Explore P: 0.6531
Episode: 7913 Total reward: 21.0 Training loss: 0.0470 Explore P: 0.6530
Episode: 7914 Total reward: 49.0 Training loss: 0.5661 Explore P: 0.6530
Episode: 7915 Total reward: 16.0 Training loss: 0.0590 Explore P: 0.6530
Episode: 7916 Total reward: 26.0 Training loss: 0.0225 Explore P: 0.6529
Episode: 7917 Total reward: 16.0 Training loss: 0.9266 Explore P: 0.6529
Episode: 7918 Total reward: 24.0 Training loss: 0.6439 Explore P: 0.6529
Episode: 7919 Total reward: 26.0 Training loss: 0.0589 Explore P: 0.6528
Episode: 7920 Total reward: 38.0 Training loss: 0.1315 Explore P: 0.6528
Episode: 7921 Total reward: 18.0 Training loss: 0.8862 Explore P: 0.6528
Episode: 7922 Total reward: 45.0 Training loss: 0.0080 Explore P: 0.6527
Episode: 7923 Total reward: 13.0 Training loss: 0.1900 Explore P: 0.6527
Episode: 7924 Total reward: 29.0 Training loss: 0.0487 Explore P: 0.6527
Episode: 7925 Total reward: 44.0 Training loss: 1.0854 Explore P: 0.6526
Episode: 7926 Total reward: 23.0 Training loss: 0.0490 Explore P: 0.6526
Episode: 7927 Total reward: 32.0 Training loss: 0.0120 Explore P: 0.6525
Episode: 7928 Total reward: 17.0 Training loss: 0.0258 Explore P: 0.6525
Episode: 7929 Total reward: 30.0 Training loss: 0.2218 Explore P: 0.6525
Episode: 7930 Total reward: 37.0 Training loss: 15.3202 Explore P: 0.6524
Episode: 7931 Total reward: 18.0 Training loss: 0.0477 Explore P: 0.6524
Episode: 7932 Total reward: 18.0 Training loss: 0.0133 Explore P: 0.6524
Episode: 7933 Total reward: 21.0 Training loss: 0.0288 Explore P: 0.6524
Episode: 7934 Total reward: 68.0 Training loss: 22.9133 Explore P: 0.6523
Episode: 7935 Total reward: 16.0 Training loss: 0.0075 Explore P: 0.6522
Episode: 7936 Total reward: 29.0 Training loss: 0.8623 Explore P: 0.6522
Episode: 7937 Total reward: 23.0 Training loss: 2.4957 Explore P: 0.6522
Episode: 7938 Total reward: 48.0 Training loss: 0.1970 Explore P: 0.6521
Episode: 7939 Total reward: 10.0 Training loss: 0.1400 Explore P: 0.6521
Episode: 7940 Total reward: 30.0 Training loss: 0.3136 Explore P: 0.6521
Episode: 7941 Total reward: 36.0 Training loss: 0.1646 Explore P: 0.6520
Episode: 7942 Total reward: 17.0 Training loss: 0.0084 Explore P: 0.6520
Episode: 7943 Total reward: 37.0 Training loss: 0.1131 Explore P: 0.6519
Episode: 7944 Total reward: 27.0 Training loss: 0.2801 Explore P: 0.6519
Episode: 7945 Total reward: 10.0 Training loss: 0.8590 Explore P: 0.6519
Episode: 7946 Total reward: 13.0 Training loss: 0.6897 Explore P: 0.6519
Episode: 7947 Total reward: 17.0 Training loss: 0.0976 Explore P: 0.6519
Episode: 7948 Total reward: 13.0 Training loss: 0.0137 Explore P: 0.6518
Episode: 7949 Total reward: 27.0 Training loss: 0.1375 Explore P: 0.6518
Episode: 7950 Total reward: 53.0 Training loss: 2.3971 Explore P: 0.6517
Episode: 7951 Total reward: 22.0 Training loss: 0.4689 Explore P: 0.6517
Episode: 7952 Total reward: 32.0 Training loss: 0.3277 Explore P: 0.6517
Episode: 7953 Total reward: 16.0 Training loss: 0.9552 Explore P: 0.6517
Episode: 7954 Total reward: 41.0 Training loss: 0.1232 Explore P: 0.6516
Episode: 7955 Total reward: 21.0 Training loss: 7.5773 Explore P: 0.6516
Episode: 7956 Total reward: 22.0 Training loss: 0.0381 Explore P: 0.6515
Episode: 7957 Total reward: 31.0 Training loss: 0.0463 Explore P: 0.6515
Episode: 7958 Total reward: 17.0 Training loss: 0.3123 Explore P: 0.6515
Episode: 7959 Total reward: 9.0 Training loss: 0.0338 Explore P: 0.6515
Episode: 7960 Total reward: 11.0 Training loss: 0.0763 Explore P: 0.6515
Episode: 7961 Total reward: 21.0 Training loss: 5.6003 Explore P: 0.6514
Episode: 7962 Total reward: 36.0 Training loss: 0.4340 Explore P: 0.6514
