We are attempting to solve the openai frozen lake environment using reinforcement learning. Openai provides many environments for simulation.
Let us understand what reinforcement learning is and compare it with other available methodologies. The frozen lake problem involves a grid maze with a starting point and a goal. Along the way there are a few fatal pitfalls. Solving the frozen lake requires us to build an agent/bot who can traverse the maze and reach the goal without falling into the pitfalls. The duration of the travel is not a constraint but it is better if the bot can reach it quicker.
SFFF (S: starting point, safe)
FHFH (F: frozen surface, safe)
FFFH (H: hole, fall to your doom)
HFFG (G: goal, where the frisbee is located)
The frozen lake can be solved using a multitude of ways with standard graph search algos to optimization algorithms. There is one caveat though, the environment adds a small complexity to the mix. If our bot wanted to move right, there is a slight chance the bot may move in a random direction. Apparently a gust of wind pushes us away This complexity tends to break our algos like graph search etc which may not handle random probabilities. One worthy method to solve this dynamic environment is Reinforcement Learning.
In [20]:
import gym
import tensorflow as tf
from collections import deque
import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import Adam
from gym import wrappers
import shutil
In [21]:
shutil.rmtree('./monitor')
env = gym.make('FrozenLake-v0')
env = wrappers.Monitor(env,'./monitor')
[2017-07-16 15:00:00,373] Making new env: FrozenLake-v0
[2017-07-16 15:00:00,373] Creating monitor directory ./monitor
In [22]:
print(env.observation_space.n)
print(env.action_space.n)
16
4
The frozen lake environment has the following important entities;
Below is an example of a single simulation episode.
In [31]:
state = env.reset()
for i in range(10):
env.render()
action = env.action_space.sample()
next_state, reward, done, prob = env.step(action)
print('state:{} action:{} next_state:{} reward:{} done:{}'.format(state, action, next_state, reward, done))
state = next_state
if done:
break
SFFF
FHFH
FFFH
HFFG
state:0 action:3 next_state:1 reward:0.0 done:False
(Up)
SFFF
FHFH
FFFH
HFFG
state:1 action:2 next_state:1 reward:0.0 done:False
(Right)
SFFF
FHFH
FFFH
HFFG
state:1 action:0 next_state:0 reward:0.0 done:False
(Left)
SFFF
FHFH
FFFH
HFFG
state:0 action:1 next_state:1 reward:0.0 done:False
(Down)
SFFF
FHFH
FFFH
HFFG
state:1 action:3 next_state:2 reward:0.0 done:False
(Up)
SFFF
FHFH
FFFH
HFFG
state:2 action:0 next_state:2 reward:0.0 done:False
(Left)
SFFF
FHFH
FFFH
HFFG
state:2 action:1 next_state:3 reward:0.0 done:False
(Down)
SFFF
FHFH
FFFH
HFFG
state:3 action:3 next_state:2 reward:0.0 done:False
(Up)
SFFF
FHFH
FFFH
HFFG
state:2 action:2 next_state:2 reward:0.0 done:False
(Right)
SFFF
FHFH
FFFH
HFFG
state:2 action:2 next_state:3 reward:0.0 done:False
Q-learning is one of the techniques used to implement RL. Q-learning relies on the Bellman's equation.
$$ Q(s, a) = r + \gamma \max{Q(s', a')} $$The Bellman equation provides a way to incorporate future rewards of an action to a current state. This is a core component of Q Learning. In a nutshell Q-learning is finding the function Q = f(state, action) which can be used to derive the action needed for a given state to traverse an environment.
The pseudo code for Q-learning is below
In [23]:
learning_rate = 0.001
memory_size = 2000
episodes = 5000
steps = 100
# changed from 0.95
gamma = 0.99
epsilon = 1
epsilon_stop = 0.01
epsilon_decay = 0.995
batch_size = 32
Our agent is a simple neural network with a rectified linear hidden layer and a linear output layer. We are using Adam optimizer. The neural network will be having a memory to store past experiences. This is known as Temporal Difference Learning.
In [24]:
bot = Sequential()
bot.add(Dense(10, input_dim=16, activation='relu'))
bot.add(Dense(4, activation='linear'))
bot.compile(loss='mse', optimizer = Adam(learning_rate))
memory = deque(maxlen=memory_size)
In [25]:
state_lkup = np.eye(env.observation_space.n)
action_lkup = np.eye(env.action_space.n)
In [26]:
reward_list=[]
state = env.reset()
for episode in range(episodes):
total_reward = 0
state = env.reset()
for step in range(steps):
if epsilon > np.random.rand():
action = env.action_space.sample()
else:
action = np.argmax(bot.predict(np.reshape(state_lkup[state], (-1, env.observation_space.n))))
next_state, reward, done, prob = env.step(action)
if done and reward==0:
reward = -1
if not done and reward==0:
reward = -0.02
memory.append((state, action, reward, next_state, done))
state = next_state
total_reward = total_reward + reward
if done:
print('episode:{} steps:{} total reward:{} epsilon:{}'.format(episode + 1, step + 1, total_reward, epsilon))
reward_list.append(total_reward)
break
minibatch = [memory[ii] for ii in np.random.choice(range(len(memory)), batch_size)]
states = [each[0] for each in minibatch]
actions = [each[1] for each in minibatch]
rewards = [each[2] for each in minibatch]
next_states = [each[3] for each in minibatch]
dones = [each[4] for each in minibatch]
next_states = np.reshape([state_lkup[state] for state in next_states], [-1,env.observation_space.n])
states = np.reshape([state_lkup[state] for state in states], [-1,env.observation_space.n])
actions = np.reshape(actions, (batch_size, 1))
targetQs = bot.predict(next_states)
episode_ends = (next_states == np.zeros(states[0].shape)).all(axis=1)
targetQs[episode_ends] = (0, 0, 0, 0)
targets = rewards + gamma * np.max(targetQs, axis=1)
targets_f = bot.predict(states)
for pos in range(len(actions)):
targets_f[pos,actions[pos]] = targets[pos]
bot.fit(states, targets_f, epochs=1, verbose=0)
if epsilon > epsilon_stop:
epsilon = epsilon * epsilon_decay
[2017-07-16 15:00:26,036] Starting new video recorder writing to C:\Users\Abdul\Documents\My Projects\Deep learning nano degree\my-experiments\reinforcement learning\monitor\openaigym.video.2.12772.video000000.json
[2017-07-16 15:00:26,036] Starting new video recorder writing to C:\Users\Abdul\Documents\My Projects\Deep learning nano degree\my-experiments\reinforcement learning\monitor\openaigym.video.2.12772.video000001.json
episode:1 steps:7 total reward:-1.12 epsilon:1
episode:2 steps:3 total reward:-1.04 epsilon:0.995
episode:3 steps:18 total reward:-1.34 epsilon:0.990025
episode:4 steps:6 total reward:-1.1 epsilon:0.985074875
episode:5 steps:8 total reward:-1.1400000000000001 epsilon:0.9801495006250001
[2017-07-16 15:00:27,069] Starting new video recorder writing to C:\Users\Abdul\Documents\My Projects\Deep learning nano degree\my-experiments\reinforcement learning\monitor\openaigym.video.2.12772.video000008.json
episode:6 steps:11 total reward:-1.2 epsilon:0.9752487531218751
episode:7 steps:4 total reward:-1.06 epsilon:0.9703725093562657
episode:8 steps:20 total reward:0.6199999999999999 epsilon:0.9655206468094844
episode:9 steps:6 total reward:-1.1 epsilon:0.960693043575437
episode:10 steps:7 total reward:-1.12 epsilon:0.9558895783575597
episode:11 steps:3 total reward:-1.04 epsilon:0.9511101304657719
episode:12 steps:10 total reward:-1.18 epsilon:0.946354579813443
episode:13 steps:4 total reward:-1.06 epsilon:0.9416228069143757
episode:14 steps:2 total reward:-1.02 epsilon:0.9369146928798039
episode:15 steps:8 total reward:-1.1400000000000001 epsilon:0.9322301194154049
episode:16 steps:9 total reward:-1.16 epsilon:0.9275689688183278
episode:17 steps:10 total reward:-1.18 epsilon:0.9229311239742362
episode:18 steps:7 total reward:-1.12 epsilon:0.918316468354365
episode:19 steps:6 total reward:-1.1 epsilon:0.9137248860125932
episode:20 steps:2 total reward:-1.02 epsilon:0.9091562615825302
episode:21 steps:16 total reward:-1.3 epsilon:0.9046104802746175
episode:22 steps:7 total reward:0.88 epsilon:0.9000874278732445
episode:23 steps:5 total reward:-1.08 epsilon:0.8955869907338783
episode:24 steps:16 total reward:-1.3 epsilon:0.8911090557802088
episode:25 steps:5 total reward:-1.08 epsilon:0.8866535105013078
[2017-07-16 15:00:27,934] Starting new video recorder writing to C:\Users\Abdul\Documents\My Projects\Deep learning nano degree\my-experiments\reinforcement learning\monitor\openaigym.video.2.12772.video000027.json
episode:26 steps:12 total reward:-1.22 epsilon:0.8822202429488013
episode:27 steps:8 total reward:-1.1400000000000001 epsilon:0.8778091417340573
episode:28 steps:3 total reward:-1.04 epsilon:0.8734200960253871
episode:29 steps:5 total reward:-1.08 epsilon:0.8690529955452602
episode:30 steps:9 total reward:-1.16 epsilon:0.8647077305675338
episode:31 steps:3 total reward:-1.04 epsilon:0.8603841919146962
episode:32 steps:5 total reward:-1.08 epsilon:0.8560822709551227
episode:33 steps:8 total reward:-1.1400000000000001 epsilon:0.851801859600347
episode:34 steps:4 total reward:-1.06 epsilon:0.8475428503023453
episode:35 steps:7 total reward:-1.12 epsilon:0.8433051360508336
episode:36 steps:7 total reward:-1.12 epsilon:0.8390886103705794
episode:37 steps:2 total reward:-1.02 epsilon:0.8348931673187264
episode:38 steps:2 total reward:-1.02 epsilon:0.8307187014821328
episode:39 steps:2 total reward:-1.02 epsilon:0.8265651079747222
episode:40 steps:10 total reward:-1.18 epsilon:0.8224322824348486
episode:41 steps:5 total reward:-1.08 epsilon:0.8183201210226743
episode:42 steps:28 total reward:-1.54 epsilon:0.8142285204175609
episode:43 steps:4 total reward:-1.06 epsilon:0.810157377815473
episode:44 steps:7 total reward:-1.12 epsilon:0.8061065909263957
episode:45 steps:7 total reward:-1.12 epsilon:0.8020760579717637
episode:46 steps:3 total reward:-1.04 epsilon:0.798065677681905
episode:47 steps:8 total reward:-1.1400000000000001 epsilon:0.7940753492934954
episode:48 steps:7 total reward:-1.12 epsilon:0.7901049725470279
episode:49 steps:9 total reward:-1.16 epsilon:0.7861544476842928
episode:50 steps:7 total reward:-1.12 epsilon:0.7822236754458713
episode:51 steps:3 total reward:-1.04 epsilon:0.778312557068642
episode:52 steps:13 total reward:-1.24 epsilon:0.7744209942832988
episode:53 steps:15 total reward:-1.28 epsilon:0.7705488893118823
[2017-07-16 15:00:29,122] Starting new video recorder writing to C:\Users\Abdul\Documents\My Projects\Deep learning nano degree\my-experiments\reinforcement learning\monitor\openaigym.video.2.12772.video000064.json
episode:54 steps:14 total reward:-1.26 epsilon:0.7666961448653229
episode:55 steps:5 total reward:-1.08 epsilon:0.7628626641409962
episode:56 steps:2 total reward:-1.02 epsilon:0.7590483508202912
episode:57 steps:2 total reward:-1.02 epsilon:0.7552531090661897
episode:58 steps:8 total reward:0.86 epsilon:0.7514768435208588
episode:59 steps:7 total reward:-1.12 epsilon:0.7477194593032545
episode:60 steps:2 total reward:-1.02 epsilon:0.7439808620067382
episode:61 steps:4 total reward:-1.06 epsilon:0.7402609576967045
episode:62 steps:2 total reward:-1.02 epsilon:0.736559652908221
episode:63 steps:7 total reward:-1.12 epsilon:0.7328768546436799
episode:64 steps:3 total reward:-1.04 epsilon:0.7292124703704616
episode:65 steps:7 total reward:-1.12 epsilon:0.7255664080186093
episode:66 steps:17 total reward:-1.32 epsilon:0.7219385759785162
episode:67 steps:2 total reward:-1.02 epsilon:0.7183288830986236
episode:68 steps:3 total reward:-1.04 epsilon:0.7147372386831305
episode:69 steps:5 total reward:-1.08 epsilon:0.7111635524897149
episode:70 steps:10 total reward:-1.18 epsilon:0.7076077347272662
episode:71 steps:9 total reward:-1.16 epsilon:0.7040696960536299
episode:72 steps:4 total reward:-1.06 epsilon:0.7005493475733617
episode:73 steps:9 total reward:-1.16 epsilon:0.697046600835495
episode:74 steps:2 total reward:-1.02 epsilon:0.6935613678313175
episode:75 steps:17 total reward:-1.32 epsilon:0.6900935609921609
episode:76 steps:5 total reward:-1.08 epsilon:0.6866430931872001
episode:77 steps:2 total reward:-1.02 epsilon:0.6832098777212641
episode:78 steps:12 total reward:-1.22 epsilon:0.6797938283326578
episode:79 steps:3 total reward:-1.04 epsilon:0.6763948591909945
episode:80 steps:2 total reward:-1.02 epsilon:0.6730128848950395
episode:81 steps:5 total reward:-1.08 epsilon:0.6696478204705644
episode:82 steps:5 total reward:-1.08 epsilon:0.6662995813682115
episode:83 steps:12 total reward:-1.22 epsilon:0.6629680834613705
episode:84 steps:6 total reward:-1.1 epsilon:0.6596532430440636
episode:85 steps:2 total reward:-1.02 epsilon:0.6563549768288433
episode:86 steps:14 total reward:-1.26 epsilon:0.653073201944699
episode:87 steps:5 total reward:-1.08 epsilon:0.6498078359349755
episode:88 steps:9 total reward:-1.16 epsilon:0.6465587967553006
episode:89 steps:12 total reward:-1.22 epsilon:0.6433260027715241
episode:90 steps:27 total reward:-1.52 epsilon:0.6401093727576664
episode:91 steps:4 total reward:-1.06 epsilon:0.6369088258938781
episode:92 steps:2 total reward:-1.02 epsilon:0.6337242817644086
episode:93 steps:8 total reward:-1.1400000000000001 epsilon:0.6305556603555866
episode:94 steps:11 total reward:-1.2 epsilon:0.6274028820538087
episode:95 steps:4 total reward:-1.06 epsilon:0.6242658676435396
episode:96 steps:12 total reward:-1.22 epsilon:0.6211445383053219
episode:97 steps:11 total reward:-1.2 epsilon:0.6180388156137953
episode:98 steps:5 total reward:-1.08 epsilon:0.6149486215357263
episode:99 steps:3 total reward:-1.04 epsilon:0.6118738784280476
episode:100 steps:5 total reward:-1.08 epsilon:0.6088145090359074
episode:101 steps:3 total reward:-1.04 epsilon:0.6057704364907278
episode:102 steps:8 total reward:-1.1400000000000001 epsilon:0.6027415843082742
episode:103 steps:5 total reward:-1.08 epsilon:0.5997278763867329
episode:104 steps:6 total reward:-1.1 epsilon:0.5967292370047992
episode:105 steps:17 total reward:-1.32 epsilon:0.5937455908197752
episode:106 steps:6 total reward:-1.1 epsilon:0.5907768628656763
episode:107 steps:5 total reward:-1.08 epsilon:0.5878229785513479
episode:108 steps:10 total reward:-1.18 epsilon:0.5848838636585911
episode:109 steps:7 total reward:-1.12 epsilon:0.5819594443402982
episode:110 steps:6 total reward:-1.1 epsilon:0.5790496471185967
episode:111 steps:3 total reward:-1.04 epsilon:0.5761543988830038
episode:112 steps:2 total reward:-1.02 epsilon:0.5732736268885887
episode:113 steps:4 total reward:-1.06 epsilon:0.5704072587541458
episode:114 steps:21 total reward:-1.4000000000000001 epsilon:0.567555222460375
episode:115 steps:8 total reward:-1.1400000000000001 epsilon:0.5647174463480732
episode:116 steps:3 total reward:-1.04 epsilon:0.5618938591163328
episode:117 steps:2 total reward:-1.02 epsilon:0.5590843898207511
episode:118 steps:18 total reward:-1.34 epsilon:0.5562889678716474
[2017-07-16 15:00:31,606] Starting new video recorder writing to C:\Users\Abdul\Documents\My Projects\Deep learning nano degree\my-experiments\reinforcement learning\monitor\openaigym.video.2.12772.video000125.json
episode:119 steps:10 total reward:-1.18 epsilon:0.5535075230322891
episode:120 steps:2 total reward:-1.02 epsilon:0.5507399854171277
episode:121 steps:2 total reward:-1.02 epsilon:0.547986285490042
episode:122 steps:12 total reward:-1.22 epsilon:0.5452463540625918
episode:123 steps:4 total reward:-1.06 epsilon:0.5425201222922789
episode:124 steps:2 total reward:-1.02 epsilon:0.5398075216808175
episode:125 steps:19 total reward:-1.36 epsilon:0.5371084840724134
episode:126 steps:4 total reward:-1.06 epsilon:0.5344229416520513
episode:127 steps:2 total reward:-1.02 epsilon:0.531750826943791
episode:128 steps:14 total reward:-1.26 epsilon:0.5290920728090721
episode:129 steps:6 total reward:-1.1 epsilon:0.5264466124450268
episode:130 steps:8 total reward:-1.1400000000000001 epsilon:0.5238143793828016
episode:131 steps:3 total reward:-1.04 epsilon:0.5211953074858876
episode:132 steps:15 total reward:-1.28 epsilon:0.5185893309484582
episode:133 steps:21 total reward:-1.4000000000000001 epsilon:0.5159963842937159
episode:134 steps:10 total reward:-1.18 epsilon:0.5134164023722473
episode:135 steps:4 total reward:-1.06 epsilon:0.510849320360386
episode:136 steps:12 total reward:-1.22 epsilon:0.5082950737585841
episode:137 steps:9 total reward:-1.16 epsilon:0.5057535983897912
episode:138 steps:3 total reward:-1.04 epsilon:0.5032248303978422
episode:139 steps:13 total reward:-1.24 epsilon:0.500708706245853
episode:140 steps:16 total reward:-1.3 epsilon:0.4982051627146237
episode:141 steps:10 total reward:-1.18 epsilon:0.49571413690105054
episode:142 steps:6 total reward:0.9 epsilon:0.4932355662165453
episode:143 steps:23 total reward:-1.4400000000000002 epsilon:0.4907693883854626
episode:144 steps:2 total reward:-1.02 epsilon:0.4883155414435353
episode:145 steps:9 total reward:-1.16 epsilon:0.4858739637363176
episode:146 steps:13 total reward:-1.24 epsilon:0.483444593917636
episode:147 steps:5 total reward:-1.08 epsilon:0.4810273709480478
episode:148 steps:5 total reward:-1.08 epsilon:0.47862223409330756
episode:149 steps:4 total reward:-1.06 epsilon:0.47622912292284103
episode:150 steps:3 total reward:-1.04 epsilon:0.4738479773082268
episode:151 steps:9 total reward:-1.16 epsilon:0.47147873742168567
episode:152 steps:4 total reward:-1.06 epsilon:0.46912134373457726
episode:153 steps:9 total reward:-1.16 epsilon:0.46677573701590436
episode:154 steps:3 total reward:-1.04 epsilon:0.46444185833082485
episode:155 steps:3 total reward:-1.04 epsilon:0.46211964903917074
episode:156 steps:5 total reward:-1.08 epsilon:0.4598090507939749
episode:157 steps:21 total reward:0.5999999999999999 epsilon:0.457510005540005
episode:158 steps:5 total reward:-1.08 epsilon:0.45522245551230495
episode:159 steps:6 total reward:-1.1 epsilon:0.4529463432347434
episode:160 steps:11 total reward:-1.2 epsilon:0.4506816115185697
episode:161 steps:8 total reward:-1.1400000000000001 epsilon:0.4484282034609769
episode:162 steps:14 total reward:-1.26 epsilon:0.446186062443672
episode:163 steps:14 total reward:-1.26 epsilon:0.4439551321314536
episode:164 steps:11 total reward:-1.2 epsilon:0.4417353564707963
episode:165 steps:5 total reward:-1.08 epsilon:0.43952667968844233
episode:166 steps:20 total reward:-1.3800000000000001 epsilon:0.43732904629000013
episode:167 steps:5 total reward:-1.08 epsilon:0.4351424010585501
episode:168 steps:9 total reward:-1.16 epsilon:0.43296668905325736
episode:169 steps:8 total reward:-1.1400000000000001 epsilon:0.43080185560799106
episode:170 steps:12 total reward:-1.22 epsilon:0.4286478463299511
episode:171 steps:17 total reward:-1.32 epsilon:0.42650460709830135
episode:172 steps:20 total reward:-1.3800000000000001 epsilon:0.42437208406280985
episode:173 steps:12 total reward:-1.22 epsilon:0.4222502236424958
episode:174 steps:9 total reward:-1.16 epsilon:0.42013897252428334
episode:175 steps:14 total reward:-1.26 epsilon:0.4180382776616619
episode:176 steps:6 total reward:-1.1 epsilon:0.4159480862733536
episode:177 steps:20 total reward:-1.3800000000000001 epsilon:0.41386834584198684
episode:178 steps:13 total reward:-1.24 epsilon:0.4117990041127769
episode:179 steps:14 total reward:-1.26 epsilon:0.40974000909221303
episode:180 steps:16 total reward:-1.3 epsilon:0.40769130904675194
episode:181 steps:4 total reward:-1.06 epsilon:0.40565285250151817
episode:182 steps:71 total reward:-0.4000000000000008 epsilon:0.4036245882390106
episode:183 steps:13 total reward:-1.24 epsilon:0.4016064652978155
episode:184 steps:43 total reward:-1.8400000000000003 epsilon:0.3995984329713264
episode:185 steps:16 total reward:-1.3 epsilon:0.3976004408064698
episode:186 steps:15 total reward:-1.28 epsilon:0.39561243860243744
episode:187 steps:26 total reward:-1.5 epsilon:0.3936343764094253
episode:188 steps:14 total reward:-1.26 epsilon:0.39166620452737816
episode:189 steps:6 total reward:-1.1 epsilon:0.3897078735047413
episode:190 steps:6 total reward:-1.1 epsilon:0.3877593341372176
episode:191 steps:26 total reward:-1.5 epsilon:0.3858205374665315
episode:192 steps:3 total reward:-1.04 epsilon:0.38389143477919885
episode:193 steps:13 total reward:-1.24 epsilon:0.3819719776053028
episode:194 steps:24 total reward:-1.4600000000000002 epsilon:0.3800621177172763
episode:195 steps:29 total reward:-1.56 epsilon:0.37816180712868996
episode:196 steps:29 total reward:0.43999999999999984 epsilon:0.37627099809304654
episode:197 steps:22 total reward:-1.4200000000000002 epsilon:0.3743896431025813
episode:198 steps:13 total reward:-1.24 epsilon:0.37251769488706843
episode:199 steps:16 total reward:-1.3 epsilon:0.3706551064126331
episode:200 steps:24 total reward:-1.4600000000000002 epsilon:0.36880183088056995
episode:201 steps:8 total reward:-1.1400000000000001 epsilon:0.3669578217261671
episode:202 steps:14 total reward:-1.26 epsilon:0.36512303261753626
episode:203 steps:7 total reward:0.88 epsilon:0.3632974174544486
episode:204 steps:3 total reward:-1.04 epsilon:0.3614809303671764
episode:205 steps:11 total reward:-1.2 epsilon:0.3596735257153405
episode:206 steps:34 total reward:-1.6600000000000001 epsilon:0.3578751580867638
episode:207 steps:6 total reward:-1.1 epsilon:0.35608578229633
episode:208 steps:8 total reward:-1.1400000000000001 epsilon:0.3543053533848483
episode:209 steps:7 total reward:-1.12 epsilon:0.35253382661792404
episode:210 steps:5 total reward:-1.08 epsilon:0.3507711574848344
episode:211 steps:5 total reward:-1.08 epsilon:0.34901730169741024
episode:212 steps:8 total reward:0.86 epsilon:0.3472722151889232
[2017-07-16 15:00:38,638] Starting new video recorder writing to C:\Users\Abdul\Documents\My Projects\Deep learning nano degree\my-experiments\reinforcement learning\monitor\openaigym.video.2.12772.video000216.json
episode:213 steps:16 total reward:-1.3 epsilon:0.3455358541129786
episode:214 steps:13 total reward:-1.24 epsilon:0.3438081748424137
episode:215 steps:13 total reward:-1.24 epsilon:0.3420891339682016
episode:216 steps:19 total reward:-1.36 epsilon:0.3403786882983606
episode:217 steps:7 total reward:-1.12 epsilon:0.3386767948568688
episode:218 steps:10 total reward:-1.18 epsilon:0.33698341088258443
episode:219 steps:12 total reward:-1.22 epsilon:0.3352984938281715
episode:220 steps:6 total reward:-1.1 epsilon:0.33362200135903064
episode:221 steps:25 total reward:-1.4800000000000002 epsilon:0.33195389135223546
episode:222 steps:14 total reward:-1.26 epsilon:0.3302941218954743
episode:223 steps:5 total reward:-1.08 epsilon:0.32864265128599696
episode:224 steps:15 total reward:-1.28 epsilon:0.326999438029567
episode:225 steps:22 total reward:0.5799999999999998 epsilon:0.3253644408394192
episode:226 steps:18 total reward:-1.34 epsilon:0.3237376186352221
episode:227 steps:23 total reward:-1.4400000000000002 epsilon:0.322118930542046
episode:228 steps:4 total reward:-1.06 epsilon:0.32050833588933575
episode:229 steps:2 total reward:-1.02 epsilon:0.31890579420988907
episode:230 steps:13 total reward:-1.24 epsilon:0.3173112652388396
episode:231 steps:22 total reward:-1.4200000000000002 epsilon:0.3157247089126454
episode:232 steps:2 total reward:-1.02 epsilon:0.3141460853680822
episode:233 steps:4 total reward:-1.06 epsilon:0.3125753549412418
episode:234 steps:5 total reward:-1.08 epsilon:0.31101247816653554
episode:235 steps:6 total reward:-1.1 epsilon:0.30945741577570285
episode:236 steps:17 total reward:-1.32 epsilon:0.3079101286968243
episode:237 steps:17 total reward:-1.32 epsilon:0.3063705780533402
episode:238 steps:3 total reward:-1.04 epsilon:0.30483872516307353
episode:239 steps:18 total reward:-1.34 epsilon:0.3033145315372582
episode:240 steps:12 total reward:-1.22 epsilon:0.3017979588795719
episode:241 steps:10 total reward:-1.18 epsilon:0.30028896908517405
episode:242 steps:22 total reward:-1.4200000000000002 epsilon:0.2987875242397482
episode:243 steps:13 total reward:-1.24 epsilon:0.29729358661854943
episode:244 steps:9 total reward:-1.16 epsilon:0.29580711868545667
episode:245 steps:13 total reward:-1.24 epsilon:0.2943280830920294
episode:246 steps:20 total reward:-1.3800000000000001 epsilon:0.29285644267656924
episode:247 steps:6 total reward:-1.1 epsilon:0.2913921604631864
episode:248 steps:23 total reward:0.5599999999999998 epsilon:0.28993519966087045
episode:249 steps:19 total reward:-1.36 epsilon:0.2884855236625661
episode:250 steps:44 total reward:-1.8600000000000003 epsilon:0.28704309604425327
episode:251 steps:9 total reward:-1.16 epsilon:0.285607880564032
episode:252 steps:11 total reward:-1.2 epsilon:0.28417984116121187
episode:253 steps:25 total reward:-1.4800000000000002 epsilon:0.2827589419554058
episode:254 steps:2 total reward:-1.02 epsilon:0.28134514724562876
episode:255 steps:21 total reward:0.5999999999999999 epsilon:0.2799384215094006
episode:256 steps:55 total reward:-2.0800000000000005 epsilon:0.27853872940185365
episode:257 steps:15 total reward:-1.28 epsilon:0.27714603575484437
episode:258 steps:11 total reward:-1.2 epsilon:0.2757603055760701
episode:259 steps:14 total reward:-1.26 epsilon:0.2743815040481898
episode:260 steps:17 total reward:0.6799999999999999 epsilon:0.2730095965279488
episode:261 steps:12 total reward:-1.22 epsilon:0.27164454854530906
episode:262 steps:15 total reward:-1.28 epsilon:0.2702863258025825
episode:263 steps:55 total reward:-2.0800000000000005 epsilon:0.2689348941735696
episode:264 steps:33 total reward:-1.6400000000000001 epsilon:0.26759021970270175
episode:265 steps:10 total reward:-1.18 epsilon:0.2662522686041882
episode:266 steps:17 total reward:-1.32 epsilon:0.2649210072611673
episode:267 steps:29 total reward:-1.56 epsilon:0.26359640222486147
episode:268 steps:11 total reward:-1.2 epsilon:0.26227842021373715
episode:269 steps:14 total reward:-1.26 epsilon:0.2609670281126685
episode:270 steps:7 total reward:-1.12 epsilon:0.25966219297210513
episode:271 steps:2 total reward:-1.02 epsilon:0.2583638820072446
episode:272 steps:7 total reward:-1.12 epsilon:0.2570720625972084
episode:273 steps:14 total reward:-1.26 epsilon:0.25578670228422234
episode:274 steps:15 total reward:-1.28 epsilon:0.25450776877280124
episode:275 steps:11 total reward:-1.2 epsilon:0.2532352299289372
episode:276 steps:7 total reward:-1.12 epsilon:0.2519690537792925
episode:277 steps:26 total reward:-1.5 epsilon:0.2507092085103961
episode:278 steps:2 total reward:-1.02 epsilon:0.2494556624678441
episode:279 steps:10 total reward:-1.18 epsilon:0.24820838415550486
episode:280 steps:6 total reward:-1.1 epsilon:0.24696734223472733
episode:281 steps:6 total reward:-1.1 epsilon:0.2457325055235537
episode:282 steps:10 total reward:0.8200000000000001 epsilon:0.24450384299593592
episode:283 steps:20 total reward:0.6199999999999999 epsilon:0.24328132378095624
episode:284 steps:2 total reward:-1.02 epsilon:0.24206491716205145
episode:285 steps:6 total reward:-1.1 epsilon:0.2408545925762412
episode:286 steps:20 total reward:-1.3800000000000001 epsilon:0.23965031961336
episode:287 steps:24 total reward:-1.4600000000000002 epsilon:0.2384520680152932
episode:288 steps:40 total reward:0.21999999999999964 epsilon:0.23725980767521673
episode:289 steps:6 total reward:-1.1 epsilon:0.23607350863684065
episode:290 steps:25 total reward:0.5199999999999998 epsilon:0.23489314109365644
episode:291 steps:15 total reward:0.72 epsilon:0.23371867538818816
episode:292 steps:16 total reward:0.7 epsilon:0.23255008201124722
episode:293 steps:19 total reward:-1.36 epsilon:0.231387331601191
episode:294 steps:17 total reward:-1.32 epsilon:0.23023039494318503
episode:295 steps:9 total reward:-1.16 epsilon:0.2290792429684691
episode:296 steps:8 total reward:-1.1400000000000001 epsilon:0.22793384675362674
episode:297 steps:20 total reward:-1.3800000000000001 epsilon:0.22679417751985861
episode:298 steps:9 total reward:0.84 epsilon:0.22566020663225933
episode:299 steps:9 total reward:-1.16 epsilon:0.22453190559909803
episode:300 steps:17 total reward:-1.32 epsilon:0.22340924607110255
episode:301 steps:6 total reward:-1.1 epsilon:0.22229219984074702
episode:302 steps:23 total reward:-1.4400000000000002 epsilon:0.2211807388415433
episode:303 steps:6 total reward:-1.1 epsilon:0.22007483514733558
episode:304 steps:3 total reward:-1.04 epsilon:0.2189744609715989
episode:305 steps:6 total reward:-1.1 epsilon:0.2178795886667409
episode:306 steps:43 total reward:0.1599999999999996 epsilon:0.2167901907234072
episode:307 steps:6 total reward:-1.1 epsilon:0.21570623976979014
episode:308 steps:18 total reward:-1.34 epsilon:0.21462770857094118
episode:309 steps:6 total reward:-1.1 epsilon:0.21355457002808648
episode:310 steps:10 total reward:-1.18 epsilon:0.21248679717794605
episode:311 steps:9 total reward:-1.16 epsilon:0.21142436319205632
episode:312 steps:3 total reward:-1.04 epsilon:0.21036724137609603
episode:313 steps:13 total reward:-1.24 epsilon:0.20931540516921554
episode:314 steps:3 total reward:-1.04 epsilon:0.20826882814336947
episode:315 steps:10 total reward:-1.18 epsilon:0.20722748400265262
episode:316 steps:35 total reward:-1.6800000000000002 epsilon:0.20619134658263935
episode:317 steps:12 total reward:-1.22 epsilon:0.20516038984972615
episode:318 steps:8 total reward:-1.1400000000000001 epsilon:0.2041345879004775
episode:319 steps:11 total reward:-1.2 epsilon:0.2031139149609751
episode:320 steps:27 total reward:-1.52 epsilon:0.20209834538617025
episode:321 steps:34 total reward:-1.6600000000000001 epsilon:0.2010878536592394
episode:322 steps:38 total reward:-1.7400000000000002 epsilon:0.2000824143909432
episode:323 steps:21 total reward:0.5999999999999999 epsilon:0.19908200231898848
episode:324 steps:24 total reward:-1.4600000000000002 epsilon:0.19808659230739353
episode:325 steps:18 total reward:-1.34 epsilon:0.19709615934585656
episode:326 steps:24 total reward:-1.4600000000000002 epsilon:0.19611067854912728
episode:327 steps:12 total reward:-1.22 epsilon:0.19513012515638165
episode:328 steps:21 total reward:-1.4000000000000001 epsilon:0.19415447453059972
episode:329 steps:9 total reward:-1.16 epsilon:0.19318370215794672
episode:330 steps:25 total reward:0.5199999999999998 epsilon:0.192217783647157
episode:331 steps:28 total reward:-1.54 epsilon:0.1912566947289212
episode:332 steps:21 total reward:-1.4000000000000001 epsilon:0.1903004112552766
episode:333 steps:10 total reward:-1.18 epsilon:0.18934890919900021
episode:334 steps:16 total reward:-1.3 epsilon:0.18840216465300522
episode:335 steps:19 total reward:-1.36 epsilon:0.18746015382974018
episode:336 steps:25 total reward:0.5199999999999998 epsilon:0.1865228530605915
episode:337 steps:6 total reward:-1.1 epsilon:0.18559023879528855
episode:338 steps:2 total reward:-1.02 epsilon:0.1846622876013121
episode:339 steps:27 total reward:-1.52 epsilon:0.18373897616330553
episode:340 steps:19 total reward:-1.36 epsilon:0.182820281282489
[2017-07-16 15:00:50,977] Starting new video recorder writing to C:\Users\Abdul\Documents\My Projects\Deep learning nano degree\my-experiments\reinforcement learning\monitor\openaigym.video.2.12772.video000343.json
episode:341 steps:10 total reward:-1.18 epsilon:0.18190617987607657
episode:342 steps:10 total reward:-1.18 epsilon:0.18099664897669618
episode:343 steps:3 total reward:-1.04 epsilon:0.1800916657318127
episode:344 steps:33 total reward:-1.6400000000000001 epsilon:0.17919120740315364
episode:345 steps:23 total reward:-1.4400000000000002 epsilon:0.17829525136613786
episode:346 steps:27 total reward:-1.52 epsilon:0.17740377510930716
episode:347 steps:8 total reward:-1.1400000000000001 epsilon:0.17651675623376062
episode:348 steps:31 total reward:-1.6 epsilon:0.1756341724525918
episode:349 steps:18 total reward:-1.34 epsilon:0.17475600159032884
episode:350 steps:13 total reward:-1.24 epsilon:0.17388222158237718
episode:351 steps:15 total reward:-1.28 epsilon:0.1730128104744653
episode:352 steps:43 total reward:0.1599999999999996 epsilon:0.17214774642209296
episode:353 steps:41 total reward:-1.8000000000000003 epsilon:0.1712870076899825
episode:354 steps:12 total reward:-1.22 epsilon:0.17043057265153258
episode:355 steps:6 total reward:-1.1 epsilon:0.16957841978827493
episode:356 steps:29 total reward:-1.56 epsilon:0.16873052768933355
episode:357 steps:22 total reward:0.5799999999999998 epsilon:0.1678868750508869
episode:358 steps:8 total reward:-1.1400000000000001 epsilon:0.16704744067563246
episode:359 steps:9 total reward:-1.16 epsilon:0.1662122034722543
episode:360 steps:15 total reward:-1.28 epsilon:0.16538114245489302
episode:361 steps:17 total reward:0.6799999999999999 epsilon:0.16455423674261854
episode:362 steps:20 total reward:-1.3800000000000001 epsilon:0.16373146555890544
episode:363 steps:31 total reward:-1.6 epsilon:0.16291280823111093
episode:364 steps:34 total reward:0.33999999999999975 epsilon:0.16209824418995536
episode:365 steps:21 total reward:0.5999999999999999 epsilon:0.16128775296900558
episode:366 steps:16 total reward:-1.3 epsilon:0.16048131420416054
episode:367 steps:58 total reward:-2.1400000000000006 epsilon:0.15967890763313974
episode:368 steps:28 total reward:-1.54 epsilon:0.15888051309497406
episode:369 steps:18 total reward:-1.34 epsilon:0.1580861105294992
episode:370 steps:24 total reward:-1.4600000000000002 epsilon:0.1572956799768517
episode:371 steps:31 total reward:0.3999999999999998 epsilon:0.15650920157696743
episode:372 steps:13 total reward:-1.24 epsilon:0.1557266555690826
episode:373 steps:26 total reward:-1.5 epsilon:0.1549480222912372
episode:374 steps:49 total reward:-1.9600000000000004 epsilon:0.15417328217978102
episode:375 steps:25 total reward:-1.4800000000000002 epsilon:0.1534024157688821
episode:376 steps:23 total reward:-1.4400000000000002 epsilon:0.1526354036900377
episode:377 steps:23 total reward:-1.4400000000000002 epsilon:0.1518722266715875
episode:378 steps:5 total reward:-1.08 epsilon:0.15111286553822956
episode:379 steps:23 total reward:-1.4400000000000002 epsilon:0.15035730121053842
episode:380 steps:10 total reward:0.8200000000000001 epsilon:0.14960551470448571
episode:381 steps:22 total reward:0.5799999999999998 epsilon:0.14885748713096328
episode:382 steps:5 total reward:-1.08 epsilon:0.14811319969530845
episode:383 steps:8 total reward:-1.1400000000000001 epsilon:0.1473726336968319
episode:384 steps:14 total reward:-1.26 epsilon:0.14663577052834775
episode:385 steps:35 total reward:-1.6800000000000002 epsilon:0.14590259167570602
episode:386 steps:73 total reward:-0.44000000000000083 epsilon:0.1451730787173275
episode:387 steps:7 total reward:-1.12 epsilon:0.14444721332374086
episode:388 steps:11 total reward:-1.2 epsilon:0.14372497725712216
episode:389 steps:30 total reward:0.4199999999999998 epsilon:0.14300635237083656
episode:390 steps:33 total reward:-1.6400000000000001 epsilon:0.14229132060898236
episode:391 steps:20 total reward:0.6199999999999999 epsilon:0.14157986400593744
episode:392 steps:9 total reward:-1.16 epsilon:0.14087196468590776
episode:393 steps:32 total reward:-1.62 epsilon:0.14016760486247823
episode:394 steps:26 total reward:-1.5 epsilon:0.13946676683816583
episode:395 steps:19 total reward:-1.36 epsilon:0.138769433003975
episode:396 steps:23 total reward:-1.4400000000000002 epsilon:0.13807558583895513
episode:397 steps:34 total reward:-1.6600000000000001 epsilon:0.13738520790976036
episode:398 steps:25 total reward:0.5199999999999998 epsilon:0.13669828187021155
episode:399 steps:22 total reward:-1.4200000000000002 epsilon:0.13601479046086049
episode:400 steps:12 total reward:-1.22 epsilon:0.1353347165085562
episode:401 steps:32 total reward:-1.62 epsilon:0.1346580429260134
episode:402 steps:46 total reward:-1.9000000000000004 epsilon:0.13398475271138335
episode:403 steps:8 total reward:-1.1400000000000001 epsilon:0.13331482894782642
episode:404 steps:8 total reward:-1.1400000000000001 epsilon:0.13264825480308728
episode:405 steps:8 total reward:-1.1400000000000001 epsilon:0.13198501352907185
episode:406 steps:7 total reward:-1.12 epsilon:0.1313250884614265
episode:407 steps:30 total reward:-1.58 epsilon:0.13066846301911936
episode:408 steps:13 total reward:-1.24 epsilon:0.13001512070402377
episode:409 steps:10 total reward:0.8200000000000001 epsilon:0.12936504510050365
episode:410 steps:5 total reward:-1.08 epsilon:0.12871821987500112
episode:411 steps:5 total reward:-1.08 epsilon:0.12807462877562611
episode:412 steps:7 total reward:-1.12 epsilon:0.12743425563174798
episode:413 steps:15 total reward:-1.28 epsilon:0.12679708435358925
episode:414 steps:27 total reward:-1.52 epsilon:0.1261630989318213
episode:415 steps:15 total reward:-1.28 epsilon:0.1255322834371622
episode:416 steps:57 total reward:-2.1200000000000006 epsilon:0.12490462201997637
episode:417 steps:8 total reward:-1.1400000000000001 epsilon:0.1242800989098765
episode:418 steps:14 total reward:-1.26 epsilon:0.12365869841532712
episode:419 steps:8 total reward:-1.1400000000000001 epsilon:0.12304040492325048
episode:420 steps:2 total reward:-1.02 epsilon:0.12242520289863423
episode:421 steps:65 total reward:-2.2800000000000007 epsilon:0.12181307688414106
episode:422 steps:15 total reward:-1.28 epsilon:0.12120401149972035
episode:423 steps:6 total reward:-1.1 epsilon:0.12059799144222175
episode:424 steps:12 total reward:-1.22 epsilon:0.11999500148501063
episode:425 steps:23 total reward:0.5599999999999998 epsilon:0.11939502647758558
episode:426 steps:13 total reward:-1.24 epsilon:0.11879805134519765
episode:427 steps:12 total reward:-1.22 epsilon:0.11820406108847166
episode:428 steps:11 total reward:-1.2 epsilon:0.1176130407830293
episode:429 steps:24 total reward:-1.4600000000000002 epsilon:0.11702497557911415
episode:430 steps:31 total reward:-1.6 epsilon:0.11643985070121858
episode:431 steps:15 total reward:-1.28 epsilon:0.11585765144771248
episode:432 steps:69 total reward:-2.3600000000000008 epsilon:0.11527836319047392
episode:433 steps:2 total reward:-1.02 epsilon:0.11470197137452155
episode:434 steps:13 total reward:-1.24 epsilon:0.11412846151764894
episode:435 steps:22 total reward:-1.4200000000000002 epsilon:0.1135578192100607
episode:436 steps:30 total reward:-1.58 epsilon:0.11299003011401039
episode:437 steps:20 total reward:-1.3800000000000001 epsilon:0.11242507996344034
episode:438 steps:31 total reward:-1.6 epsilon:0.11186295456362313
episode:439 steps:7 total reward:-1.12 epsilon:0.11130363979080501
episode:440 steps:19 total reward:-1.36 epsilon:0.11074712159185099
episode:441 steps:10 total reward:-1.18 epsilon:0.11019338598389174
episode:442 steps:17 total reward:0.6799999999999999 epsilon:0.10964241905397228
episode:443 steps:21 total reward:-1.4000000000000001 epsilon:0.10909420695870241
episode:444 steps:32 total reward:-1.62 epsilon:0.1085487359239089
episode:445 steps:18 total reward:-1.34 epsilon:0.10800599224428936
episode:446 steps:16 total reward:-1.3 epsilon:0.10746596228306791
episode:447 steps:5 total reward:-1.08 epsilon:0.10692863247165257
episode:448 steps:7 total reward:-1.12 epsilon:0.1063939893092943
episode:449 steps:31 total reward:-1.6 epsilon:0.10586201936274783
episode:450 steps:10 total reward:-1.18 epsilon:0.10533270926593409
episode:451 steps:10 total reward:-1.18 epsilon:0.10480604571960442
episode:452 steps:3 total reward:-1.04 epsilon:0.1042820154910064
episode:453 steps:8 total reward:-1.1400000000000001 epsilon:0.10376060541355137
episode:454 steps:10 total reward:0.8200000000000001 epsilon:0.1032418023864836
episode:455 steps:9 total reward:-1.16 epsilon:0.10272559337455119
episode:456 steps:15 total reward:-1.28 epsilon:0.10221196540767843
episode:457 steps:13 total reward:-1.24 epsilon:0.10170090558064004
episode:458 steps:10 total reward:-1.18 epsilon:0.10119240105273684
episode:459 steps:29 total reward:-1.56 epsilon:0.10068643904747315
episode:460 steps:25 total reward:-1.4800000000000002 epsilon:0.10018300685223579
episode:461 steps:5 total reward:-1.08 epsilon:0.0996820918179746
episode:462 steps:27 total reward:0.47999999999999987 epsilon:0.09918368135888474
episode:463 steps:18 total reward:-1.34 epsilon:0.09868776295209031
episode:464 steps:33 total reward:-1.6400000000000001 epsilon:0.09819432413732986
episode:465 steps:9 total reward:-1.16 epsilon:0.09770335251664321
episode:466 steps:4 total reward:-1.06 epsilon:0.09721483575406
episode:467 steps:35 total reward:-1.6800000000000002 epsilon:0.09672876157528969
episode:468 steps:11 total reward:-1.2 epsilon:0.09624511776741324
episode:469 steps:7 total reward:-1.12 epsilon:0.09576389217857617
episode:470 steps:9 total reward:-1.16 epsilon:0.09528507271768329
episode:471 steps:14 total reward:-1.26 epsilon:0.09480864735409487
episode:472 steps:2 total reward:-1.02 epsilon:0.0943346041173244
episode:473 steps:15 total reward:-1.28 epsilon:0.09386293109673778
episode:474 steps:39 total reward:0.23999999999999966 epsilon:0.09339361644125409
episode:475 steps:13 total reward:-1.24 epsilon:0.09292664835904782
episode:476 steps:13 total reward:0.76 epsilon:0.09246201511725258
episode:477 steps:38 total reward:-1.7400000000000002 epsilon:0.09199970504166631
episode:478 steps:26 total reward:-1.5 epsilon:0.09153970651645797
episode:479 steps:50 total reward:0.019999999999999463 epsilon:0.09108200798387568
episode:480 steps:4 total reward:-1.06 epsilon:0.0906265979439563
episode:481 steps:13 total reward:0.76 epsilon:0.09017346495423652
episode:482 steps:23 total reward:-1.4400000000000002 epsilon:0.08972259762946533
episode:483 steps:4 total reward:-1.06 epsilon:0.089273984641318
episode:484 steps:6 total reward:-1.1 epsilon:0.0888276147181114
episode:485 steps:3 total reward:-1.04 epsilon:0.08838347664452084
episode:486 steps:28 total reward:-1.54 epsilon:0.08794155926129824
episode:487 steps:26 total reward:-1.5 epsilon:0.08750185146499175
episode:488 steps:10 total reward:-1.18 epsilon:0.08706434220766679
episode:489 steps:20 total reward:-1.3800000000000001 epsilon:0.08662902049662846
episode:490 steps:33 total reward:-1.6400000000000001 epsilon:0.08619587539414532
episode:491 steps:20 total reward:0.6199999999999999 epsilon:0.08576489601717459
episode:492 steps:16 total reward:-1.3 epsilon:0.08533607153708872
episode:493 steps:18 total reward:-1.34 epsilon:0.08490939117940327
episode:494 steps:14 total reward:-1.26 epsilon:0.08448484422350626
episode:495 steps:14 total reward:-1.26 epsilon:0.08406242000238873
episode:496 steps:15 total reward:-1.28 epsilon:0.08364210790237678
episode:497 steps:38 total reward:-1.7400000000000002 epsilon:0.0832238973628649
episode:498 steps:9 total reward:-1.16 epsilon:0.08280777787605056
episode:499 steps:24 total reward:0.5399999999999998 epsilon:0.08239373898667031
episode:500 steps:11 total reward:0.8 epsilon:0.08198177029173696
episode:501 steps:21 total reward:-1.4000000000000001 epsilon:0.08157186144027828
episode:502 steps:8 total reward:-1.1400000000000001 epsilon:0.0811640021330769
episode:503 steps:15 total reward:-1.28 epsilon:0.08075818212241151
episode:504 steps:11 total reward:-1.2 epsilon:0.08035439121179945
episode:505 steps:9 total reward:-1.16 epsilon:0.07995261925574046
episode:506 steps:13 total reward:-1.24 epsilon:0.07955285615946175
episode:507 steps:6 total reward:-1.1 epsilon:0.07915509187866444
episode:508 steps:21 total reward:-1.4000000000000001 epsilon:0.07875931641927113
episode:509 steps:26 total reward:0.4999999999999999 epsilon:0.07836551983717477
[2017-07-16 15:01:12,240] Starting new video recorder writing to C:\Users\Abdul\Documents\My Projects\Deep learning nano degree\my-experiments\reinforcement learning\monitor\openaigym.video.2.12772.video000512.json
episode:510 steps:29 total reward:0.43999999999999984 epsilon:0.07797369223798889
episode:511 steps:10 total reward:-1.18 epsilon:0.07758382377679894
episode:512 steps:7 total reward:-1.12 epsilon:0.07719590465791494
episode:513 steps:10 total reward:0.8200000000000001 epsilon:0.07680992513462537
episode:514 steps:46 total reward:-1.9000000000000004 epsilon:0.07642587550895225
episode:515 steps:20 total reward:0.6199999999999999 epsilon:0.07604374613140748
episode:516 steps:36 total reward:0.2999999999999997 epsilon:0.07566352740075044
episode:517 steps:26 total reward:-1.5 epsilon:0.07528520976374668
episode:518 steps:13 total reward:0.76 epsilon:0.07490878371492794
episode:519 steps:25 total reward:-1.4800000000000002 epsilon:0.0745342397963533
episode:520 steps:18 total reward:0.6599999999999999 epsilon:0.07416156859737154
episode:521 steps:19 total reward:-1.36 epsilon:0.07379076075438468
episode:522 steps:7 total reward:-1.12 epsilon:0.07342180695061275
episode:523 steps:32 total reward:-1.62 epsilon:0.07305469791585968
episode:524 steps:36 total reward:-1.7000000000000002 epsilon:0.07268942442628039
episode:525 steps:16 total reward:-1.3 epsilon:0.07232597730414898
episode:526 steps:26 total reward:0.4999999999999999 epsilon:0.07196434741762824
episode:527 steps:39 total reward:-1.7600000000000002 epsilon:0.0716045256805401
episode:528 steps:9 total reward:0.84 epsilon:0.0712465030521374
episode:529 steps:10 total reward:-1.18 epsilon:0.0708902705368767
episode:530 steps:21 total reward:-1.4000000000000001 epsilon:0.07053581918419231
episode:531 steps:47 total reward:0.07999999999999952 epsilon:0.07018314008827135
episode:532 steps:12 total reward:-1.22 epsilon:0.06983222438783
episode:533 steps:22 total reward:-1.4200000000000002 epsilon:0.06948306326589085
episode:534 steps:8 total reward:-1.1400000000000001 epsilon:0.0691356479495614
episode:535 steps:55 total reward:-2.0800000000000005 epsilon:0.06878996970981359
episode:536 steps:9 total reward:0.84 epsilon:0.06844601986126451
episode:537 steps:2 total reward:-1.02 epsilon:0.06810378976195819
episode:538 steps:19 total reward:0.6399999999999999 epsilon:0.0677632708131484
episode:539 steps:40 total reward:0.21999999999999964 epsilon:0.06742445445908266
episode:540 steps:15 total reward:-1.28 epsilon:0.06708733218678724
episode:541 steps:10 total reward:-1.18 epsilon:0.0667518955258533
episode:542 steps:20 total reward:-1.3800000000000001 epsilon:0.06641813604822402
episode:543 steps:13 total reward:-1.24 epsilon:0.0660860453679829
episode:544 steps:51 total reward:-4.440892098500626e-16 epsilon:0.06575561514114299
episode:545 steps:26 total reward:0.4999999999999999 epsilon:0.06542683706543727
episode:546 steps:9 total reward:-1.16 epsilon:0.06509970288011008
episode:547 steps:16 total reward:-1.3 epsilon:0.06477420436570952
episode:548 steps:18 total reward:-1.34 epsilon:0.06445033334388098
episode:549 steps:55 total reward:-2.0800000000000005 epsilon:0.06412808167716157
episode:550 steps:15 total reward:-1.28 epsilon:0.06380744126877576
episode:551 steps:31 total reward:-1.6 epsilon:0.06348840406243188
episode:552 steps:10 total reward:-1.18 epsilon:0.06317096204211972
episode:553 steps:18 total reward:-1.34 epsilon:0.06285510723190912
episode:554 steps:25 total reward:-1.4800000000000002 epsilon:0.06254083169574957
episode:555 steps:41 total reward:-1.8000000000000003 epsilon:0.062228127537270826
episode:556 steps:10 total reward:0.8200000000000001 epsilon:0.06191698689958447
episode:557 steps:28 total reward:-1.54 epsilon:0.061607401965086545
episode:558 steps:43 total reward:0.1599999999999996 epsilon:0.06129936495526111
episode:559 steps:6 total reward:-1.1 epsilon:0.0609928681304848
episode:560 steps:14 total reward:-1.26 epsilon:0.060687903789832374
episode:561 steps:18 total reward:-1.34 epsilon:0.06038446427088321
episode:562 steps:59 total reward:-0.1600000000000006 epsilon:0.06008254194952879
episode:563 steps:23 total reward:-1.4400000000000002 epsilon:0.05978212923978115
episode:564 steps:13 total reward:-1.24 epsilon:0.05948321859358224
episode:565 steps:35 total reward:-1.6800000000000002 epsilon:0.05918580250061433
episode:566 steps:22 total reward:0.5799999999999998 epsilon:0.058889873488111255
episode:567 steps:14 total reward:-1.26 epsilon:0.058595424120670696
episode:568 steps:22 total reward:-1.4200000000000002 epsilon:0.05830244700006734
episode:569 steps:7 total reward:-1.12 epsilon:0.058010934765067
episode:570 steps:41 total reward:-1.8000000000000003 epsilon:0.05772088009124167
episode:571 steps:25 total reward:0.5199999999999998 epsilon:0.05743227569078546
episode:572 steps:14 total reward:-1.26 epsilon:0.05714511431233153
episode:573 steps:11 total reward:-1.2 epsilon:0.05685938874076987
episode:574 steps:14 total reward:-1.26 epsilon:0.056575091797066025
episode:575 steps:13 total reward:-1.24 epsilon:0.056292216338080694
episode:576 steps:25 total reward:-1.4800000000000002 epsilon:0.05601075525639029
episode:577 steps:15 total reward:-1.28 epsilon:0.05573070148010834
episode:578 steps:23 total reward:-1.4400000000000002 epsilon:0.0554520479727078
episode:579 steps:12 total reward:-1.22 epsilon:0.05517478773284426
episode:580 steps:6 total reward:-1.1 epsilon:0.05489891379418004
episode:581 steps:23 total reward:-1.4400000000000002 epsilon:0.05462441922520914
episode:582 steps:16 total reward:-1.3 epsilon:0.0543512971290831
episode:583 steps:36 total reward:-1.7000000000000002 epsilon:0.05407954064343768
episode:584 steps:16 total reward:-1.3 epsilon:0.05380914294022049
episode:585 steps:22 total reward:-1.4200000000000002 epsilon:0.05354009722551939
episode:586 steps:21 total reward:0.5999999999999999 epsilon:0.05327239673939179
episode:587 steps:15 total reward:0.72 epsilon:0.053006034755694834
episode:588 steps:26 total reward:0.4999999999999999 epsilon:0.052741004581916356
episode:589 steps:23 total reward:-1.4400000000000002 epsilon:0.052477299559006776
episode:590 steps:15 total reward:-1.28 epsilon:0.052214913061211746
episode:591 steps:5 total reward:-1.08 epsilon:0.05195383849590569
episode:592 steps:7 total reward:-1.12 epsilon:0.05169406930342616
episode:593 steps:9 total reward:-1.16 epsilon:0.05143559895690903
episode:594 steps:40 total reward:-1.7800000000000002 epsilon:0.051178420962124486
episode:595 steps:18 total reward:-1.34 epsilon:0.05092252885731386
episode:596 steps:8 total reward:-1.1400000000000001 epsilon:0.05066791621302729
episode:597 steps:35 total reward:0.31999999999999973 epsilon:0.05041457663196215
episode:598 steps:12 total reward:-1.22 epsilon:0.050162503748802344
episode:599 steps:49 total reward:-1.9600000000000004 epsilon:0.049911691230058335
episode:600 steps:9 total reward:-1.16 epsilon:0.04966213277390804
episode:601 steps:27 total reward:-1.52 epsilon:0.0494138221100385
episode:602 steps:40 total reward:0.21999999999999964 epsilon:0.04916675299948831
episode:603 steps:13 total reward:-1.24 epsilon:0.04892091923449087
episode:604 steps:36 total reward:-1.7000000000000002 epsilon:0.04867631463831842
episode:605 steps:25 total reward:-1.4800000000000002 epsilon:0.048432933065126825
episode:606 steps:27 total reward:0.47999999999999987 epsilon:0.048190768399801194
episode:607 steps:21 total reward:0.5999999999999999 epsilon:0.04794981455780219
episode:608 steps:16 total reward:0.7 epsilon:0.04771006548501318
episode:609 steps:14 total reward:0.74 epsilon:0.047471515157588115
episode:610 steps:9 total reward:-1.16 epsilon:0.047234157581800176
episode:611 steps:34 total reward:-1.6600000000000001 epsilon:0.046997986793891174
episode:612 steps:13 total reward:0.76 epsilon:0.04676299685992172
episode:613 steps:25 total reward:0.5199999999999998 epsilon:0.04652918187562211
episode:614 steps:19 total reward:-1.36 epsilon:0.046296535966244
episode:615 steps:11 total reward:-1.2 epsilon:0.046065053286412784
episode:616 steps:8 total reward:-1.1400000000000001 epsilon:0.04583472801998072
episode:617 steps:40 total reward:-1.7800000000000002 epsilon:0.045605554379880814
episode:618 steps:5 total reward:-1.08 epsilon:0.04537752660798141
episode:619 steps:12 total reward:0.78 epsilon:0.0451506389749415
episode:620 steps:8 total reward:-1.1400000000000001 epsilon:0.044924885780066794
episode:621 steps:9 total reward:-1.16 epsilon:0.04470026135116646
episode:622 steps:48 total reward:-1.9400000000000004 epsilon:0.04447676004441063
episode:623 steps:6 total reward:-1.1 epsilon:0.04425437624418858
episode:624 steps:8 total reward:-1.1400000000000001 epsilon:0.04403310436296763
episode:625 steps:54 total reward:-0.0600000000000005 epsilon:0.043812938841152796
episode:626 steps:12 total reward:-1.22 epsilon:0.04359387414694703
episode:627 steps:16 total reward:0.7 epsilon:0.043375904776212296
episode:628 steps:13 total reward:-1.24 epsilon:0.043159025252331236
episode:629 steps:20 total reward:0.6199999999999999 epsilon:0.04294323012606958
episode:630 steps:13 total reward:-1.24 epsilon:0.04272851397543923
episode:631 steps:2 total reward:-1.02 epsilon:0.04251487140556204
episode:632 steps:17 total reward:-1.32 epsilon:0.04230229704853423
episode:633 steps:18 total reward:-1.34 epsilon:0.04209078556329156
episode:634 steps:14 total reward:-1.26 epsilon:0.0418803316354751
episode:635 steps:13 total reward:-1.24 epsilon:0.041670929977297724
episode:636 steps:21 total reward:-1.4000000000000001 epsilon:0.04146257532741124
episode:637 steps:15 total reward:-1.28 epsilon:0.04125526245077418
episode:638 steps:23 total reward:0.5599999999999998 epsilon:0.04104898613852031
episode:639 steps:14 total reward:-1.26 epsilon:0.04084374120782771
episode:640 steps:9 total reward:-1.16 epsilon:0.04063952250178857
episode:641 steps:5 total reward:-1.08 epsilon:0.04043632488927963
episode:642 steps:36 total reward:0.2999999999999997 epsilon:0.04023414326483323
episode:643 steps:15 total reward:-1.28 epsilon:0.040032972548509065
episode:644 steps:5 total reward:-1.08 epsilon:0.03983280768576652
episode:645 steps:14 total reward:-1.26 epsilon:0.03963364364733769
episode:646 steps:11 total reward:-1.2 epsilon:0.039435475429100995
episode:647 steps:23 total reward:0.5599999999999998 epsilon:0.03923829805195549
episode:648 steps:39 total reward:-1.7600000000000002 epsilon:0.03904210656169572
episode:649 steps:5 total reward:-1.08 epsilon:0.03884689602888724
episode:650 steps:14 total reward:-1.26 epsilon:0.0386526615487428
episode:651 steps:19 total reward:0.6399999999999999 epsilon:0.03845939824099909
episode:652 steps:25 total reward:-1.4800000000000002 epsilon:0.03826710124979409
episode:653 steps:20 total reward:-1.3800000000000001 epsilon:0.038075765743545126
episode:654 steps:29 total reward:-1.56 epsilon:0.0378853869148274
episode:655 steps:37 total reward:0.2799999999999997 epsilon:0.03769595998025326
episode:656 steps:5 total reward:-1.08 epsilon:0.03750748018035199
episode:657 steps:15 total reward:-1.28 epsilon:0.037319942779450235
episode:658 steps:11 total reward:-1.2 epsilon:0.037133343065552986
episode:659 steps:27 total reward:-1.52 epsilon:0.03694767635022522
episode:660 steps:35 total reward:0.31999999999999973 epsilon:0.036762937968474095
episode:661 steps:16 total reward:-1.3 epsilon:0.03657912327863173
episode:662 steps:62 total reward:-2.2200000000000006 epsilon:0.036396227662238566
episode:663 steps:46 total reward:0.09999999999999953 epsilon:0.03621424652392737
episode:664 steps:24 total reward:0.5399999999999998 epsilon:0.036033175291307735
episode:665 steps:6 total reward:-1.1 epsilon:0.03585300941485119
episode:666 steps:14 total reward:-1.26 epsilon:0.035673744367776934
episode:667 steps:21 total reward:-1.4000000000000001 epsilon:0.03549537564593805
episode:668 steps:8 total reward:-1.1400000000000001 epsilon:0.035317898767708356
episode:669 steps:6 total reward:-1.1 epsilon:0.03514130927386981
episode:670 steps:5 total reward:-1.08 epsilon:0.03496560272750046
episode:671 steps:11 total reward:-1.2 epsilon:0.03479077471386296
episode:672 steps:21 total reward:-1.4000000000000001 epsilon:0.03461682084029365
episode:673 steps:8 total reward:-1.1400000000000001 epsilon:0.034443736736092176
episode:674 steps:9 total reward:-1.16 epsilon:0.034271518052411715
episode:675 steps:18 total reward:-1.34 epsilon:0.034100160462149656
episode:676 steps:5 total reward:-1.08 epsilon:0.03392965965983891
episode:677 steps:22 total reward:-1.4200000000000002 epsilon:0.033760011361539714
episode:678 steps:8 total reward:-1.1400000000000001 epsilon:0.03359121130473201
episode:679 steps:15 total reward:-1.28 epsilon:0.033423255248208356
episode:680 steps:20 total reward:-1.3800000000000001 epsilon:0.03325613897196732
episode:681 steps:5 total reward:-1.08 epsilon:0.03308985827710748
episode:682 steps:33 total reward:-1.6400000000000001 epsilon:0.032924408985721944
episode:683 steps:40 total reward:-1.7800000000000002 epsilon:0.03275978694079333
episode:684 steps:29 total reward:-1.56 epsilon:0.032595988006089364
episode:685 steps:21 total reward:-1.4000000000000001 epsilon:0.032433008066058915
episode:686 steps:17 total reward:-1.32 epsilon:0.03227084302572862
episode:687 steps:100 total reward:-2.9800000000000013 epsilon:0.032109488810599975
episode:688 steps:19 total reward:-1.36 epsilon:0.031948941366546975
episode:689 steps:17 total reward:-1.32 epsilon:0.03178919665971424
episode:690 steps:7 total reward:-1.12 epsilon:0.03163025067641567
episode:691 steps:38 total reward:-1.7400000000000002 epsilon:0.03147209942303359
episode:692 steps:35 total reward:-1.6800000000000002 epsilon:0.03131473892591842
episode:693 steps:57 total reward:-2.1200000000000006 epsilon:0.031158165231288826
episode:694 steps:10 total reward:-1.18 epsilon:0.03100237440513238
episode:695 steps:18 total reward:0.6599999999999999 epsilon:0.030847362533106718
episode:696 steps:7 total reward:-1.12 epsilon:0.030693125720441184
episode:697 steps:26 total reward:-1.5 epsilon:0.030539660091838977
episode:698 steps:17 total reward:0.6799999999999999 epsilon:0.03038696179137978
episode:699 steps:13 total reward:-1.24 epsilon:0.030235026982422884
episode:700 steps:19 total reward:0.6399999999999999 epsilon:0.030083851847510768
episode:701 steps:26 total reward:-1.5 epsilon:0.029933432588273214
episode:702 steps:14 total reward:-1.26 epsilon:0.029783765425331846
episode:703 steps:24 total reward:0.5399999999999998 epsilon:0.029634846598205186
episode:704 steps:15 total reward:-1.28 epsilon:0.02948667236521416
episode:705 steps:7 total reward:-1.12 epsilon:0.029339239003388088
episode:706 steps:26 total reward:0.4999999999999999 epsilon:0.029192542808371146
episode:707 steps:21 total reward:-1.4000000000000001 epsilon:0.02904658009432929
episode:708 steps:14 total reward:0.74 epsilon:0.028901347193857643
episode:709 steps:7 total reward:0.88 epsilon:0.028756840457888354
episode:710 steps:43 total reward:-1.8400000000000003 epsilon:0.02861305625559891
episode:711 steps:38 total reward:-1.7400000000000002 epsilon:0.028469990974320916
episode:712 steps:36 total reward:-1.7000000000000002 epsilon:0.02832764101944931
episode:713 steps:18 total reward:-1.34 epsilon:0.028186002814352063
episode:714 steps:18 total reward:0.6599999999999999 epsilon:0.0280450728002803
episode:715 steps:33 total reward:0.35999999999999976 epsilon:0.0279048474362789
episode:716 steps:5 total reward:-1.08 epsilon:0.027765323199097504
episode:717 steps:17 total reward:-1.32 epsilon:0.027626496583102015
episode:718 steps:20 total reward:0.6199999999999999 epsilon:0.027488364100186506
episode:719 steps:12 total reward:-1.22 epsilon:0.027350922279685573
episode:720 steps:8 total reward:-1.1400000000000001 epsilon:0.027214167668287145
episode:721 steps:17 total reward:-1.32 epsilon:0.02707809682994571
episode:722 steps:23 total reward:-1.4400000000000002 epsilon:0.02694270634579598
episode:723 steps:18 total reward:-1.34 epsilon:0.026807992814067
episode:724 steps:23 total reward:-1.4400000000000002 epsilon:0.026673952849996664
episode:725 steps:30 total reward:-1.58 epsilon:0.02654058308574668
episode:726 steps:4 total reward:-1.06 epsilon:0.026407880170317945
episode:727 steps:11 total reward:0.8 epsilon:0.026275840769466357
[2017-07-16 15:01:42,927] Starting new video recorder writing to C:\Users\Abdul\Documents\My Projects\Deep learning nano degree\my-experiments\reinforcement learning\monitor\openaigym.video.2.12772.video000729.json
episode:728 steps:22 total reward:-1.4200000000000002 epsilon:0.026144461565619025
episode:729 steps:30 total reward:-1.58 epsilon:0.02601373925779093
episode:730 steps:15 total reward:-1.28 epsilon:0.025883670561501974
episode:731 steps:31 total reward:0.3999999999999998 epsilon:0.025754252208694463
episode:732 steps:24 total reward:0.5399999999999998 epsilon:0.02562548094765099
episode:733 steps:8 total reward:-1.1400000000000001 epsilon:0.025497353542912736
episode:734 steps:32 total reward:-1.62 epsilon:0.02536986677519817
episode:735 steps:13 total reward:-1.24 epsilon:0.02524301744132218
episode:736 steps:9 total reward:-1.16 epsilon:0.025116802354115567
episode:737 steps:16 total reward:-1.3 epsilon:0.024991218342344988
episode:738 steps:16 total reward:-1.3 epsilon:0.024866262250633264
episode:739 steps:9 total reward:0.84 epsilon:0.024741930939380097
episode:740 steps:15 total reward:0.72 epsilon:0.024618221284683196
episode:741 steps:9 total reward:0.84 epsilon:0.02449513017825978
episode:742 steps:23 total reward:-1.4400000000000002 epsilon:0.02437265452736848
episode:743 steps:7 total reward:-1.12 epsilon:0.024250791254731636
episode:744 steps:18 total reward:-1.34 epsilon:0.024129537298457977
episode:745 steps:16 total reward:-1.3 epsilon:0.024008889611965685
episode:746 steps:42 total reward:0.1799999999999996 epsilon:0.023888845163905856
episode:747 steps:37 total reward:-1.7200000000000002 epsilon:0.023769400938086327
episode:748 steps:37 total reward:-1.7200000000000002 epsilon:0.023650553933395897
episode:749 steps:12 total reward:-1.22 epsilon:0.023532301163728918
episode:750 steps:10 total reward:-1.18 epsilon:0.023414639657910272
episode:751 steps:6 total reward:-1.1 epsilon:0.023297566459620722
episode:752 steps:28 total reward:0.45999999999999985 epsilon:0.023181078627322618
episode:753 steps:28 total reward:-1.54 epsilon:0.023065173234186005
episode:754 steps:19 total reward:-1.36 epsilon:0.022949847368015076
episode:755 steps:9 total reward:-1.16 epsilon:0.022835098131175
episode:756 steps:21 total reward:-1.4000000000000001 epsilon:0.022720922640519125
episode:757 steps:16 total reward:-1.3 epsilon:0.02260731802731653
episode:758 steps:5 total reward:-1.08 epsilon:0.022494281437179946
episode:759 steps:14 total reward:-1.26 epsilon:0.022381810029994047
episode:760 steps:17 total reward:0.6799999999999999 epsilon:0.022269900979844076
episode:761 steps:8 total reward:-1.1400000000000001 epsilon:0.022158551474944856
episode:762 steps:15 total reward:-1.28 epsilon:0.022047758717570132
episode:763 steps:17 total reward:0.6799999999999999 epsilon:0.021937519923982282
episode:764 steps:26 total reward:-1.5 epsilon:0.021827832324362372
episode:765 steps:33 total reward:-1.6400000000000001 epsilon:0.02171869316274056
episode:766 steps:9 total reward:-1.16 epsilon:0.021610099696926857
episode:767 steps:21 total reward:-1.4000000000000001 epsilon:0.021502049198442223
episode:768 steps:5 total reward:-1.08 epsilon:0.021394538952450012
episode:769 steps:33 total reward:0.35999999999999976 epsilon:0.02128756625768776
episode:770 steps:51 total reward:-2.0000000000000004 epsilon:0.021181128426399323
episode:771 steps:8 total reward:-1.1400000000000001 epsilon:0.021075222784267326
episode:772 steps:21 total reward:-1.4000000000000001 epsilon:0.020969846670345987
episode:773 steps:19 total reward:-1.36 epsilon:0.020864997436994256
episode:774 steps:33 total reward:-1.6400000000000001 epsilon:0.020760672449809284
episode:775 steps:22 total reward:-1.4200000000000002 epsilon:0.020656869087560238
episode:776 steps:3 total reward:-1.04 epsilon:0.020553584742122436
episode:777 steps:50 total reward:-1.9800000000000004 epsilon:0.020450816818411825
episode:778 steps:6 total reward:-1.1 epsilon:0.020348562734319765
episode:779 steps:27 total reward:0.47999999999999987 epsilon:0.020246819920648168
episode:780 steps:12 total reward:-1.22 epsilon:0.020145585821044927
episode:781 steps:12 total reward:0.78 epsilon:0.020044857891939702
episode:782 steps:12 total reward:-1.22 epsilon:0.019944633602480003
episode:783 steps:19 total reward:0.6399999999999999 epsilon:0.019844910434467605
episode:784 steps:26 total reward:-1.5 epsilon:0.019745685882295267
episode:785 steps:11 total reward:-1.2 epsilon:0.01964695745288379
episode:786 steps:22 total reward:-1.4200000000000002 epsilon:0.01954872266561937
episode:787 steps:14 total reward:-1.26 epsilon:0.019450979052291272
episode:788 steps:24 total reward:0.5399999999999998 epsilon:0.019353724157029815
episode:789 steps:36 total reward:-1.7000000000000002 epsilon:0.019256955536244666
episode:790 steps:25 total reward:-1.4800000000000002 epsilon:0.019160670758563442
episode:791 steps:17 total reward:0.6799999999999999 epsilon:0.019064867404770626
episode:792 steps:5 total reward:-1.08 epsilon:0.018969543067746772
episode:793 steps:10 total reward:-1.18 epsilon:0.018874695352408037
episode:794 steps:12 total reward:-1.22 epsilon:0.018780321875645996
episode:795 steps:12 total reward:0.78 epsilon:0.018686420266267767
episode:796 steps:22 total reward:-1.4200000000000002 epsilon:0.018592988164936427
episode:797 steps:9 total reward:0.84 epsilon:0.018500023224111744
episode:798 steps:31 total reward:0.3999999999999998 epsilon:0.018407523107991184
episode:799 steps:16 total reward:-1.3 epsilon:0.01831548549245123
episode:800 steps:7 total reward:-1.12 epsilon:0.018223908064988973
episode:801 steps:29 total reward:-1.56 epsilon:0.018132788524664028
episode:802 steps:10 total reward:-1.18 epsilon:0.018042124582040707
episode:803 steps:35 total reward:-1.6800000000000002 epsilon:0.017951913959130504
episode:804 steps:45 total reward:0.11999999999999955 epsilon:0.01786215438933485
episode:805 steps:22 total reward:-1.4200000000000002 epsilon:0.017772843617388175
episode:806 steps:46 total reward:0.09999999999999953 epsilon:0.017683979399301233
episode:807 steps:6 total reward:-1.1 epsilon:0.017595559502304726
episode:808 steps:62 total reward:-2.2200000000000006 epsilon:0.0175075817047932
episode:809 steps:7 total reward:-1.12 epsilon:0.017420043796269234
episode:810 steps:16 total reward:-1.3 epsilon:0.017332943577287888
episode:811 steps:12 total reward:-1.22 epsilon:0.01724627885940145
episode:812 steps:22 total reward:-1.4200000000000002 epsilon:0.017160047465104442
episode:813 steps:29 total reward:0.43999999999999984 epsilon:0.01707424722777892
episode:814 steps:7 total reward:-1.12 epsilon:0.016988875991640028
episode:815 steps:29 total reward:0.43999999999999984 epsilon:0.016903931611681827
episode:816 steps:8 total reward:-1.1400000000000001 epsilon:0.01681941195362342
episode:817 steps:34 total reward:0.33999999999999975 epsilon:0.016735314893855303
episode:818 steps:12 total reward:0.78 epsilon:0.016651638319386028
episode:819 steps:25 total reward:0.5199999999999998 epsilon:0.0165683801277891
episode:820 steps:20 total reward:-1.3800000000000001 epsilon:0.016485538227150154
episode:821 steps:9 total reward:0.84 epsilon:0.0164031105360144
episode:822 steps:34 total reward:-1.6600000000000001 epsilon:0.01632109498333433
episode:823 steps:42 total reward:-1.8200000000000003 epsilon:0.016239489508417658
episode:824 steps:6 total reward:-1.1 epsilon:0.01615829206087557
episode:825 steps:6 total reward:-1.1 epsilon:0.01607750060057119
episode:826 steps:37 total reward:-1.7200000000000002 epsilon:0.015997113097568336
episode:827 steps:17 total reward:0.6799999999999999 epsilon:0.015917127532080494
episode:828 steps:9 total reward:0.84 epsilon:0.01583754189442009
episode:829 steps:25 total reward:-1.4800000000000002 epsilon:0.01575835418494799
episode:830 steps:19 total reward:-1.36 epsilon:0.01567956241402325
episode:831 steps:6 total reward:-1.1 epsilon:0.015601164601953134
episode:832 steps:13 total reward:-1.24 epsilon:0.015523158778943369
episode:833 steps:14 total reward:0.74 epsilon:0.015445542985048652
episode:834 steps:7 total reward:-1.12 epsilon:0.015368315270123408
episode:835 steps:6 total reward:-1.1 epsilon:0.01529147369377279
episode:836 steps:14 total reward:0.74 epsilon:0.015215016325303928
episode:837 steps:13 total reward:0.76 epsilon:0.015138941243677408
episode:838 steps:76 total reward:-0.5000000000000009 epsilon:0.01506324653745902
episode:839 steps:26 total reward:-1.5 epsilon:0.014987930304771725
episode:840 steps:40 total reward:-1.7800000000000002 epsilon:0.014912990653247866
episode:841 steps:43 total reward:-1.8400000000000003 epsilon:0.014838425699981627
episode:842 steps:12 total reward:0.78 epsilon:0.01476423357148172
episode:843 steps:33 total reward:-1.6400000000000001 epsilon:0.014690412403624311
episode:844 steps:14 total reward:-1.26 epsilon:0.01461696034160619
episode:845 steps:9 total reward:-1.16 epsilon:0.014543875539898159
episode:846 steps:15 total reward:-1.28 epsilon:0.014471156162198668
episode:847 steps:23 total reward:0.5599999999999998 epsilon:0.014398800381387675
episode:848 steps:10 total reward:-1.18 epsilon:0.014326806379480736
episode:849 steps:55 total reward:-2.0800000000000005 epsilon:0.014255172347583332
episode:850 steps:41 total reward:0.19999999999999962 epsilon:0.014183896485845416
episode:851 steps:26 total reward:-1.5 epsilon:0.014112977003416188
episode:852 steps:14 total reward:-1.26 epsilon:0.014042412118399107
episode:853 steps:66 total reward:-2.3000000000000007 epsilon:0.013972200057807112
episode:854 steps:17 total reward:-1.32 epsilon:0.013902339057518077
episode:855 steps:46 total reward:-1.9000000000000004 epsilon:0.013832827362230486
episode:856 steps:5 total reward:-1.08 epsilon:0.013763663225419333
episode:857 steps:61 total reward:-2.2000000000000006 epsilon:0.013694844909292236
episode:858 steps:16 total reward:0.7 epsilon:0.013626370684745774
episode:859 steps:23 total reward:-1.4400000000000002 epsilon:0.013558238831322046
episode:860 steps:11 total reward:-1.2 epsilon:0.013490447637165436
episode:861 steps:60 total reward:-2.1800000000000006 epsilon:0.013422995398979608
episode:862 steps:17 total reward:-1.32 epsilon:0.01335588042198471
episode:863 steps:18 total reward:-1.34 epsilon:0.013289101019874787
episode:864 steps:15 total reward:0.72 epsilon:0.013222655514775413
episode:865 steps:18 total reward:-1.34 epsilon:0.013156542237201536
episode:866 steps:2 total reward:-1.02 epsilon:0.013090759526015528
episode:867 steps:15 total reward:-1.28 epsilon:0.01302530572838545
episode:868 steps:23 total reward:0.5599999999999998 epsilon:0.012960179199743523
episode:869 steps:14 total reward:-1.26 epsilon:0.012895378303744804
episode:870 steps:44 total reward:-1.8600000000000003 epsilon:0.01283090141222608
episode:871 steps:11 total reward:-1.2 epsilon:0.012766746905164949
episode:872 steps:54 total reward:-2.0600000000000005 epsilon:0.012702913170639124
episode:873 steps:43 total reward:-1.8400000000000003 epsilon:0.012639398604785928
episode:874 steps:19 total reward:-1.36 epsilon:0.012576201611761997
episode:875 steps:37 total reward:-1.7200000000000002 epsilon:0.012513320603703188
episode:876 steps:37 total reward:-1.7200000000000002 epsilon:0.012450754000684672
episode:877 steps:17 total reward:-1.32 epsilon:0.012388500230681249
episode:878 steps:26 total reward:0.4999999999999999 epsilon:0.012326557729527843
episode:879 steps:11 total reward:-1.2 epsilon:0.012264924940880204
episode:880 steps:13 total reward:0.76 epsilon:0.012203600316175803
episode:881 steps:5 total reward:-1.08 epsilon:0.012142582314594924
episode:882 steps:3 total reward:-1.04 epsilon:0.01208186940302195
episode:883 steps:46 total reward:-1.9000000000000004 epsilon:0.01202146005600684
episode:884 steps:48 total reward:0.0599999999999995 epsilon:0.011961352755726806
episode:885 steps:49 total reward:-1.9600000000000004 epsilon:0.01190154599194817
episode:886 steps:29 total reward:0.43999999999999984 epsilon:0.01184203826198843
episode:887 steps:24 total reward:0.5399999999999998 epsilon:0.011782828070678488
episode:888 steps:13 total reward:0.76 epsilon:0.011723913930325095
episode:889 steps:19 total reward:-1.36 epsilon:0.01166529436067347
episode:890 steps:26 total reward:0.4999999999999999 epsilon:0.011606967888870102
episode:891 steps:21 total reward:-1.4000000000000001 epsilon:0.01154893304942575
episode:892 steps:13 total reward:-1.24 epsilon:0.011491188384178622
episode:893 steps:100 total reward:-2.9800000000000013 epsilon:0.011433732442257729
episode:894 steps:19 total reward:0.6399999999999999 epsilon:0.01137656378004644
episode:895 steps:23 total reward:0.5599999999999998 epsilon:0.011319680961146208
episode:896 steps:19 total reward:-1.36 epsilon:0.011263082556340478
episode:897 steps:32 total reward:0.3799999999999998 epsilon:0.011206767143558775
episode:898 steps:9 total reward:0.84 epsilon:0.011150733307840981
episode:899 steps:36 total reward:0.2999999999999997 epsilon:0.011094979641301777
episode:900 steps:33 total reward:0.35999999999999976 epsilon:0.011039504743095268
episode:901 steps:30 total reward:0.4199999999999998 epsilon:0.01098430721937979
episode:902 steps:9 total reward:-1.16 epsilon:0.010929385683282892
episode:903 steps:9 total reward:-1.16 epsilon:0.010874738754866477
episode:904 steps:35 total reward:0.31999999999999973 epsilon:0.010820365061092144
episode:905 steps:12 total reward:0.78 epsilon:0.010766263235786683
episode:906 steps:19 total reward:0.6399999999999999 epsilon:0.01071243191960775
episode:907 steps:72 total reward:-0.4200000000000008 epsilon:0.010658869760009713
episode:908 steps:8 total reward:-1.1400000000000001 epsilon:0.010605575411209664
episode:909 steps:22 total reward:0.5799999999999998 epsilon:0.010552547534153616
episode:910 steps:23 total reward:0.5599999999999998 epsilon:0.010499784796482848
episode:911 steps:13 total reward:-1.24 epsilon:0.010447285872500434
episode:912 steps:40 total reward:0.21999999999999964 epsilon:0.01039504944313793
episode:913 steps:21 total reward:-1.4000000000000001 epsilon:0.010343074195922241
episode:914 steps:58 total reward:-2.1400000000000006 epsilon:0.01029135882494263
episode:915 steps:10 total reward:0.8200000000000001 epsilon:0.010239902030817916
episode:916 steps:24 total reward:0.5399999999999998 epsilon:0.010188702520663827
episode:917 steps:10 total reward:0.8200000000000001 epsilon:0.010137759008060509
episode:918 steps:67 total reward:-0.32000000000000073 epsilon:0.010087070213020206
episode:919 steps:12 total reward:-1.22 epsilon:0.010036634861955105
episode:920 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:921 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:922 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:923 steps:34 total reward:-1.6600000000000001 epsilon:0.00998645168764533
episode:924 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:925 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:926 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:927 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:928 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:929 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:930 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:931 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:932 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:933 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:934 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:935 steps:78 total reward:-2.540000000000001 epsilon:0.00998645168764533
episode:936 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:937 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:938 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:939 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:940 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:941 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:942 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:943 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:944 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:945 steps:57 total reward:-2.1200000000000006 epsilon:0.00998645168764533
episode:946 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:947 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:948 steps:82 total reward:-0.620000000000001 epsilon:0.00998645168764533
episode:949 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:950 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:951 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:952 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:953 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:954 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:955 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:956 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:957 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:958 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:959 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:960 steps:65 total reward:-0.2800000000000007 epsilon:0.00998645168764533