Episode: 7963 Total reward: 13.0 Training loss: 0.1144 Explore P: 0.6514
Episode: 7964 Total reward: 17.0 Training loss: 0.0068 Explore P: 0.6513
Episode: 7965 Total reward: 35.0 Training loss: 0.0328 Explore P: 0.6513
Episode: 7966 Total reward: 27.0 Training loss: 2.2556 Explore P: 0.6513
Episode: 7967 Total reward: 14.0 Training loss: 0.0297 Explore P: 0.6513
Episode: 7968 Total reward: 10.0 Training loss: 0.2007 Explore P: 0.6512
Episode: 7969 Total reward: 28.0 Training loss: 1.5715 Explore P: 0.6512
Episode: 7970 Total reward: 26.0 Training loss: 0.1558 Explore P: 0.6512
Episode: 7971 Total reward: 25.0 Training loss: 0.3011 Explore P: 0.6511
Episode: 7972 Total reward: 32.0 Training loss: 0.0663 Explore P: 0.6511
Episode: 7973 Total reward: 17.0 Training loss: 0.2086 Explore P: 0.6511
Episode: 7974 Total reward: 8.0 Training loss: 0.1131 Explore P: 0.6511
Episode: 7975 Total reward: 9.0 Training loss: 0.0143 Explore P: 0.6511
Episode: 7976 Total reward: 12.0 Training loss: 0.0976 Explore P: 0.6510
Episode: 7977 Total reward: 23.0 Training loss: 0.1020 Explore P: 0.6510
Episode: 7978 Total reward: 24.0 Training loss: 0.7685 Explore P: 0.6510
Episode: 7979 Total reward: 25.0 Training loss: 0.1214 Explore P: 0.6509
Episode: 7980 Total reward: 33.0 Training loss: 0.2954 Explore P: 0.6509
Episode: 7981 Total reward: 13.0 Training loss: 0.0773 Explore P: 0.6509
Episode: 7982 Total reward: 26.0 Training loss: 0.1001 Explore P: 0.6509
Episode: 7983 Total reward: 40.0 Training loss: 0.0950 Explore P: 0.6508
Episode: 7984 Total reward: 17.0 Training loss: 0.0618 Explore P: 0.6508
Episode: 7985 Total reward: 25.0 Training loss: 0.0600 Explore P: 0.6507
Episode: 7986 Total reward: 33.0 Training loss: 0.0116 Explore P: 0.6507
Episode: 7987 Total reward: 18.0 Training loss: 0.1092 Explore P: 0.6507
Episode: 7988 Total reward: 17.0 Training loss: 0.0981 Explore P: 0.6507
Episode: 7989 Total reward: 19.0 Training loss: 0.2898 Explore P: 0.6506
Episode: 7990 Total reward: 11.0 Training loss: 1.1455 Explore P: 0.6506
Episode: 7991 Total reward: 23.0 Training loss: 0.2702 Explore P: 0.6506
Episode: 7992 Total reward: 9.0 Training loss: 0.0170 Explore P: 0.6506
Episode: 7993 Total reward: 32.0 Training loss: 0.0086 Explore P: 0.6505
Episode: 7994 Total reward: 16.0 Training loss: 0.1212 Explore P: 0.6505
Episode: 7995 Total reward: 40.0 Training loss: 0.0322 Explore P: 0.6505
Episode: 7996 Total reward: 12.0 Training loss: 0.1332 Explore P: 0.6505
Episode: 7997 Total reward: 16.0 Training loss: 0.5769 Explore P: 0.6504
Episode: 7998 Total reward: 37.0 Training loss: 0.0120 Explore P: 0.6504
Episode: 7999 Total reward: 13.0 Training loss: 10.9105 Explore P: 0.6504
Episode: 8000 Total reward: 23.0 Training loss: 7.6241 Explore P: 0.6503
Episode: 8001 Total reward: 12.0 Training loss: 0.1451 Explore P: 0.6503
Episode: 8002 Total reward: 36.0 Training loss: 0.0376 Explore P: 0.6503
Episode: 8003 Total reward: 25.0 Training loss: 0.2408 Explore P: 0.6502
Episode: 8004 Total reward: 15.0 Training loss: 0.9637 Explore P: 0.6502
Episode: 8005 Total reward: 34.0 Training loss: 0.1055 Explore P: 0.6502
Episode: 8006 Total reward: 13.0 Training loss: 0.0049 Explore P: 0.6502
Episode: 8007 Total reward: 25.0 Training loss: 0.1871 Explore P: 0.6501
Episode: 8008 Total reward: 13.0 Training loss: 0.0225 Explore P: 0.6501
Episode: 8009 Total reward: 39.0 Training loss: 1.1093 Explore P: 0.6501
Episode: 8010 Total reward: 37.0 Training loss: 0.0496 Explore P: 0.6500
Episode: 8011 Total reward: 99.0 Training loss: 0.2469 Explore P: 0.6499
Episode: 8012 Total reward: 22.0 Training loss: 0.0339 Explore P: 0.6499
Episode: 8013 Total reward: 13.0 Training loss: 0.2522 Explore P: 0.6498