episode:961 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:962 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:963 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:964 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:965 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:966 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:967 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:968 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:969 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:970 steps:34 total reward:-1.6600000000000001 epsilon:0.00998645168764533
episode:971 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:972 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:973 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:974 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:975 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:976 steps:57 total reward:-2.1200000000000006 epsilon:0.00998645168764533
episode:977 steps:6 total reward:0.9 epsilon:0.00998645168764533
episode:978 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:979 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:980 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:981 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:982 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:983 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:984 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:985 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:986 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:987 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:988 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:989 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:990 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:991 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:992 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:993 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:994 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:995 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:996 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:997 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:998 steps:93 total reward:-0.8400000000000012 epsilon:0.00998645168764533
[2017-07-16 15:02:30,121] Starting new video recorder writing to C:\Users\Abdul\Documents\My Projects\Deep learning nano degree\my-experiments\reinforcement learning\monitor\openaigym.video.2.12772.video001000.json
episode:999 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:1000 steps:47 total reward:-1.9200000000000004 epsilon:0.00998645168764533
episode:1001 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:1002 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:1003 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:1004 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:1005 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:1006 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:1007 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:1008 steps:49 total reward:-1.9600000000000004 epsilon:0.00998645168764533
episode:1009 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:1010 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:1011 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:1012 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:1013 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1014 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1015 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:1016 steps:54 total reward:-2.0600000000000005 epsilon:0.00998645168764533
episode:1017 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:1018 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:1019 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:1020 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:1021 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:1022 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:1023 steps:74 total reward:-2.460000000000001 epsilon:0.00998645168764533
episode:1024 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:1025 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:1026 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:1027 steps:4 total reward:-1.06 epsilon:0.00998645168764533
episode:1028 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1029 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:1030 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:1031 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:1032 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:1033 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:1034 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1035 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:1036 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:1037 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:1038 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:1039 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:1040 steps:60 total reward:-2.1800000000000006 epsilon:0.00998645168764533
episode:1041 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:1042 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:1043 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:1044 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:1045 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:1046 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:1047 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:1048 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:1049 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:1050 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:1051 steps:86 total reward:-0.7000000000000011 epsilon:0.00998645168764533
episode:1052 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:1053 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:1054 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:1055 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1056 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:1057 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:1058 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1059 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:1060 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1061 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:1062 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:1063 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:1064 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:1065 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1066 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1067 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:1068 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:1069 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1070 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1071 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1072 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:1073 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:1074 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:1075 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:1076 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1077 steps:57 total reward:-2.1200000000000006 epsilon:0.00998645168764533
episode:1078 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:1079 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:1080 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:1081 steps:43 total reward:-1.8400000000000003 epsilon:0.00998645168764533
episode:1082 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:1083 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:1084 steps:54 total reward:-2.0600000000000005 epsilon:0.00998645168764533
episode:1085 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:1086 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:1087 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1088 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:1089 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:1090 steps:62 total reward:-2.2200000000000006 epsilon:0.00998645168764533
episode:1091 steps:61 total reward:-2.2000000000000006 epsilon:0.00998645168764533
episode:1092 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:1093 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:1094 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:1095 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:1096 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:1097 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:1098 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:1099 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:1100 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:1101 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:1102 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:1103 steps:69 total reward:-0.36000000000000076 epsilon:0.00998645168764533
episode:1104 steps:75 total reward:-0.48000000000000087 epsilon:0.00998645168764533
episode:1105 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:1106 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:1107 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:1108 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:1109 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:1110 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:1111 steps:60 total reward:-0.1800000000000006 epsilon:0.00998645168764533
episode:1112 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:1113 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:1114 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:1115 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:1116 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1117 steps:70 total reward:-0.3800000000000008 epsilon:0.00998645168764533
episode:1118 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:1119 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:1120 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:1121 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:1122 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1123 steps:72 total reward:-2.420000000000001 epsilon:0.00998645168764533
episode:1124 steps:88 total reward:-2.740000000000001 epsilon:0.00998645168764533
episode:1125 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1126 steps:53 total reward:-0.04000000000000048 epsilon:0.00998645168764533
episode:1127 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:1128 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:1129 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:1130 steps:49 total reward:-1.9600000000000004 epsilon:0.00998645168764533
episode:1131 steps:84 total reward:-2.660000000000001 epsilon:0.00998645168764533
episode:1132 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:1133 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:1134 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1135 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:1136 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1137 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1138 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:1139 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:1140 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:1141 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:1142 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:1143 steps:64 total reward:-2.2600000000000007 epsilon:0.00998645168764533
episode:1144 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:1145 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:1146 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:1147 steps:56 total reward:-2.1000000000000005 epsilon:0.00998645168764533
episode:1148 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:1149 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:1150 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:1151 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:1152 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:1153 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:1154 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:1155 steps:66 total reward:-2.3000000000000007 epsilon:0.00998645168764533
episode:1156 steps:53 total reward:-0.04000000000000048 epsilon:0.00998645168764533
episode:1157 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:1158 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1159 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:1160 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1161 steps:35 total reward:-1.6800000000000002 epsilon:0.00998645168764533
episode:1162 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:1163 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1164 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:1165 steps:85 total reward:-2.680000000000001 epsilon:0.00998645168764533
episode:1166 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:1167 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1168 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:1169 steps:32 total reward:-1.62 epsilon:0.00998645168764533
episode:1170 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:1171 steps:64 total reward:-2.2600000000000007 epsilon:0.00998645168764533
episode:1172 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:1173 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:1174 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:1175 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:1176 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1177 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:1178 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1179 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1180 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:1181 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:1182 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:1183 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:1184 steps:47 total reward:-1.9200000000000004 epsilon:0.00998645168764533
episode:1185 steps:38 total reward:-1.7400000000000002 epsilon:0.00998645168764533
episode:1186 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:1187 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:1188 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:1189 steps:94 total reward:-0.8600000000000012 epsilon:0.00998645168764533
episode:1190 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:1191 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:1192 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:1193 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:1194 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:1195 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1196 steps:49 total reward:-1.9600000000000004 epsilon:0.00998645168764533
episode:1197 steps:48 total reward:-1.9400000000000004 epsilon:0.00998645168764533
episode:1198 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:1199 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:1200 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:1201 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:1202 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:1203 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:1204 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:1205 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:1206 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:1207 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:1208 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:1209 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:1210 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1211 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:1212 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:1213 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:1214 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:1215 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:1216 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:1217 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1218 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:1219 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:1220 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:1221 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:1222 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:1223 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1224 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:1225 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:1226 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1227 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:1228 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:1229 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:1230 steps:64 total reward:-2.2600000000000007 epsilon:0.00998645168764533
episode:1231 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:1232 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:1233 steps:89 total reward:-0.7600000000000011 epsilon:0.00998645168764533
episode:1234 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:1235 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:1236 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:1237 steps:34 total reward:-1.6600000000000001 epsilon:0.00998645168764533
episode:1238 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:1239 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:1240 steps:44 total reward:-1.8600000000000003 epsilon:0.00998645168764533
episode:1241 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:1242 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:1243 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1244 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:1245 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:1246 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:1247 steps:60 total reward:-0.1800000000000006 epsilon:0.00998645168764533
episode:1248 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:1249 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:1250 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1251 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:1252 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:1253 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:1254 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:1255 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:1256 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1257 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:1258 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:1259 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1260 steps:93 total reward:-2.840000000000001 epsilon:0.00998645168764533
episode:1261 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1262 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:1263 steps:32 total reward:-1.62 epsilon:0.00998645168764533
episode:1264 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:1265 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:1266 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:1267 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:1268 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:1269 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:1270 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1271 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:1272 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:1273 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:1274 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:1275 steps:67 total reward:-2.3200000000000007 epsilon:0.00998645168764533
episode:1276 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:1277 steps:70 total reward:-2.380000000000001 epsilon:0.00998645168764533
episode:1278 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:1279 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1280 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:1281 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:1282 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:1283 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:1284 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:1285 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:1286 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:1287 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:1288 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:1289 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:1290 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:1291 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1292 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:1293 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:1294 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:1295 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1296 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:1297 steps:57 total reward:-2.1200000000000006 epsilon:0.00998645168764533
episode:1298 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:1299 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:1300 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:1301 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:1302 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:1303 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:1304 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:1305 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:1306 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:1307 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1308 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:1309 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1310 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:1311 steps:94 total reward:-2.860000000000001 epsilon:0.00998645168764533
episode:1312 steps:84 total reward:-2.660000000000001 epsilon:0.00998645168764533
episode:1313 steps:45 total reward:-1.8800000000000003 epsilon:0.00998645168764533
episode:1314 steps:60 total reward:-2.1800000000000006 epsilon:0.00998645168764533
episode:1315 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1316 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1317 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1318 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:1319 steps:70 total reward:-2.380000000000001 epsilon:0.00998645168764533
episode:1320 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:1321 steps:47 total reward:-1.9200000000000004 epsilon:0.00998645168764533
episode:1322 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:1323 steps:46 total reward:-1.9000000000000004 epsilon:0.00998645168764533
episode:1324 steps:57 total reward:-2.1200000000000006 epsilon:0.00998645168764533
episode:1325 steps:68 total reward:-2.3400000000000007 epsilon:0.00998645168764533
episode:1326 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:1327 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:1328 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:1329 steps:98 total reward:-2.9400000000000013 epsilon:0.00998645168764533
episode:1330 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:1331 steps:49 total reward:-1.9600000000000004 epsilon:0.00998645168764533
episode:1332 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1333 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:1334 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:1335 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1336 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:1337 steps:53 total reward:-0.04000000000000048 epsilon:0.00998645168764533
episode:1338 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1339 steps:82 total reward:-0.620000000000001 epsilon:0.00998645168764533
episode:1340 steps:62 total reward:-2.2200000000000006 epsilon:0.00998645168764533
episode:1341 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:1342 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:1343 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:1344 steps:62 total reward:-0.22000000000000064 epsilon:0.00998645168764533
episode:1345 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:1346 steps:54 total reward:-2.0600000000000005 epsilon:0.00998645168764533
episode:1347 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:1348 steps:4 total reward:-1.06 epsilon:0.00998645168764533
episode:1349 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:1350 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:1351 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1352 steps:79 total reward:-0.5600000000000009 epsilon:0.00998645168764533
episode:1353 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1354 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:1355 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1356 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:1357 steps:40 total reward:-1.7800000000000002 epsilon:0.00998645168764533
episode:1358 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:1359 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1360 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1361 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1362 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:1363 steps:53 total reward:-0.04000000000000048 epsilon:0.00998645168764533
episode:1364 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:1365 steps:48 total reward:-1.9400000000000004 epsilon:0.00998645168764533
episode:1366 steps:47 total reward:-1.9200000000000004 epsilon:0.00998645168764533
episode:1367 steps:65 total reward:-2.2800000000000007 epsilon:0.00998645168764533
episode:1368 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:1369 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:1370 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1371 steps:95 total reward:-2.8800000000000012 epsilon:0.00998645168764533
episode:1372 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:1373 steps:45 total reward:-1.8800000000000003 epsilon:0.00998645168764533
episode:1374 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:1375 steps:47 total reward:-1.9200000000000004 epsilon:0.00998645168764533
episode:1376 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:1377 steps:34 total reward:-1.6600000000000001 epsilon:0.00998645168764533
episode:1378 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:1379 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:1380 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:1381 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:1382 steps:45 total reward:-1.8800000000000003 epsilon:0.00998645168764533
episode:1383 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:1384 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:1385 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:1386 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1387 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:1388 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:1389 steps:65 total reward:-0.2800000000000007 epsilon:0.00998645168764533
episode:1390 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:1391 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:1392 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:1393 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:1394 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:1395 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:1396 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:1397 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1398 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:1399 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:1400 steps:95 total reward:-2.8800000000000012 epsilon:0.00998645168764533
episode:1401 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:1402 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:1403 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1404 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:1405 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:1406 steps:45 total reward:-1.8800000000000003 epsilon:0.00998645168764533
episode:1407 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:1408 steps:35 total reward:-1.6800000000000002 epsilon:0.00998645168764533
episode:1409 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:1410 steps:35 total reward:-1.6800000000000002 epsilon:0.00998645168764533
episode:1411 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:1412 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:1413 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:1414 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:1415 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:1416 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:1417 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:1418 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:1419 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:1420 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:1421 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:1422 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1423 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1424 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:1425 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:1426 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:1427 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:1428 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:1429 steps:82 total reward:-2.620000000000001 epsilon:0.00998645168764533
episode:1430 steps:61 total reward:-2.2000000000000006 epsilon:0.00998645168764533
episode:1431 steps:75 total reward:-2.480000000000001 epsilon:0.00998645168764533
episode:1432 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1433 steps:47 total reward:-1.9200000000000004 epsilon:0.00998645168764533
episode:1434 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:1435 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:1436 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:1437 steps:50 total reward:-1.9800000000000004 epsilon:0.00998645168764533
episode:1438 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:1439 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:1440 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:1441 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:1442 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:1443 steps:78 total reward:-2.540000000000001 epsilon:0.00998645168764533
episode:1444 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:1445 steps:83 total reward:-2.640000000000001 epsilon:0.00998645168764533
episode:1446 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:1447 steps:53 total reward:-2.0400000000000005 epsilon:0.00998645168764533
episode:1448 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:1449 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1450 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1451 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:1452 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:1453 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:1454 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:1455 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:1456 steps:62 total reward:-0.22000000000000064 epsilon:0.00998645168764533
episode:1457 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:1458 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1459 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:1460 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:1461 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:1462 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:1463 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:1464 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:1465 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1466 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:1467 steps:68 total reward:-2.3400000000000007 epsilon:0.00998645168764533
episode:1468 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1469 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:1470 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:1471 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:1472 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:1473 steps:70 total reward:-0.3800000000000008 epsilon:0.00998645168764533
episode:1474 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1475 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:1476 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:1477 steps:96 total reward:-0.9000000000000012 epsilon:0.00998645168764533
episode:1478 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:1479 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1480 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:1481 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:1482 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:1483 steps:79 total reward:-2.560000000000001 epsilon:0.00998645168764533
episode:1484 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:1485 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:1486 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:1487 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1488 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:1489 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1490 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:1491 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:1492 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1493 steps:60 total reward:-0.1800000000000006 epsilon:0.00998645168764533
episode:1494 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:1495 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:1496 steps:79 total reward:-0.5600000000000009 epsilon:0.00998645168764533
episode:1497 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:1498 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:1499 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:1500 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:1501 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:1502 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:1503 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:1504 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1505 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:1506 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:1507 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:1508 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:1509 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:1510 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:1511 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:1512 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:1513 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:1514 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:1515 steps:34 total reward:-1.6600000000000001 epsilon:0.00998645168764533
episode:1516 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:1517 steps:76 total reward:-0.5000000000000009 epsilon:0.00998645168764533
episode:1518 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:1519 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:1520 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:1521 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:1522 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:1523 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:1524 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1525 steps:55 total reward:-2.0800000000000005 epsilon:0.00998645168764533
episode:1526 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1527 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1528 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:1529 steps:46 total reward:-1.9000000000000004 epsilon:0.00998645168764533
episode:1530 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:1531 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1532 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1533 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1534 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:1535 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:1536 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1537 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:1538 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:1539 steps:2 total reward:-1.02 epsilon:0.00998645168764533
episode:1540 steps:68 total reward:-2.3400000000000007 epsilon:0.00998645168764533
episode:1541 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1542 steps:56 total reward:-2.1000000000000005 epsilon:0.00998645168764533
episode:1543 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:1544 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:1545 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:1546 steps:60 total reward:-2.1800000000000006 epsilon:0.00998645168764533
episode:1547 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:1548 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:1549 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1550 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1551 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:1552 steps:89 total reward:-0.7600000000000011 epsilon:0.00998645168764533
episode:1553 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:1554 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1555 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:1556 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:1557 steps:49 total reward:-1.9600000000000004 epsilon:0.00998645168764533
episode:1558 steps:38 total reward:-1.7400000000000002 epsilon:0.00998645168764533
episode:1559 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:1560 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:1561 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:1562 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:1563 steps:55 total reward:-2.0800000000000005 epsilon:0.00998645168764533
episode:1564 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:1565 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:1566 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:1567 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:1568 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:1569 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1570 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:1571 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:1572 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:1573 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:1574 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:1575 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:1576 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1577 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:1578 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1579 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:1580 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:1581 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1582 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:1583 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:1584 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:1585 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:1586 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:1587 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:1588 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:1589 steps:39 total reward:-1.7600000000000002 epsilon:0.00998645168764533
episode:1590 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:1591 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:1592 steps:62 total reward:-0.22000000000000064 epsilon:0.00998645168764533
episode:1593 steps:81 total reward:-0.600000000000001 epsilon:0.00998645168764533
episode:1594 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:1595 steps:51 total reward:-2.0000000000000004 epsilon:0.00998645168764533
episode:1596 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:1597 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:1598 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1599 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:1600 steps:79 total reward:-0.5600000000000009 epsilon:0.00998645168764533
episode:1601 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:1602 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1603 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:1604 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:1605 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1606 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:1607 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:1608 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:1609 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:1610 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:1611 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:1612 steps:88 total reward:-0.7400000000000011 epsilon:0.00998645168764533
episode:1613 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:1614 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1615 steps:51 total reward:-2.0000000000000004 epsilon:0.00998645168764533
episode:1616 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:1617 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:1618 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:1619 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:1620 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:1621 steps:76 total reward:-0.5000000000000009 epsilon:0.00998645168764533
episode:1622 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:1623 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1624 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1625 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1626 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:1627 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:1628 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:1629 steps:78 total reward:-0.5400000000000009 epsilon:0.00998645168764533
episode:1630 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:1631 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1632 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:1633 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:1634 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:1635 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1636 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:1637 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1638 steps:84 total reward:-0.660000000000001 epsilon:0.00998645168764533
episode:1639 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:1640 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:1641 steps:91 total reward:-2.800000000000001 epsilon:0.00998645168764533
episode:1642 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:1643 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:1644 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:1645 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:1646 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:1647 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:1648 steps:91 total reward:-0.8000000000000012 epsilon:0.00998645168764533
episode:1649 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:1650 steps:80 total reward:-2.580000000000001 epsilon:0.00998645168764533
episode:1651 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1652 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:1653 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:1654 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:1655 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1656 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:1657 steps:80 total reward:-0.580000000000001 epsilon:0.00998645168764533
episode:1658 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1659 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:1660 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1661 steps:56 total reward:-2.1000000000000005 epsilon:0.00998645168764533
episode:1662 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:1663 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:1664 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:1665 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:1666 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:1667 steps:47 total reward:-1.9200000000000004 epsilon:0.00998645168764533
episode:1668 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1669 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:1670 steps:93 total reward:-2.840000000000001 epsilon:0.00998645168764533
episode:1671 steps:97 total reward:-0.9200000000000013 epsilon:0.00998645168764533
episode:1672 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:1673 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:1674 steps:64 total reward:-2.2600000000000007 epsilon:0.00998645168764533
episode:1675 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:1676 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:1677 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:1678 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:1679 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:1680 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:1681 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1682 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:1683 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:1684 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1685 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:1686 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1687 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:1688 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:1689 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1690 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:1691 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:1692 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:1693 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:1694 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1695 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:1696 steps:62 total reward:-0.22000000000000064 epsilon:0.00998645168764533
episode:1697 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:1698 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1699 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:1700 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:1701 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:1702 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:1703 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:1704 steps:65 total reward:-0.2800000000000007 epsilon:0.00998645168764533
episode:1705 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:1706 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:1707 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1708 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:1709 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:1710 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:1711 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:1712 steps:93 total reward:-0.8400000000000012 epsilon:0.00998645168764533
episode:1713 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:1714 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1715 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:1716 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:1717 steps:70 total reward:-0.3800000000000008 epsilon:0.00998645168764533
episode:1718 steps:70 total reward:-0.3800000000000008 epsilon:0.00998645168764533
episode:1719 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:1720 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1721 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1722 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1723 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:1724 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1725 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:1726 steps:82 total reward:-0.620000000000001 epsilon:0.00998645168764533
episode:1727 steps:81 total reward:-0.600000000000001 epsilon:0.00998645168764533
episode:1728 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:1729 steps:86 total reward:-2.700000000000001 epsilon:0.00998645168764533
episode:1730 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:1731 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:1732 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:1733 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:1734 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:1735 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1736 steps:38 total reward:-1.7400000000000002 epsilon:0.00998645168764533
episode:1737 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1738 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:1739 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:1740 steps:68 total reward:-2.3400000000000007 epsilon:0.00998645168764533
episode:1741 steps:65 total reward:-0.2800000000000007 epsilon:0.00998645168764533
episode:1742 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:1743 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:1744 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:1745 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:1746 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:1747 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:1748 steps:89 total reward:-0.7600000000000011 epsilon:0.00998645168764533
episode:1749 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:1750 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:1751 steps:34 total reward:-1.6600000000000001 epsilon:0.00998645168764533
episode:1752 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:1753 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:1754 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1755 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:1756 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:1757 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:1758 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1759 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:1760 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:1761 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:1762 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:1763 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:1764 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:1765 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1766 steps:4 total reward:-1.06 epsilon:0.00998645168764533
episode:1767 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:1768 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:1769 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:1770 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:1771 steps:46 total reward:-1.9000000000000004 epsilon:0.00998645168764533
episode:1772 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:1773 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:1774 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:1775 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:1776 steps:78 total reward:-0.5400000000000009 epsilon:0.00998645168764533
episode:1777 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:1778 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:1779 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:1780 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1781 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1782 steps:95 total reward:-2.8800000000000012 epsilon:0.00998645168764533
episode:1783 steps:66 total reward:-2.3000000000000007 epsilon:0.00998645168764533
episode:1784 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:1785 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:1786 steps:91 total reward:-2.800000000000001 epsilon:0.00998645168764533
episode:1787 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:1788 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:1789 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1790 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1791 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:1792 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1793 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:1794 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1795 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:1796 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1797 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:1798 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1799 steps:89 total reward:-0.7600000000000011 epsilon:0.00998645168764533
episode:1800 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1801 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1802 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:1803 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1804 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:1805 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:1806 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:1807 steps:49 total reward:-1.9600000000000004 epsilon:0.00998645168764533
episode:1808 steps:40 total reward:-1.7800000000000002 epsilon:0.00998645168764533
episode:1809 steps:92 total reward:-0.8200000000000012 epsilon:0.00998645168764533
episode:1810 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:1811 steps:75 total reward:-0.48000000000000087 epsilon:0.00998645168764533
episode:1812 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1813 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:1814 steps:88 total reward:-0.7400000000000011 epsilon:0.00998645168764533
episode:1815 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1816 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:1817 steps:92 total reward:-0.8200000000000012 epsilon:0.00998645168764533
episode:1818 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1819 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:1820 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1821 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:1822 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:1823 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:1824 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:1825 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:1826 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:1827 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1828 steps:95 total reward:-0.8800000000000012 epsilon:0.00998645168764533
episode:1829 steps:70 total reward:-2.380000000000001 epsilon:0.00998645168764533
episode:1830 steps:70 total reward:-0.3800000000000008 epsilon:0.00998645168764533
episode:1831 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1832 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:1833 steps:69 total reward:-0.36000000000000076 epsilon:0.00998645168764533
episode:1834 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:1835 steps:96 total reward:-2.9000000000000012 epsilon:0.00998645168764533
episode:1836 steps:70 total reward:-0.3800000000000008 epsilon:0.00998645168764533
episode:1837 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:1838 steps:35 total reward:-1.6800000000000002 epsilon:0.00998645168764533
episode:1839 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:1840 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:1841 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:1842 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:1843 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1844 steps:60 total reward:-2.1800000000000006 epsilon:0.00998645168764533
episode:1845 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:1846 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:1847 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:1848 steps:59 total reward:-2.1600000000000006 epsilon:0.00998645168764533
episode:1849 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:1850 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1851 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:1852 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1853 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:1854 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:1855 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:1856 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:1857 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:1858 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:1859 steps:53 total reward:-2.0400000000000005 epsilon:0.00998645168764533
episode:1860 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:1861 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:1862 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:1863 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1864 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1865 steps:2 total reward:-1.02 epsilon:0.00998645168764533
episode:1866 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:1867 steps:79 total reward:-0.5600000000000009 epsilon:0.00998645168764533
episode:1868 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:1869 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:1870 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:1871 steps:53 total reward:-0.04000000000000048 epsilon:0.00998645168764533
episode:1872 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:1873 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:1874 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1875 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:1876 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:1877 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:1878 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:1879 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:1880 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:1881 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1882 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:1883 steps:57 total reward:-2.1200000000000006 epsilon:0.00998645168764533
episode:1884 steps:69 total reward:-0.36000000000000076 epsilon:0.00998645168764533
episode:1885 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:1886 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:1887 steps:60 total reward:-0.1800000000000006 epsilon:0.00998645168764533
episode:1888 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:1889 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:1890 steps:70 total reward:-0.3800000000000008 epsilon:0.00998645168764533
episode:1891 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1892 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:1893 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:1894 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:1895 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:1896 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:1897 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1898 steps:63 total reward:-2.2400000000000007 epsilon:0.00998645168764533
episode:1899 steps:60 total reward:-0.1800000000000006 epsilon:0.00998645168764533
episode:1900 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:1901 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1902 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:1903 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:1904 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:1905 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1906 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:1907 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:1908 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:1909 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:1910 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1911 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:1912 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1913 steps:44 total reward:-1.8600000000000003 epsilon:0.00998645168764533
episode:1914 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:1915 steps:32 total reward:-1.62 epsilon:0.00998645168764533
episode:1916 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:1917 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:1918 steps:45 total reward:-1.8800000000000003 epsilon:0.00998645168764533
episode:1919 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:1920 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1921 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1922 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:1923 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:1924 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1925 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:1926 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:1927 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1928 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:1929 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:1930 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:1931 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:1932 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:1933 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:1934 steps:76 total reward:-0.5000000000000009 epsilon:0.00998645168764533
episode:1935 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:1936 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:1937 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:1938 steps:87 total reward:-0.7200000000000011 epsilon:0.00998645168764533
episode:1939 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1940 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:1941 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1942 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:1943 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:1944 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:1945 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:1946 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:1947 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:1948 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:1949 steps:48 total reward:-1.9400000000000004 epsilon:0.00998645168764533
episode:1950 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:1951 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:1952 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1953 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1954 steps:65 total reward:-2.2800000000000007 epsilon:0.00998645168764533
episode:1955 steps:95 total reward:-2.8800000000000012 epsilon:0.00998645168764533
episode:1956 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:1957 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:1958 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:1959 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:1960 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:1961 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:1962 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:1963 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1964 steps:78 total reward:-2.540000000000001 epsilon:0.00998645168764533
episode:1965 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:1966 steps:4 total reward:-1.06 epsilon:0.00998645168764533
episode:1967 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:1968 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:1969 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:1970 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:1971 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:1972 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:1973 steps:40 total reward:-1.7800000000000002 epsilon:0.00998645168764533
episode:1974 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:1975 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:1976 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1977 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:1978 steps:70 total reward:-2.380000000000001 epsilon:0.00998645168764533
episode:1979 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1980 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:1981 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:1982 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1983 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:1984 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:1985 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:1986 steps:54 total reward:-2.0600000000000005 epsilon:0.00998645168764533
episode:1987 steps:66 total reward:-2.3000000000000007 epsilon:0.00998645168764533
episode:1988 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:1989 steps:61 total reward:-2.2000000000000006 epsilon:0.00998645168764533
episode:1990 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:1991 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:1992 steps:77 total reward:-2.520000000000001 epsilon:0.00998645168764533
episode:1993 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:1994 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:1995 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:1996 steps:55 total reward:-2.0800000000000005 epsilon:0.00998645168764533
episode:1997 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:1998 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
[2017-07-16 15:06:31,041] Starting new video recorder writing to C:\Users\Abdul\Documents\My Projects\Deep learning nano degree\my-experiments\reinforcement learning\monitor\openaigym.video.2.12772.video002000.json
episode:1999 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:2000 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:2001 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:2002 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:2003 steps:43 total reward:-1.8400000000000003 epsilon:0.00998645168764533
episode:2004 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:2005 steps:97 total reward:-0.9200000000000013 epsilon:0.00998645168764533
episode:2006 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:2007 steps:81 total reward:-0.600000000000001 epsilon:0.00998645168764533
episode:2008 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2009 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2010 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:2011 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2012 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:2013 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:2014 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2015 steps:70 total reward:-0.3800000000000008 epsilon:0.00998645168764533
episode:2016 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:2017 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:2018 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:2019 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:2020 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2021 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2022 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:2023 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:2024 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:2025 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:2026 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2027 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:2028 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:2029 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:2030 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:2031 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2032 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:2033 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2034 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2035 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:2036 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:2037 steps:2 total reward:-1.02 epsilon:0.00998645168764533
episode:2038 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:2039 steps:96 total reward:-0.9000000000000012 epsilon:0.00998645168764533
episode:2040 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2041 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2042 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2043 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:2044 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:2045 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2046 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:2047 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:2048 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:2049 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:2050 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:2051 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2052 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:2053 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:2054 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:2055 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:2056 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2057 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2058 steps:78 total reward:-0.5400000000000009 epsilon:0.00998645168764533
episode:2059 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:2060 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:2061 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:2062 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2063 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:2064 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:2065 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:2066 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:2067 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:2068 steps:53 total reward:-2.0400000000000005 epsilon:0.00998645168764533
episode:2069 steps:76 total reward:-0.5000000000000009 epsilon:0.00998645168764533
episode:2070 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:2071 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:2072 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:2073 steps:98 total reward:-0.9400000000000013 epsilon:0.00998645168764533
episode:2074 steps:32 total reward:-1.62 epsilon:0.00998645168764533
episode:2075 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:2076 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2077 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:2078 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:2079 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:2080 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2081 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:2082 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2083 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:2084 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:2085 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:2086 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:2087 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2088 steps:74 total reward:-0.46000000000000085 epsilon:0.00998645168764533
episode:2089 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:2090 steps:4 total reward:-1.06 epsilon:0.00998645168764533
episode:2091 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:2092 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:2093 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:2094 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2095 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2096 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2097 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:2098 steps:91 total reward:-0.8000000000000012 epsilon:0.00998645168764533
episode:2099 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:2100 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:2101 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:2102 steps:97 total reward:-0.9200000000000013 epsilon:0.00998645168764533
episode:2103 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:2104 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2105 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2106 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:2107 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:2108 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2109 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2110 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:2111 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:2112 steps:62 total reward:-0.22000000000000064 epsilon:0.00998645168764533
episode:2113 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:2114 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2115 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:2116 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:2117 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:2118 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:2119 steps:81 total reward:-0.600000000000001 epsilon:0.00998645168764533
episode:2120 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:2121 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:2122 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:2123 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2124 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:2125 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2126 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:2127 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:2128 steps:83 total reward:-2.640000000000001 epsilon:0.00998645168764533
episode:2129 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2130 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:2131 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2132 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:2133 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:2134 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:2135 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:2136 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:2137 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:2138 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:2139 steps:64 total reward:-2.2600000000000007 epsilon:0.00998645168764533
episode:2140 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2141 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2142 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:2143 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2144 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:2145 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2146 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2147 steps:4 total reward:-1.06 epsilon:0.00998645168764533
episode:2148 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:2149 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:2150 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:2151 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:2152 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2153 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:2154 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:2155 steps:87 total reward:-0.7200000000000011 epsilon:0.00998645168764533
episode:2156 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2157 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2158 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2159 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2160 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2161 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:2162 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:2163 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:2164 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:2165 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:2166 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:2167 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2168 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:2169 steps:87 total reward:-0.7200000000000011 epsilon:0.00998645168764533
episode:2170 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2171 steps:58 total reward:-2.1400000000000006 epsilon:0.00998645168764533
episode:2172 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2173 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:2174 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:2175 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:2176 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2177 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2178 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2179 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:2180 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2181 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:2182 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:2183 steps:4 total reward:-1.06 epsilon:0.00998645168764533
episode:2184 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:2185 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:2186 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:2187 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:2188 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:2189 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:2190 steps:44 total reward:-1.8600000000000003 epsilon:0.00998645168764533
episode:2191 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:2192 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:2193 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2194 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2195 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2196 steps:63 total reward:-2.2400000000000007 epsilon:0.00998645168764533
episode:2197 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:2198 steps:94 total reward:-2.860000000000001 epsilon:0.00998645168764533
episode:2199 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:2200 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:2201 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:2202 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2203 steps:80 total reward:-0.580000000000001 epsilon:0.00998645168764533
episode:2204 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:2205 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:2206 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:2207 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2208 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2209 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2210 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:2211 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2212 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2213 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:2214 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2215 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2216 steps:75 total reward:-0.48000000000000087 epsilon:0.00998645168764533
episode:2217 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2218 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:2219 steps:74 total reward:-0.46000000000000085 epsilon:0.00998645168764533
episode:2220 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:2221 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2222 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:2223 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:2224 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:2225 steps:81 total reward:-0.600000000000001 epsilon:0.00998645168764533
episode:2226 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:2227 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2228 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:2229 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:2230 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:2231 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:2232 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:2233 steps:53 total reward:-0.04000000000000048 epsilon:0.00998645168764533
episode:2234 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:2235 steps:62 total reward:-0.22000000000000064 epsilon:0.00998645168764533
episode:2236 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:2237 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:2238 steps:81 total reward:-2.600000000000001 epsilon:0.00998645168764533
episode:2239 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2240 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:2241 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:2242 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:2243 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2244 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:2245 steps:53 total reward:-2.0400000000000005 epsilon:0.00998645168764533
episode:2246 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2247 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:2248 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:2249 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2250 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:2251 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:2252 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:2253 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:2254 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2255 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:2256 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:2257 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:2258 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2259 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:2260 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2261 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2262 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:2263 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2264 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:2265 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2266 steps:82 total reward:-0.620000000000001 epsilon:0.00998645168764533
episode:2267 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:2268 steps:75 total reward:-0.48000000000000087 epsilon:0.00998645168764533
episode:2269 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:2270 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:2271 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:2272 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:2273 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:2274 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2275 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2276 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:2277 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:2278 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2279 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2280 steps:71 total reward:-2.400000000000001 epsilon:0.00998645168764533
episode:2281 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:2282 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2283 steps:65 total reward:-0.2800000000000007 epsilon:0.00998645168764533
episode:2284 steps:77 total reward:-0.5200000000000009 epsilon:0.00998645168764533
episode:2285 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:2286 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:2287 steps:4 total reward:-1.06 epsilon:0.00998645168764533
episode:2288 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:2289 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2290 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:2291 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:2292 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:2293 steps:65 total reward:-2.2800000000000007 epsilon:0.00998645168764533
episode:2294 steps:70 total reward:-0.3800000000000008 epsilon:0.00998645168764533
episode:2295 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2296 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:2297 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:2298 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:2299 steps:32 total reward:-1.62 epsilon:0.00998645168764533
episode:2300 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2301 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2302 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2303 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:2304 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:2305 steps:69 total reward:-0.36000000000000076 epsilon:0.00998645168764533
episode:2306 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:2307 steps:89 total reward:-0.7600000000000011 epsilon:0.00998645168764533
episode:2308 steps:44 total reward:-1.8600000000000003 epsilon:0.00998645168764533
episode:2309 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:2310 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:2311 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:2312 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2313 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2314 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:2315 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:2316 steps:39 total reward:-1.7600000000000002 epsilon:0.00998645168764533
episode:2317 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:2318 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:2319 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:2320 steps:90 total reward:-0.7800000000000011 epsilon:0.00998645168764533
episode:2321 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:2322 steps:88 total reward:-0.7400000000000011 epsilon:0.00998645168764533
episode:2323 steps:54 total reward:-2.0600000000000005 epsilon:0.00998645168764533
episode:2324 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:2325 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:2326 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2327 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2328 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2329 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2330 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:2331 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2332 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2333 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:2334 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2335 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:2336 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2337 steps:94 total reward:-0.8600000000000012 epsilon:0.00998645168764533
episode:2338 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2339 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:2340 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2341 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2342 steps:54 total reward:-2.0600000000000005 epsilon:0.00998645168764533
episode:2343 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2344 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:2345 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2346 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:2347 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2348 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:2349 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:2350 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:2351 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:2352 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:2353 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:2354 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:2355 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:2356 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2357 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2358 steps:91 total reward:-0.8000000000000012 epsilon:0.00998645168764533
episode:2359 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:2360 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2361 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2362 steps:92 total reward:-0.8200000000000012 epsilon:0.00998645168764533
episode:2363 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2364 steps:77 total reward:-0.5200000000000009 epsilon:0.00998645168764533
episode:2365 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:2366 steps:82 total reward:-2.620000000000001 epsilon:0.00998645168764533
episode:2367 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:2368 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:2369 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2370 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:2371 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2372 steps:64 total reward:-2.2600000000000007 epsilon:0.00998645168764533
episode:2373 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2374 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:2375 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:2376 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2377 steps:80 total reward:-0.580000000000001 epsilon:0.00998645168764533
episode:2378 steps:84 total reward:-0.660000000000001 epsilon:0.00998645168764533
episode:2379 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:2380 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:2381 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2382 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:2383 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2384 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:2385 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:2386 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:2387 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:2388 steps:62 total reward:-0.22000000000000064 epsilon:0.00998645168764533
episode:2389 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:2390 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2391 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:2392 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:2393 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:2394 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:2395 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:2396 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:2397 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:2398 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:2399 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:2400 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:2401 steps:78 total reward:-0.5400000000000009 epsilon:0.00998645168764533
episode:2402 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:2403 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:2404 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2405 steps:80 total reward:-0.580000000000001 epsilon:0.00998645168764533
episode:2406 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:2407 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2408 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2409 steps:60 total reward:-0.1800000000000006 epsilon:0.00998645168764533
episode:2410 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:2411 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:2412 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:2413 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:2414 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:2415 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:2416 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:2417 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:2418 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:2419 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:2420 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:2421 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2422 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:2423 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:2424 steps:88 total reward:-0.7400000000000011 epsilon:0.00998645168764533
episode:2425 steps:83 total reward:-0.640000000000001 epsilon:0.00998645168764533
episode:2426 steps:48 total reward:-1.9400000000000004 epsilon:0.00998645168764533
episode:2427 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:2428 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:2429 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:2430 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:2431 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:2432 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:2433 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2434 steps:70 total reward:-0.3800000000000008 epsilon:0.00998645168764533
episode:2435 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:2436 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2437 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:2438 steps:89 total reward:-0.7600000000000011 epsilon:0.00998645168764533
episode:2439 steps:94 total reward:-0.8600000000000012 epsilon:0.00998645168764533
episode:2440 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:2441 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:2442 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:2443 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:2444 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:2445 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2446 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:2447 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:2448 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2449 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:2450 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:2451 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:2452 steps:69 total reward:-0.36000000000000076 epsilon:0.00998645168764533
episode:2453 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2454 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:2455 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:2456 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:2457 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:2458 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:2459 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2460 steps:77 total reward:-0.5200000000000009 epsilon:0.00998645168764533
episode:2461 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:2462 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2463 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:2464 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:2465 steps:62 total reward:-0.22000000000000064 epsilon:0.00998645168764533
episode:2466 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:2467 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:2468 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:2469 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2470 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2471 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:2472 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:2473 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:2474 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:2475 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:2476 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:2477 steps:74 total reward:-0.46000000000000085 epsilon:0.00998645168764533
episode:2478 steps:45 total reward:-1.8800000000000003 epsilon:0.00998645168764533
episode:2479 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:2480 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:2481 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2482 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:2483 steps:62 total reward:-0.22000000000000064 epsilon:0.00998645168764533
episode:2484 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:2485 steps:59 total reward:-2.1600000000000006 epsilon:0.00998645168764533
episode:2486 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:2487 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2488 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2489 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:2490 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:2491 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:2492 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:2493 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:2494 steps:67 total reward:-2.3200000000000007 epsilon:0.00998645168764533
episode:2495 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:2496 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:2497 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:2498 steps:60 total reward:-0.1800000000000006 epsilon:0.00998645168764533
episode:2499 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2500 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2501 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2502 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:2503 steps:98 total reward:-0.9400000000000013 epsilon:0.00998645168764533
episode:2504 steps:92 total reward:-0.8200000000000012 epsilon:0.00998645168764533
episode:2505 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2506 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:2507 steps:87 total reward:-0.7200000000000011 epsilon:0.00998645168764533
episode:2508 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:2509 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2510 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:2511 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:2512 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:2513 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:2514 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2515 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:2516 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2517 steps:65 total reward:-0.2800000000000007 epsilon:0.00998645168764533
episode:2518 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:2519 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:2520 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2521 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:2522 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:2523 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:2524 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2525 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2526 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2527 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2528 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2529 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:2530 steps:91 total reward:-2.800000000000001 epsilon:0.00998645168764533
episode:2531 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2532 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2533 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2534 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2535 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:2536 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:2537 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:2538 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:2539 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:2540 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:2541 steps:4 total reward:-1.06 epsilon:0.00998645168764533
episode:2542 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2543 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:2544 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:2545 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:2546 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:2547 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:2548 steps:87 total reward:-0.7200000000000011 epsilon:0.00998645168764533
episode:2549 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:2550 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:2551 steps:50 total reward:-1.9800000000000004 epsilon:0.00998645168764533
episode:2552 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:2553 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2554 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:2555 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:2556 steps:83 total reward:-0.640000000000001 epsilon:0.00998645168764533
episode:2557 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2558 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:2559 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2560 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2561 steps:99 total reward:-2.9600000000000013 epsilon:0.00998645168764533
episode:2562 steps:94 total reward:-0.8600000000000012 epsilon:0.00998645168764533
episode:2563 steps:76 total reward:-0.5000000000000009 epsilon:0.00998645168764533
episode:2564 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2565 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:2566 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:2567 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:2568 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2569 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:2570 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2571 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:2572 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:2573 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:2574 steps:98 total reward:-0.9400000000000013 epsilon:0.00998645168764533
episode:2575 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:2576 steps:51 total reward:-2.0000000000000004 epsilon:0.00998645168764533
episode:2577 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:2578 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:2579 steps:94 total reward:-0.8600000000000012 epsilon:0.00998645168764533
episode:2580 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2581 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2582 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:2583 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:2584 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:2585 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2586 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2587 steps:91 total reward:-2.800000000000001 epsilon:0.00998645168764533
episode:2588 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:2589 steps:91 total reward:-2.800000000000001 epsilon:0.00998645168764533
episode:2590 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:2591 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2592 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:2593 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:2594 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:2595 steps:80 total reward:-0.580000000000001 epsilon:0.00998645168764533
episode:2596 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:2597 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2598 steps:62 total reward:-0.22000000000000064 epsilon:0.00998645168764533
episode:2599 steps:43 total reward:-1.8400000000000003 epsilon:0.00998645168764533
episode:2600 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2601 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:2602 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2603 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:2604 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:2605 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2606 steps:75 total reward:-0.48000000000000087 epsilon:0.00998645168764533
episode:2607 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:2608 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:2609 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:2610 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2611 steps:6 total reward:0.9 epsilon:0.00998645168764533
episode:2612 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2613 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2614 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:2615 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:2616 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2617 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:2618 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:2619 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:2620 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2621 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2622 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:2623 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2624 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:2625 steps:53 total reward:-0.04000000000000048 epsilon:0.00998645168764533
episode:2626 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2627 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:2628 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:2629 steps:51 total reward:-2.0000000000000004 epsilon:0.00998645168764533
episode:2630 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2631 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2632 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:2633 steps:61 total reward:-2.2000000000000006 epsilon:0.00998645168764533
episode:2634 steps:46 total reward:-1.9000000000000004 epsilon:0.00998645168764533
episode:2635 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:2636 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2637 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:2638 steps:67 total reward:-2.3200000000000007 epsilon:0.00998645168764533
episode:2639 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:2640 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2641 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:2642 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2643 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2644 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:2645 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2646 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2647 steps:35 total reward:-1.6800000000000002 epsilon:0.00998645168764533
episode:2648 steps:64 total reward:-2.2600000000000007 epsilon:0.00998645168764533
episode:2649 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:2650 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:2651 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2652 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:2653 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2654 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:2655 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2656 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:2657 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:2658 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:2659 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:2660 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:2661 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:2662 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2663 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:2664 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:2665 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:2666 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:2667 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2668 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2669 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2670 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:2671 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:2672 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:2673 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:2674 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:2675 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:2676 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:2677 steps:54 total reward:-2.0600000000000005 epsilon:0.00998645168764533
episode:2678 steps:78 total reward:-0.5400000000000009 epsilon:0.00998645168764533
episode:2679 steps:45 total reward:-1.8800000000000003 epsilon:0.00998645168764533
episode:2680 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2681 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:2682 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:2683 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:2684 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2685 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:2686 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:2687 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2688 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:2689 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:2690 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:2691 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:2692 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:2693 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:2694 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:2695 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:2696 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2697 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2698 steps:32 total reward:-1.62 epsilon:0.00998645168764533
episode:2699 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:2700 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:2701 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:2702 steps:82 total reward:-2.620000000000001 epsilon:0.00998645168764533
episode:2703 steps:59 total reward:-2.1600000000000006 epsilon:0.00998645168764533
episode:2704 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:2705 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:2706 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:2707 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:2708 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:2709 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:2710 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:2711 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:2712 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:2713 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:2714 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2715 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:2716 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:2717 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2718 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:2719 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:2720 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2721 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:2722 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:2723 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:2724 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2725 steps:100 total reward:-0.9800000000000013 epsilon:0.00998645168764533
episode:2726 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:2727 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:2728 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2729 steps:79 total reward:-0.5600000000000009 epsilon:0.00998645168764533
episode:2730 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:2731 steps:44 total reward:-1.8600000000000003 epsilon:0.00998645168764533
episode:2732 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:2733 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:2734 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:2735 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:2736 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:2737 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:2738 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:2739 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2740 steps:6 total reward:0.9 epsilon:0.00998645168764533
episode:2741 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:2742 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2743 steps:83 total reward:-2.640000000000001 epsilon:0.00998645168764533
episode:2744 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:2745 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:2746 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:2747 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:2748 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:2749 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2750 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:2751 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:2752 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2753 steps:40 total reward:-1.7800000000000002 epsilon:0.00998645168764533
episode:2754 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:2755 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:2756 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:2757 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:2758 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2759 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:2760 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:2761 steps:95 total reward:-2.8800000000000012 epsilon:0.00998645168764533
episode:2762 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2763 steps:53 total reward:-0.04000000000000048 epsilon:0.00998645168764533
episode:2764 steps:100 total reward:-0.9800000000000013 epsilon:0.00998645168764533
episode:2765 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:2766 steps:54 total reward:-2.0600000000000005 epsilon:0.00998645168764533
episode:2767 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:2768 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:2769 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:2770 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:2771 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:2772 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:2773 steps:70 total reward:-0.3800000000000008 epsilon:0.00998645168764533
episode:2774 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:2775 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:2776 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:2777 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2778 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2779 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2780 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:2781 steps:74 total reward:-0.46000000000000085 epsilon:0.00998645168764533
episode:2782 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2783 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2784 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:2785 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:2786 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:2787 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:2788 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:2789 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:2790 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:2791 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2792 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2793 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:2794 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2795 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:2796 steps:51 total reward:-2.0000000000000004 epsilon:0.00998645168764533
episode:2797 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:2798 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:2799 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:2800 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:2801 steps:43 total reward:-1.8400000000000003 epsilon:0.00998645168764533
episode:2802 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:2803 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2804 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2805 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2806 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:2807 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:2808 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:2809 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:2810 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:2811 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:2812 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:2813 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:2814 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:2815 steps:96 total reward:-0.9000000000000012 epsilon:0.00998645168764533
episode:2816 steps:69 total reward:-0.36000000000000076 epsilon:0.00998645168764533
episode:2817 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:2818 steps:83 total reward:-2.640000000000001 epsilon:0.00998645168764533
episode:2819 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:2820 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:2821 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2822 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:2823 steps:66 total reward:-2.3000000000000007 epsilon:0.00998645168764533
episode:2824 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:2825 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:2826 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:2827 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:2828 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:2829 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:2830 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:2831 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:2832 steps:78 total reward:-0.5400000000000009 epsilon:0.00998645168764533
episode:2833 steps:46 total reward:-1.9000000000000004 epsilon:0.00998645168764533
episode:2834 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:2835 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:2836 steps:38 total reward:-1.7400000000000002 epsilon:0.00998645168764533
episode:2837 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:2838 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2839 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:2840 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:2841 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:2842 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:2843 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:2844 steps:35 total reward:-1.6800000000000002 epsilon:0.00998645168764533
episode:2845 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:2846 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:2847 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:2848 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2849 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:2850 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:2851 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:2852 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:2853 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2854 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:2855 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:2856 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:2857 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:2858 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:2859 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:2860 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:2861 steps:96 total reward:-2.9000000000000012 epsilon:0.00998645168764533
episode:2862 steps:97 total reward:-0.9200000000000013 epsilon:0.00998645168764533
episode:2863 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:2864 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:2865 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:2866 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:2867 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:2868 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:2869 steps:66 total reward:-2.3000000000000007 epsilon:0.00998645168764533
episode:2870 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:2871 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:2872 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:2873 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:2874 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:2875 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:2876 steps:77 total reward:-0.5200000000000009 epsilon:0.00998645168764533
episode:2877 steps:91 total reward:-0.8000000000000012 epsilon:0.00998645168764533
episode:2878 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:2879 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:2880 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:2881 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2882 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:2883 steps:75 total reward:-0.48000000000000087 epsilon:0.00998645168764533
episode:2884 steps:53 total reward:-0.04000000000000048 epsilon:0.00998645168764533
episode:2885 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:2886 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:2887 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2888 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:2889 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:2890 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:2891 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:2892 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:2893 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:2894 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:2895 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:2896 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2897 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2898 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:2899 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:2900 steps:45 total reward:-1.8800000000000003 epsilon:0.00998645168764533
episode:2901 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:2902 steps:83 total reward:-0.640000000000001 epsilon:0.00998645168764533
episode:2903 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:2904 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:2905 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:2906 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:2907 steps:54 total reward:-2.0600000000000005 epsilon:0.00998645168764533
episode:2908 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:2909 steps:74 total reward:-0.46000000000000085 epsilon:0.00998645168764533
episode:2910 steps:68 total reward:-2.3400000000000007 epsilon:0.00998645168764533
episode:2911 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:2912 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:2913 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:2914 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2915 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2916 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:2917 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:2918 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:2919 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:2920 steps:2 total reward:-1.02 epsilon:0.00998645168764533
episode:2921 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2922 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:2923 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2924 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2925 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:2926 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:2927 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2928 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:2929 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:2930 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2931 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:2932 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:2933 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:2934 steps:62 total reward:-2.2200000000000006 epsilon:0.00998645168764533
episode:2935 steps:79 total reward:-0.5600000000000009 epsilon:0.00998645168764533
episode:2936 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:2937 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:2938 steps:63 total reward:-2.2400000000000007 epsilon:0.00998645168764533
episode:2939 steps:81 total reward:-0.600000000000001 epsilon:0.00998645168764533
episode:2940 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:2941 steps:35 total reward:-1.6800000000000002 epsilon:0.00998645168764533
episode:2942 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:2943 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:2944 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2945 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2946 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:2947 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:2948 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:2949 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:2950 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:2951 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:2952 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2953 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:2954 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:2955 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:2956 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:2957 steps:76 total reward:-0.5000000000000009 epsilon:0.00998645168764533
episode:2958 steps:43 total reward:-1.8400000000000003 epsilon:0.00998645168764533
episode:2959 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2960 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:2961 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:2962 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:2963 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:2964 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:2965 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:2966 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:2967 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:2968 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:2969 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:2970 steps:49 total reward:-1.9600000000000004 epsilon:0.00998645168764533
episode:2971 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:2972 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:2973 steps:32 total reward:-1.62 epsilon:0.00998645168764533
episode:2974 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:2975 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:2976 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:2977 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:2978 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:2979 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:2980 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:2981 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:2982 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:2983 steps:55 total reward:-2.0800000000000005 epsilon:0.00998645168764533
episode:2984 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:2985 steps:83 total reward:-0.640000000000001 epsilon:0.00998645168764533
episode:2986 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:2987 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:2988 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:2989 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:2990 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:2991 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:2992 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2993 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:2994 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:2995 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:2996 steps:92 total reward:-2.820000000000001 epsilon:0.00998645168764533
episode:2997 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:2998 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
[2017-07-16 15:10:48,683] Starting new video recorder writing to C:\Users\Abdul\Documents\My Projects\Deep learning nano degree\my-experiments\reinforcement learning\monitor\openaigym.video.2.12772.video003000.json
episode:2999 steps:38 total reward:-1.7400000000000002 epsilon:0.00998645168764533
episode:3000 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:3001 steps:38 total reward:-1.7400000000000002 epsilon:0.00998645168764533
episode:3002 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:3003 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3004 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:3005 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:3006 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:3007 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:3008 steps:85 total reward:-2.680000000000001 epsilon:0.00998645168764533
episode:3009 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:3010 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:3011 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:3012 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:3013 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:3014 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:3015 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:3016 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:3017 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:3018 steps:49 total reward:-1.9600000000000004 epsilon:0.00998645168764533
episode:3019 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:3020 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:3021 steps:40 total reward:-1.7800000000000002 epsilon:0.00998645168764533
episode:3022 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:3023 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:3024 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:3025 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:3026 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:3027 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:3028 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3029 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:3030 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3031 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:3032 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:3033 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:3034 steps:81 total reward:-0.600000000000001 epsilon:0.00998645168764533
episode:3035 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3036 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:3037 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:3038 steps:93 total reward:-0.8400000000000012 epsilon:0.00998645168764533
episode:3039 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:3040 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:3041 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:3042 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:3043 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:3044 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:3045 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3046 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:3047 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:3048 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:3049 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:3050 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3051 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:3052 steps:85 total reward:-2.680000000000001 epsilon:0.00998645168764533
episode:3053 steps:55 total reward:-2.0800000000000005 epsilon:0.00998645168764533
episode:3054 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:3055 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:3056 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:3057 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3058 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3059 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:3060 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:3061 steps:72 total reward:-2.420000000000001 epsilon:0.00998645168764533
episode:3062 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:3063 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:3064 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:3065 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:3066 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:3067 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:3068 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3069 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:3070 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:3071 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:3072 steps:40 total reward:-1.7800000000000002 epsilon:0.00998645168764533
episode:3073 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:3074 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:3075 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:3076 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:3077 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:3078 steps:57 total reward:-2.1200000000000006 epsilon:0.00998645168764533
episode:3079 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:3080 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:3081 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3082 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:3083 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:3084 steps:96 total reward:-0.9000000000000012 epsilon:0.00998645168764533
episode:3085 steps:32 total reward:-1.62 epsilon:0.00998645168764533
episode:3086 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:3087 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3088 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:3089 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:3090 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3091 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:3092 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:3093 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:3094 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:3095 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:3096 steps:98 total reward:-0.9400000000000013 epsilon:0.00998645168764533
episode:3097 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:3098 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3099 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:3100 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:3101 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3102 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:3103 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:3104 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:3105 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:3106 steps:80 total reward:-0.580000000000001 epsilon:0.00998645168764533
episode:3107 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:3108 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:3109 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:3110 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3111 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:3112 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:3113 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:3114 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3115 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:3116 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:3117 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:3118 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:3119 steps:58 total reward:-2.1400000000000006 epsilon:0.00998645168764533
episode:3120 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:3121 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:3122 steps:35 total reward:-1.6800000000000002 epsilon:0.00998645168764533
episode:3123 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:3124 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:3125 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:3126 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:3127 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3128 steps:77 total reward:-2.520000000000001 epsilon:0.00998645168764533
episode:3129 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:3130 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:3131 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3132 steps:53 total reward:-0.04000000000000048 epsilon:0.00998645168764533
episode:3133 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:3134 steps:44 total reward:-1.8600000000000003 epsilon:0.00998645168764533
episode:3135 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3136 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:3137 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:3138 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:3139 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3140 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:3141 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:3142 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:3143 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:3144 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:3145 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:3146 steps:70 total reward:-2.380000000000001 epsilon:0.00998645168764533
episode:3147 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:3148 steps:48 total reward:-1.9400000000000004 epsilon:0.00998645168764533
episode:3149 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:3150 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:3151 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3152 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:3153 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3154 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:3155 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:3156 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:3157 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3158 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:3159 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:3160 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:3161 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:3162 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:3163 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:3164 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3165 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:3166 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:3167 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:3168 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3169 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3170 steps:60 total reward:-2.1800000000000006 epsilon:0.00998645168764533
episode:3171 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:3172 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:3173 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3174 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:3175 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:3176 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:3177 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:3178 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:3179 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:3180 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:3181 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:3182 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3183 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:3184 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:3185 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:3186 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:3187 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:3188 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:3189 steps:96 total reward:-0.9000000000000012 epsilon:0.00998645168764533
episode:3190 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3191 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:3192 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:3193 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:3194 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:3195 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3196 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:3197 steps:53 total reward:-2.0400000000000005 epsilon:0.00998645168764533
episode:3198 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:3199 steps:90 total reward:-0.7800000000000011 epsilon:0.00998645168764533
episode:3200 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:3201 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:3202 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:3203 steps:63 total reward:-2.2400000000000007 epsilon:0.00998645168764533
episode:3204 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:3205 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:3206 steps:76 total reward:-0.5000000000000009 epsilon:0.00998645168764533
episode:3207 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:3208 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:3209 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:3210 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3211 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:3212 steps:45 total reward:-1.8800000000000003 epsilon:0.00998645168764533
episode:3213 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:3214 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3215 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:3216 steps:40 total reward:-1.7800000000000002 epsilon:0.00998645168764533
episode:3217 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:3218 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:3219 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:3220 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:3221 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:3222 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:3223 steps:75 total reward:-0.48000000000000087 epsilon:0.00998645168764533
episode:3224 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:3225 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:3226 steps:65 total reward:-0.2800000000000007 epsilon:0.00998645168764533
episode:3227 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:3228 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:3229 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:3230 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:3231 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:3232 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:3233 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:3234 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3235 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3236 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:3237 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3238 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:3239 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:3240 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:3241 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:3242 steps:51 total reward:-2.0000000000000004 epsilon:0.00998645168764533
episode:3243 steps:81 total reward:-0.600000000000001 epsilon:0.00998645168764533
episode:3244 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:3245 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:3246 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:3247 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:3248 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:3249 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:3250 steps:39 total reward:-1.7600000000000002 epsilon:0.00998645168764533
episode:3251 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:3252 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3253 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:3254 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3255 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:3256 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:3257 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3258 steps:76 total reward:-0.5000000000000009 epsilon:0.00998645168764533
episode:3259 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3260 steps:32 total reward:-1.62 epsilon:0.00998645168764533
episode:3261 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:3262 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:3263 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3264 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:3265 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3266 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:3267 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:3268 steps:83 total reward:-2.640000000000001 epsilon:0.00998645168764533
episode:3269 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:3270 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:3271 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:3272 steps:86 total reward:-0.7000000000000011 epsilon:0.00998645168764533
episode:3273 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:3274 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:3275 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:3276 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:3277 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:3278 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:3279 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3280 steps:65 total reward:-0.2800000000000007 epsilon:0.00998645168764533
episode:3281 steps:34 total reward:-1.6600000000000001 epsilon:0.00998645168764533
episode:3282 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:3283 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3284 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:3285 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:3286 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:3287 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3288 steps:60 total reward:-0.1800000000000006 epsilon:0.00998645168764533
episode:3289 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:3290 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:3291 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3292 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:3293 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3294 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:3295 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:3296 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:3297 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:3298 steps:94 total reward:-0.8600000000000012 epsilon:0.00998645168764533
episode:3299 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:3300 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:3301 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3302 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:3303 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:3304 steps:100 total reward:-0.9800000000000013 epsilon:0.00998645168764533
episode:3305 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:3306 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:3307 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:3308 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:3309 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:3310 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:3311 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3312 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3313 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:3314 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:3315 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:3316 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3317 steps:39 total reward:-1.7600000000000002 epsilon:0.00998645168764533
episode:3318 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3319 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3320 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:3321 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:3322 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:3323 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:3324 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:3325 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3326 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:3327 steps:53 total reward:-2.0400000000000005 epsilon:0.00998645168764533
episode:3328 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3329 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:3330 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:3331 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3332 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:3333 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:3334 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:3335 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:3336 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:3337 steps:86 total reward:-0.7000000000000011 epsilon:0.00998645168764533
episode:3338 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:3339 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:3340 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:3341 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:3342 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:3343 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:3344 steps:90 total reward:-0.7800000000000011 epsilon:0.00998645168764533
episode:3345 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3346 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:3347 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:3348 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:3349 steps:44 total reward:-1.8600000000000003 epsilon:0.00998645168764533
episode:3350 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:3351 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:3352 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:3353 steps:95 total reward:-0.8800000000000012 epsilon:0.00998645168764533
episode:3354 steps:60 total reward:-0.1800000000000006 epsilon:0.00998645168764533
episode:3355 steps:77 total reward:-0.5200000000000009 epsilon:0.00998645168764533
episode:3356 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3357 steps:56 total reward:-2.1000000000000005 epsilon:0.00998645168764533
episode:3358 steps:35 total reward:-1.6800000000000002 epsilon:0.00998645168764533
episode:3359 steps:92 total reward:-0.8200000000000012 epsilon:0.00998645168764533
episode:3360 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:3361 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:3362 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:3363 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:3364 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:3365 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3366 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:3367 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:3368 steps:57 total reward:-2.1200000000000006 epsilon:0.00998645168764533
episode:3369 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:3370 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:3371 steps:60 total reward:-2.1800000000000006 epsilon:0.00998645168764533
episode:3372 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:3373 steps:78 total reward:-2.540000000000001 epsilon:0.00998645168764533
episode:3374 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:3375 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:3376 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3377 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:3378 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:3379 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:3380 steps:6 total reward:0.9 epsilon:0.00998645168764533
episode:3381 steps:71 total reward:-2.400000000000001 epsilon:0.00998645168764533
episode:3382 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:3383 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3384 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:3385 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:3386 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:3387 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3388 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:3389 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:3390 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3391 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:3392 steps:45 total reward:-1.8800000000000003 epsilon:0.00998645168764533
episode:3393 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:3394 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3395 steps:95 total reward:-0.8800000000000012 epsilon:0.00998645168764533
episode:3396 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:3397 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:3398 steps:94 total reward:-2.860000000000001 epsilon:0.00998645168764533
episode:3399 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:3400 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:3401 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:3402 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:3403 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3404 steps:43 total reward:-1.8400000000000003 epsilon:0.00998645168764533
episode:3405 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:3406 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:3407 steps:67 total reward:-2.3200000000000007 epsilon:0.00998645168764533
episode:3408 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:3409 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:3410 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:3411 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3412 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3413 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:3414 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:3415 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:3416 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:3417 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:3418 steps:82 total reward:-2.620000000000001 epsilon:0.00998645168764533
episode:3419 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:3420 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:3421 steps:77 total reward:-2.520000000000001 epsilon:0.00998645168764533
episode:3422 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3423 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:3424 steps:76 total reward:-0.5000000000000009 epsilon:0.00998645168764533
episode:3425 steps:34 total reward:-1.6600000000000001 epsilon:0.00998645168764533
episode:3426 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:3427 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:3428 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:3429 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:3430 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:3431 steps:87 total reward:-0.7200000000000011 epsilon:0.00998645168764533
episode:3432 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3433 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3434 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:3435 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:3436 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:3437 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3438 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:3439 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3440 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3441 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:3442 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:3443 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3444 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:3445 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3446 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3447 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:3448 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:3449 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3450 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3451 steps:74 total reward:-0.46000000000000085 epsilon:0.00998645168764533
episode:3452 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:3453 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3454 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3455 steps:55 total reward:-2.0800000000000005 epsilon:0.00998645168764533
episode:3456 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:3457 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:3458 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:3459 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:3460 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:3461 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:3462 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3463 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:3464 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:3465 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:3466 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:3467 steps:60 total reward:-0.1800000000000006 epsilon:0.00998645168764533
episode:3468 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:3469 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:3470 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3471 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:3472 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:3473 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:3474 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3475 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3476 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:3477 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:3478 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:3479 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3480 steps:61 total reward:-2.2000000000000006 epsilon:0.00998645168764533
episode:3481 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:3482 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:3483 steps:62 total reward:-0.22000000000000064 epsilon:0.00998645168764533
episode:3484 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:3485 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:3486 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:3487 steps:71 total reward:-2.400000000000001 epsilon:0.00998645168764533
episode:3488 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:3489 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:3490 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:3491 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:3492 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:3493 steps:65 total reward:-0.2800000000000007 epsilon:0.00998645168764533
episode:3494 steps:32 total reward:-1.62 epsilon:0.00998645168764533
episode:3495 steps:70 total reward:-2.380000000000001 epsilon:0.00998645168764533
episode:3496 steps:89 total reward:-0.7600000000000011 epsilon:0.00998645168764533
episode:3497 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:3498 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:3499 steps:65 total reward:-0.2800000000000007 epsilon:0.00998645168764533
episode:3500 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:3501 steps:46 total reward:-1.9000000000000004 epsilon:0.00998645168764533
episode:3502 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:3503 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:3504 steps:46 total reward:-1.9000000000000004 epsilon:0.00998645168764533
episode:3505 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:3506 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:3507 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:3508 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:3509 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:3510 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:3511 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3512 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3513 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3514 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:3515 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3516 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:3517 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:3518 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:3519 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:3520 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:3521 steps:60 total reward:-2.1800000000000006 epsilon:0.00998645168764533
episode:3522 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:3523 steps:34 total reward:-1.6600000000000001 epsilon:0.00998645168764533
episode:3524 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:3525 steps:4 total reward:-1.06 epsilon:0.00998645168764533
episode:3526 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:3527 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:3528 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3529 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:3530 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3531 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:3532 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:3533 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3534 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:3535 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:3536 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:3537 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:3538 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:3539 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3540 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3541 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:3542 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:3543 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:3544 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:3545 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:3546 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:3547 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:3548 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3549 steps:49 total reward:-1.9600000000000004 epsilon:0.00998645168764533
episode:3550 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:3551 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:3552 steps:70 total reward:-0.3800000000000008 epsilon:0.00998645168764533
episode:3553 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:3554 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:3555 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:3556 steps:45 total reward:-1.8800000000000003 epsilon:0.00998645168764533
episode:3557 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:3558 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:3559 steps:93 total reward:-2.840000000000001 epsilon:0.00998645168764533
episode:3560 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:3561 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:3562 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:3563 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:3564 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:3565 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:3566 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:3567 steps:54 total reward:-2.0600000000000005 epsilon:0.00998645168764533
episode:3568 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3569 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:3570 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:3571 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:3572 steps:75 total reward:-0.48000000000000087 epsilon:0.00998645168764533
episode:3573 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:3574 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:3575 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3576 steps:74 total reward:-0.46000000000000085 epsilon:0.00998645168764533
episode:3577 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3578 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:3579 steps:81 total reward:-0.600000000000001 epsilon:0.00998645168764533
episode:3580 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3581 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:3582 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:3583 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3584 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:3585 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3586 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:3587 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:3588 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:3589 steps:39 total reward:-1.7600000000000002 epsilon:0.00998645168764533
episode:3590 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:3591 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3592 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:3593 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3594 steps:65 total reward:-2.2800000000000007 epsilon:0.00998645168764533
episode:3595 steps:69 total reward:-0.36000000000000076 epsilon:0.00998645168764533
episode:3596 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:3597 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:3598 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:3599 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:3600 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3601 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:3602 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3603 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:3604 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:3605 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:3606 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3607 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:3608 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:3609 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3610 steps:53 total reward:-0.04000000000000048 epsilon:0.00998645168764533
episode:3611 steps:38 total reward:-1.7400000000000002 epsilon:0.00998645168764533
episode:3612 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:3613 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:3614 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:3615 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:3616 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:3617 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:3618 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:3619 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:3620 steps:96 total reward:-2.9000000000000012 epsilon:0.00998645168764533
episode:3621 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:3622 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:3623 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:3624 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:3625 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:3626 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:3627 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:3628 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:3629 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:3630 steps:90 total reward:-0.7800000000000011 epsilon:0.00998645168764533
episode:3631 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:3632 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:3633 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:3634 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:3635 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:3636 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:3637 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3638 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:3639 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:3640 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:3641 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:3642 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:3643 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:3644 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:3645 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:3646 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:3647 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:3648 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:3649 steps:93 total reward:-0.8400000000000012 epsilon:0.00998645168764533
episode:3650 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:3651 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:3652 steps:39 total reward:-1.7600000000000002 epsilon:0.00998645168764533
episode:3653 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:3654 steps:40 total reward:-1.7800000000000002 epsilon:0.00998645168764533
episode:3655 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:3656 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:3657 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:3658 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:3659 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:3660 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:3661 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:3662 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:3663 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:3664 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:3665 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3666 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:3667 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:3668 steps:62 total reward:-0.22000000000000064 epsilon:0.00998645168764533
episode:3669 steps:70 total reward:-0.3800000000000008 epsilon:0.00998645168764533
episode:3670 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:3671 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3672 steps:71 total reward:-2.400000000000001 epsilon:0.00998645168764533
episode:3673 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:3674 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:3675 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:3676 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:3677 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:3678 steps:43 total reward:-1.8400000000000003 epsilon:0.00998645168764533
episode:3679 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:3680 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:3681 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:3682 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:3683 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:3684 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:3685 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:3686 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3687 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3688 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:3689 steps:39 total reward:-1.7600000000000002 epsilon:0.00998645168764533
episode:3690 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:3691 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:3692 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:3693 steps:40 total reward:-1.7800000000000002 epsilon:0.00998645168764533
episode:3694 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:3695 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:3696 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:3697 steps:35 total reward:-1.6800000000000002 epsilon:0.00998645168764533
episode:3698 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3699 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:3700 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:3701 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:3702 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:3703 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:3704 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:3705 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:3706 steps:62 total reward:-0.22000000000000064 epsilon:0.00998645168764533
episode:3707 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:3708 steps:100 total reward:-0.9800000000000013 epsilon:0.00998645168764533
episode:3709 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3710 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:3711 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:3712 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3713 steps:76 total reward:-2.500000000000001 epsilon:0.00998645168764533
episode:3714 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3715 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:3716 steps:47 total reward:-1.9200000000000004 epsilon:0.00998645168764533
episode:3717 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3718 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:3719 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:3720 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3721 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:3722 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:3723 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3724 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:3725 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:3726 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:3727 steps:34 total reward:-1.6600000000000001 epsilon:0.00998645168764533
episode:3728 steps:74 total reward:-0.46000000000000085 epsilon:0.00998645168764533
episode:3729 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:3730 steps:92 total reward:-0.8200000000000012 epsilon:0.00998645168764533
episode:3731 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:3732 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:3733 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:3734 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3735 steps:94 total reward:-0.8600000000000012 epsilon:0.00998645168764533
episode:3736 steps:4 total reward:-1.06 epsilon:0.00998645168764533
episode:3737 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:3738 steps:81 total reward:-0.600000000000001 epsilon:0.00998645168764533
episode:3739 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:3740 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:3741 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:3742 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:3743 steps:99 total reward:-0.9600000000000013 epsilon:0.00998645168764533
episode:3744 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3745 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:3746 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3747 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:3748 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:3749 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:3750 steps:48 total reward:-1.9400000000000004 epsilon:0.00998645168764533
episode:3751 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3752 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:3753 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:3754 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:3755 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:3756 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3757 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:3758 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:3759 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:3760 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:3761 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:3762 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:3763 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:3764 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:3765 steps:32 total reward:-1.62 epsilon:0.00998645168764533
episode:3766 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:3767 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:3768 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:3769 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:3770 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:3771 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:3772 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3773 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:3774 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3775 steps:95 total reward:-0.8800000000000012 epsilon:0.00998645168764533
episode:3776 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:3777 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:3778 steps:38 total reward:-1.7400000000000002 epsilon:0.00998645168764533
episode:3779 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:3780 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:3781 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:3782 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:3783 steps:94 total reward:-2.860000000000001 epsilon:0.00998645168764533
episode:3784 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:3785 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:3786 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3787 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:3788 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:3789 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:3790 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:3791 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:3792 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:3793 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3794 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3795 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3796 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3797 steps:78 total reward:-0.5400000000000009 epsilon:0.00998645168764533
episode:3798 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:3799 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:3800 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:3801 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:3802 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:3803 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:3804 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:3805 steps:89 total reward:-0.7600000000000011 epsilon:0.00998645168764533
episode:3806 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:3807 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3808 steps:60 total reward:-2.1800000000000006 epsilon:0.00998645168764533
episode:3809 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:3810 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:3811 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:3812 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:3813 steps:98 total reward:-0.9400000000000013 epsilon:0.00998645168764533
episode:3814 steps:50 total reward:-1.9800000000000004 epsilon:0.00998645168764533
episode:3815 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:3816 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:3817 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:3818 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:3819 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:3820 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:3821 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:3822 steps:53 total reward:-2.0400000000000005 epsilon:0.00998645168764533
episode:3823 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:3824 steps:88 total reward:-0.7400000000000011 epsilon:0.00998645168764533
episode:3825 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:3826 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:3827 steps:70 total reward:-2.380000000000001 epsilon:0.00998645168764533
episode:3828 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:3829 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3830 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3831 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:3832 steps:84 total reward:-2.660000000000001 epsilon:0.00998645168764533
episode:3833 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3834 steps:86 total reward:-2.700000000000001 epsilon:0.00998645168764533
episode:3835 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:3836 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3837 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:3838 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:3839 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:3840 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:3841 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:3842 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3843 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3844 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:3845 steps:34 total reward:-1.6600000000000001 epsilon:0.00998645168764533
episode:3846 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:3847 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:3848 steps:44 total reward:-1.8600000000000003 epsilon:0.00998645168764533
episode:3849 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3850 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3851 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:3852 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:3853 steps:77 total reward:-0.5200000000000009 epsilon:0.00998645168764533
episode:3854 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:3855 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3856 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:3857 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:3858 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:3859 steps:82 total reward:-0.620000000000001 epsilon:0.00998645168764533
episode:3860 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:3861 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:3862 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:3863 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:3864 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:3865 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:3866 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3867 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:3868 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:3869 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:3870 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:3871 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:3872 steps:35 total reward:-1.6800000000000002 epsilon:0.00998645168764533
episode:3873 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:3874 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:3875 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3876 steps:88 total reward:-2.740000000000001 epsilon:0.00998645168764533
episode:3877 steps:81 total reward:-0.600000000000001 epsilon:0.00998645168764533
episode:3878 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3879 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3880 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:3881 steps:40 total reward:-1.7800000000000002 epsilon:0.00998645168764533
episode:3882 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3883 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:3884 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:3885 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3886 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:3887 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:3888 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:3889 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:3890 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3891 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:3892 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:3893 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:3894 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:3895 steps:2 total reward:-1.02 epsilon:0.00998645168764533
episode:3896 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:3897 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:3898 steps:77 total reward:-0.5200000000000009 epsilon:0.00998645168764533
episode:3899 steps:58 total reward:-2.1400000000000006 epsilon:0.00998645168764533
episode:3900 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:3901 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3902 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3903 steps:93 total reward:-2.840000000000001 epsilon:0.00998645168764533
episode:3904 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:3905 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3906 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:3907 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:3908 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:3909 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:3910 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3911 steps:50 total reward:-1.9800000000000004 epsilon:0.00998645168764533
episode:3912 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:3913 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:3914 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:3915 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3916 steps:75 total reward:-0.48000000000000087 epsilon:0.00998645168764533
episode:3917 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:3918 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:3919 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:3920 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:3921 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:3922 steps:88 total reward:-2.740000000000001 epsilon:0.00998645168764533
episode:3923 steps:71 total reward:-2.400000000000001 epsilon:0.00998645168764533
episode:3924 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3925 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:3926 steps:78 total reward:-2.540000000000001 epsilon:0.00998645168764533
episode:3927 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:3928 steps:63 total reward:-2.2400000000000007 epsilon:0.00998645168764533
episode:3929 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3930 steps:81 total reward:-2.600000000000001 epsilon:0.00998645168764533
episode:3931 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3932 steps:78 total reward:-0.5400000000000009 epsilon:0.00998645168764533
episode:3933 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3934 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:3935 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3936 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:3937 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:3938 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:3939 steps:40 total reward:-1.7800000000000002 epsilon:0.00998645168764533
episode:3940 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:3941 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3942 steps:57 total reward:-2.1200000000000006 epsilon:0.00998645168764533
episode:3943 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:3944 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:3945 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:3946 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:3947 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:3948 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:3949 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:3950 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:3951 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:3952 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:3953 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:3954 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:3955 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:3956 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:3957 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:3958 steps:51 total reward:-2.0000000000000004 epsilon:0.00998645168764533
episode:3959 steps:84 total reward:-0.660000000000001 epsilon:0.00998645168764533
episode:3960 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:3961 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:3962 steps:54 total reward:-2.0600000000000005 epsilon:0.00998645168764533
episode:3963 steps:75 total reward:-0.48000000000000087 epsilon:0.00998645168764533
episode:3964 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:3965 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:3966 steps:61 total reward:-2.2000000000000006 epsilon:0.00998645168764533
episode:3967 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3968 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:3969 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3970 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:3971 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:3972 steps:44 total reward:-1.8600000000000003 epsilon:0.00998645168764533
episode:3973 steps:89 total reward:-0.7600000000000011 epsilon:0.00998645168764533
episode:3974 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:3975 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:3976 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:3977 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:3978 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:3979 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:3980 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:3981 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:3982 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:3983 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:3984 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:3985 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:3986 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:3987 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3988 steps:60 total reward:-2.1800000000000006 epsilon:0.00998645168764533
episode:3989 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:3990 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:3991 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:3992 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:3993 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:3994 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:3995 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:3996 steps:85 total reward:-2.680000000000001 epsilon:0.00998645168764533
episode:3997 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
[2017-07-16 15:15:05,725] Starting new video recorder writing to C:\Users\Abdul\Documents\My Projects\Deep learning nano degree\my-experiments\reinforcement learning\monitor\openaigym.video.2.12772.video004000.json
episode:3998 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:3999 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:4000 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:4001 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:4002 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:4003 steps:97 total reward:-0.9200000000000013 epsilon:0.00998645168764533
episode:4004 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:4005 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4006 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4007 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:4008 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:4009 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:4010 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4011 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:4012 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4013 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:4014 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4015 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:4016 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:4017 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:4018 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:4019 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:4020 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:4021 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:4022 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:4023 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:4024 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:4025 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:4026 steps:2 total reward:-1.02 epsilon:0.00998645168764533
episode:4027 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:4028 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4029 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:4030 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:4031 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:4032 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:4033 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:4034 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:4035 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:4036 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:4037 steps:45 total reward:-1.8800000000000003 epsilon:0.00998645168764533
episode:4038 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:4039 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:4040 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:4041 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:4042 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:4043 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:4044 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:4045 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:4046 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:4047 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:4048 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:4049 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:4050 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:4051 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4052 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:4053 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:4054 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:4055 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:4056 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:4057 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:4058 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:4059 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:4060 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:4061 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4062 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:4063 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:4064 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:4065 steps:98 total reward:-2.9400000000000013 epsilon:0.00998645168764533
episode:4066 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:4067 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:4068 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:4069 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:4070 steps:89 total reward:-0.7600000000000011 epsilon:0.00998645168764533
episode:4071 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:4072 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:4073 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:4074 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:4075 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4076 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:4077 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:4078 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4079 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:4080 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:4081 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:4082 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:4083 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:4084 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:4085 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:4086 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:4087 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:4088 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4089 steps:86 total reward:-0.7000000000000011 epsilon:0.00998645168764533
episode:4090 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:4091 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:4092 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:4093 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:4094 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:4095 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:4096 steps:96 total reward:-0.9000000000000012 epsilon:0.00998645168764533
episode:4097 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:4098 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:4099 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:4100 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:4101 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:4102 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:4103 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:4104 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:4105 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4106 steps:49 total reward:-1.9600000000000004 epsilon:0.00998645168764533
episode:4107 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:4108 steps:82 total reward:-0.620000000000001 epsilon:0.00998645168764533
episode:4109 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:4110 steps:64 total reward:-2.2600000000000007 epsilon:0.00998645168764533
episode:4111 steps:43 total reward:-1.8400000000000003 epsilon:0.00998645168764533
episode:4112 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:4113 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:4114 steps:44 total reward:-1.8600000000000003 epsilon:0.00998645168764533
episode:4115 steps:71 total reward:-2.400000000000001 epsilon:0.00998645168764533
episode:4116 steps:100 total reward:-0.9800000000000013 epsilon:0.00998645168764533
episode:4117 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:4118 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:4119 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:4120 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4121 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:4122 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:4123 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:4124 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4125 steps:84 total reward:-0.660000000000001 epsilon:0.00998645168764533
episode:4126 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:4127 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:4128 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4129 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:4130 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:4131 steps:60 total reward:-0.1800000000000006 epsilon:0.00998645168764533
episode:4132 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:4133 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:4134 steps:62 total reward:-2.2200000000000006 epsilon:0.00998645168764533
episode:4135 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:4136 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:4137 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:4138 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:4139 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:4140 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4141 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:4142 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:4143 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:4144 steps:95 total reward:-0.8800000000000012 epsilon:0.00998645168764533
episode:4145 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:4146 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:4147 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4148 steps:34 total reward:-1.6600000000000001 epsilon:0.00998645168764533
episode:4149 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:4150 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:4151 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4152 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4153 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:4154 steps:81 total reward:-0.600000000000001 epsilon:0.00998645168764533
episode:4155 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4156 steps:74 total reward:-0.46000000000000085 epsilon:0.00998645168764533
episode:4157 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:4158 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:4159 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4160 steps:62 total reward:-2.2200000000000006 epsilon:0.00998645168764533
episode:4161 steps:35 total reward:-1.6800000000000002 epsilon:0.00998645168764533
episode:4162 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:4163 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:4164 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:4165 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:4166 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4167 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:4168 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:4169 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:4170 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:4171 steps:50 total reward:-1.9800000000000004 epsilon:0.00998645168764533
episode:4172 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:4173 steps:4 total reward:-1.06 epsilon:0.00998645168764533
episode:4174 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4175 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4176 steps:80 total reward:-0.580000000000001 epsilon:0.00998645168764533
episode:4177 steps:87 total reward:-2.720000000000001 epsilon:0.00998645168764533
episode:4178 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:4179 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4180 steps:43 total reward:-1.8400000000000003 epsilon:0.00998645168764533
episode:4181 steps:58 total reward:-2.1400000000000006 epsilon:0.00998645168764533
episode:4182 steps:43 total reward:-1.8400000000000003 epsilon:0.00998645168764533
episode:4183 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:4184 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:4185 steps:45 total reward:-1.8800000000000003 epsilon:0.00998645168764533
episode:4186 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:4187 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:4188 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:4189 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:4190 steps:68 total reward:-2.3400000000000007 epsilon:0.00998645168764533
episode:4191 steps:76 total reward:-0.5000000000000009 epsilon:0.00998645168764533
episode:4192 steps:49 total reward:-1.9600000000000004 epsilon:0.00998645168764533
episode:4193 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4194 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:4195 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:4196 steps:79 total reward:-0.5600000000000009 epsilon:0.00998645168764533
episode:4197 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:4198 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:4199 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:4200 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:4201 steps:88 total reward:-2.740000000000001 epsilon:0.00998645168764533
episode:4202 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:4203 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4204 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:4205 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:4206 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:4207 steps:74 total reward:-2.460000000000001 epsilon:0.00998645168764533
episode:4208 steps:100 total reward:-0.9800000000000013 epsilon:0.00998645168764533
episode:4209 steps:55 total reward:-2.0800000000000005 epsilon:0.00998645168764533
episode:4210 steps:53 total reward:-2.0400000000000005 epsilon:0.00998645168764533
episode:4211 steps:39 total reward:-1.7600000000000002 epsilon:0.00998645168764533
episode:4212 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4213 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:4214 steps:97 total reward:-2.9200000000000013 epsilon:0.00998645168764533
episode:4215 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:4216 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:4217 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:4218 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:4219 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:4220 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:4221 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4222 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:4223 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:4224 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:4225 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:4226 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4227 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:4228 steps:36 total reward:-1.7000000000000002 epsilon:0.00998645168764533
episode:4229 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:4230 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:4231 steps:83 total reward:-2.640000000000001 epsilon:0.00998645168764533
episode:4232 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:4233 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:4234 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:4235 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:4236 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:4237 steps:3 total reward:-1.04 epsilon:0.00998645168764533
episode:4238 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:4239 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:4240 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:4241 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:4242 steps:48 total reward:-1.9400000000000004 epsilon:0.00998645168764533
episode:4243 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:4244 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:4245 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:4246 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:4247 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:4248 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4249 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:4250 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:4251 steps:63 total reward:-2.2400000000000007 epsilon:0.00998645168764533
episode:4252 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4253 steps:83 total reward:-0.640000000000001 epsilon:0.00998645168764533
episode:4254 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:4255 steps:60 total reward:-2.1800000000000006 epsilon:0.00998645168764533
episode:4256 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:4257 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:4258 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:4259 steps:38 total reward:-1.7400000000000002 epsilon:0.00998645168764533
episode:4260 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:4261 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:4262 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:4263 steps:98 total reward:-0.9400000000000013 epsilon:0.00998645168764533
episode:4264 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:4265 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:4266 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:4267 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:4268 steps:98 total reward:-0.9400000000000013 epsilon:0.00998645168764533
episode:4269 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:4270 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:4271 steps:89 total reward:-0.7600000000000011 epsilon:0.00998645168764533
episode:4272 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:4273 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4274 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:4275 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:4276 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:4277 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4278 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:4279 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:4280 steps:99 total reward:-0.9600000000000013 epsilon:0.00998645168764533
episode:4281 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:4282 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:4283 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:4284 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:4285 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:4286 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:4287 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:4288 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4289 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4290 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:4291 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:4292 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:4293 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:4294 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:4295 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:4296 steps:94 total reward:-0.8600000000000012 epsilon:0.00998645168764533
episode:4297 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:4298 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:4299 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4300 steps:61 total reward:-2.2000000000000006 epsilon:0.00998645168764533
episode:4301 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:4302 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:4303 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:4304 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:4305 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:4306 steps:60 total reward:-0.1800000000000006 epsilon:0.00998645168764533
episode:4307 steps:54 total reward:-2.0600000000000005 epsilon:0.00998645168764533
episode:4308 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:4309 steps:74 total reward:-0.46000000000000085 epsilon:0.00998645168764533
episode:4310 steps:90 total reward:-0.7800000000000011 epsilon:0.00998645168764533
episode:4311 steps:32 total reward:-1.62 epsilon:0.00998645168764533
episode:4312 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:4313 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:4314 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:4315 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:4316 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4317 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:4318 steps:79 total reward:-2.560000000000001 epsilon:0.00998645168764533
episode:4319 steps:59 total reward:-2.1600000000000006 epsilon:0.00998645168764533
episode:4320 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4321 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4322 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:4323 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:4324 steps:77 total reward:-0.5200000000000009 epsilon:0.00998645168764533
episode:4325 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:4326 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:4327 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:4328 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:4329 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:4330 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:4331 steps:78 total reward:-0.5400000000000009 epsilon:0.00998645168764533
episode:4332 steps:66 total reward:-2.3000000000000007 epsilon:0.00998645168764533
episode:4333 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:4334 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:4335 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:4336 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:4337 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4338 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:4339 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:4340 steps:32 total reward:-1.62 epsilon:0.00998645168764533
episode:4341 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:4342 steps:72 total reward:-2.420000000000001 epsilon:0.00998645168764533
episode:4343 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:4344 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4345 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4346 steps:69 total reward:-2.3600000000000008 epsilon:0.00998645168764533
episode:4347 steps:4 total reward:-1.06 epsilon:0.00998645168764533
episode:4348 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:4349 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:4350 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:4351 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4352 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:4353 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:4354 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:4355 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:4356 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:4357 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:4358 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:4359 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:4360 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:4361 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:4362 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:4363 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:4364 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:4365 steps:11 total reward:-1.2 epsilon:0.00998645168764533
episode:4366 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:4367 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:4368 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:4369 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4370 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:4371 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:4372 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:4373 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:4374 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:4375 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:4376 steps:77 total reward:-2.520000000000001 epsilon:0.00998645168764533
episode:4377 steps:71 total reward:-2.400000000000001 epsilon:0.00998645168764533
episode:4378 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:4379 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4380 steps:77 total reward:-2.520000000000001 epsilon:0.00998645168764533
episode:4381 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:4382 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:4383 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4384 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:4385 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:4386 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:4387 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:4388 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:4389 steps:74 total reward:-2.460000000000001 epsilon:0.00998645168764533
episode:4390 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:4391 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:4392 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:4393 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:4394 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:4395 steps:74 total reward:-0.46000000000000085 epsilon:0.00998645168764533
episode:4396 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:4397 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:4398 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:4399 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:4400 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:4401 steps:73 total reward:-2.440000000000001 epsilon:0.00998645168764533
episode:4402 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:4403 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:4404 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:4405 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:4406 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:4407 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:4408 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:4409 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:4410 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:4411 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4412 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:4413 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:4414 steps:53 total reward:-0.04000000000000048 epsilon:0.00998645168764533
episode:4415 steps:75 total reward:-0.48000000000000087 epsilon:0.00998645168764533
episode:4416 steps:88 total reward:-0.7400000000000011 epsilon:0.00998645168764533
episode:4417 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:4418 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:4419 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:4420 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:4421 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:4422 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:4423 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4424 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4425 steps:41 total reward:-1.8000000000000003 epsilon:0.00998645168764533
episode:4426 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4427 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:4428 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4429 steps:77 total reward:-0.5200000000000009 epsilon:0.00998645168764533
episode:4430 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4431 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4432 steps:62 total reward:-0.22000000000000064 epsilon:0.00998645168764533
episode:4433 steps:34 total reward:-1.6600000000000001 epsilon:0.00998645168764533
episode:4434 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:4435 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:4436 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:4437 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:4438 steps:93 total reward:-0.8400000000000012 epsilon:0.00998645168764533
episode:4439 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:4440 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:4441 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:4442 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:4443 steps:40 total reward:-1.7800000000000002 epsilon:0.00998645168764533
episode:4444 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:4445 steps:88 total reward:-0.7400000000000011 epsilon:0.00998645168764533
episode:4446 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:4447 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4448 steps:81 total reward:-0.600000000000001 epsilon:0.00998645168764533
episode:4449 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:4450 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:4451 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4452 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:4453 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4454 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4455 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:4456 steps:39 total reward:-1.7600000000000002 epsilon:0.00998645168764533
episode:4457 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:4458 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4459 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:4460 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:4461 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:4462 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:4463 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:4464 steps:82 total reward:-0.620000000000001 epsilon:0.00998645168764533
episode:4465 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:4466 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:4467 steps:56 total reward:-2.1000000000000005 epsilon:0.00998645168764533
episode:4468 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:4469 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4470 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4471 steps:78 total reward:-0.5400000000000009 epsilon:0.00998645168764533
episode:4472 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4473 steps:83 total reward:-0.640000000000001 epsilon:0.00998645168764533
episode:4474 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:4475 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4476 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:4477 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:4478 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4479 steps:84 total reward:-0.660000000000001 epsilon:0.00998645168764533
episode:4480 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:4481 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:4482 steps:45 total reward:-1.8800000000000003 epsilon:0.00998645168764533
episode:4483 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:4484 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4485 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:4486 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:4487 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:4488 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:4489 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:4490 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:4491 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:4492 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:4493 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4494 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:4495 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:4496 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4497 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4498 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:4499 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:4500 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:4501 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:4502 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:4503 steps:100 total reward:-0.9800000000000013 epsilon:0.00998645168764533
episode:4504 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:4505 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:4506 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:4507 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:4508 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:4509 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:4510 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4511 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:4512 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4513 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4514 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4515 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:4516 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4517 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:4518 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:4519 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:4520 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:4521 steps:72 total reward:-0.4200000000000008 epsilon:0.00998645168764533
episode:4522 steps:53 total reward:-0.04000000000000048 epsilon:0.00998645168764533
episode:4523 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:4524 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:4525 steps:53 total reward:-0.04000000000000048 epsilon:0.00998645168764533
episode:4526 steps:48 total reward:-1.9400000000000004 epsilon:0.00998645168764533
episode:4527 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:4528 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:4529 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4530 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:4531 steps:91 total reward:-0.8000000000000012 epsilon:0.00998645168764533
episode:4532 steps:92 total reward:-0.8200000000000012 epsilon:0.00998645168764533
episode:4533 steps:53 total reward:-0.04000000000000048 epsilon:0.00998645168764533
episode:4534 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:4535 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:4536 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4537 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:4538 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:4539 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:4540 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:4541 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:4542 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:4543 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:4544 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:4545 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:4546 steps:51 total reward:-4.440892098500626e-16 epsilon:0.00998645168764533
episode:4547 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:4548 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:4549 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:4550 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:4551 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:4552 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:4553 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:4554 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4555 steps:78 total reward:-2.540000000000001 epsilon:0.00998645168764533
episode:4556 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:4557 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:4558 steps:87 total reward:-2.720000000000001 epsilon:0.00998645168764533
episode:4559 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:4560 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:4561 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4562 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:4563 steps:82 total reward:-2.620000000000001 epsilon:0.00998645168764533
episode:4564 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:4565 steps:31 total reward:-1.6 epsilon:0.00998645168764533
episode:4566 steps:55 total reward:-2.0800000000000005 epsilon:0.00998645168764533
episode:4567 steps:93 total reward:-0.8400000000000012 epsilon:0.00998645168764533
episode:4568 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:4569 steps:65 total reward:-0.2800000000000007 epsilon:0.00998645168764533
episode:4570 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:4571 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4572 steps:74 total reward:-0.46000000000000085 epsilon:0.00998645168764533
episode:4573 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:4574 steps:35 total reward:-1.6800000000000002 epsilon:0.00998645168764533
episode:4575 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4576 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4577 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:4578 steps:75 total reward:-0.48000000000000087 epsilon:0.00998645168764533
episode:4579 steps:2 total reward:-1.02 epsilon:0.00998645168764533
episode:4580 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4581 steps:64 total reward:-2.2600000000000007 epsilon:0.00998645168764533
episode:4582 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:4583 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:4584 steps:83 total reward:-0.640000000000001 epsilon:0.00998645168764533
episode:4585 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:4586 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:4587 steps:44 total reward:0.13999999999999957 epsilon:0.00998645168764533
episode:4588 steps:79 total reward:-0.5600000000000009 epsilon:0.00998645168764533
episode:4589 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:4590 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4591 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:4592 steps:78 total reward:-0.5400000000000009 epsilon:0.00998645168764533
episode:4593 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:4594 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:4595 steps:81 total reward:-0.600000000000001 epsilon:0.00998645168764533
episode:4