Episode: 8014 Total reward: 39.0 Training loss: 0.0581 Explore P: 0.6498
Episode: 8015 Total reward: 10.0 Training loss: 0.2937 Explore P: 0.6498
Episode: 8016 Total reward: 49.0 Training loss: 0.1723 Explore P: 0.6497
Episode: 8017 Total reward: 22.0 Training loss: 0.0789 Explore P: 0.6497
Episode: 8018 Total reward: 30.0 Training loss: 0.0266 Explore P: 0.6497
Episode: 8019 Total reward: 23.0 Training loss: 0.1309 Explore P: 0.6496
Episode: 8020 Total reward: 12.0 Training loss: 0.0938 Explore P: 0.6496
Episode: 8021 Total reward: 19.0 Training loss: 0.0815 Explore P: 0.6496
Episode: 8022 Total reward: 19.0 Training loss: 0.1836 Explore P: 0.6496
Episode: 8023 Total reward: 16.0 Training loss: 0.3761 Explore P: 0.6495
Episode: 8024 Total reward: 33.0 Training loss: 0.1406 Explore P: 0.6495
Episode: 8025 Total reward: 14.0 Training loss: 0.0814 Explore P: 0.6495
Episode: 8026 Total reward: 17.0 Training loss: 0.0945 Explore P: 0.6495
Episode: 8027 Total reward: 18.0 Training loss: 0.5232 Explore P: 0.6494
Episode: 8028 Total reward: 19.0 Training loss: 0.0280 Explore P: 0.6494
Episode: 8029 Total reward: 19.0 Training loss: 0.1839 Explore P: 0.6494
Episode: 8030 Total reward: 16.0 Training loss: 0.0930 Explore P: 0.6494
Episode: 8031 Total reward: 10.0 Training loss: 0.3210 Explore P: 0.6494
Episode: 8032 Total reward: 14.0 Training loss: 0.3200 Explore P: 0.6493
In [ ]:
%matplotlib inline
import matplotlib.pyplot as plt
def running_mean(x, N):
cumsum = np.cumsum(np.insert(x, 0, 0))
return (cumsum[N:] - cumsum[:-N]) / N
In [ ]:
eps, rews = np.array(rewards_list).T
smoothed_rews = running_mean(rews, 10)
plt.plot(eps[-len(smoothed_rews):], smoothed_rews)
plt.plot(eps, rews, color='grey', alpha=0.3)
plt.xlabel('Episode')
plt.ylabel('Total Reward')
In [ ]:
mystate = get_state(all_states, previous_steps)
feed = {mainQN.inputs_: mystate.reshape((1, *mystate.shape))}
In [18]:
test_episodes = 10
test_max_steps = 400
env.reset()
state, reward, done, _ = env.step(env.action_space.sample())
all_states = [state]
with tf.Session() as sess:
saver.restore(sess, tf.train.latest_checkpoint('checkpoints'))
for ep in range(1, test_episodes):
t = 0
while t < test_max_steps:
env.render()
# Get action from Q-network
mystate = get_state(all_states, previous_steps)
feed = {mainQN.inputs_: mystate.reshape((1, *mystate.shape))}
Qs = sess.run(mainQN.output, feed_dict=feed)
action = np.argmax(Qs)
# Take action, get new state and reward
next_state, reward, done, _ = env.step(action)
if done:
print("Completed {} steps.".format(t))
t = test_max_steps
env.reset()
# Take one random step to get the pole and cart moving
state, reward, done, _ = env.step(env.action_space.sample())
all_states = [state]
else:
state = next_state
all_states.append(state)
t += 1
INFO:tensorflow:Restoring parameters from checkpoints/cartpole.ckpt
[2017-07-20 12:02:49,229] Restoring parameters from checkpoints/cartpole.ckpt
Completed 10 steps.
Completed 8 steps.
Completed 7 steps.
Completed 7 steps.
Completed 10 steps.
Completed 7 steps.
Completed 10 steps.
Completed 10 steps.
Completed 8 steps.
In [184]:
env.close()
So, Cart-Pole is a pretty simple game. However, the same model can be used to train an agent to play something much more complicated like Pong or Space Invaders. Instead of a state like we're using here though, you'd want to use convolutional layers to get the state from the screen images.
I'll leave it as a challenge for you to use deep Q-learning to train an agent to play Atari games. Here's the original paper which will get you started: http://www.davidqiu.com:8888/research/nature14236.pdf.
Content source: scottquiring/Udacity_Deeplearning
Similar notebooks: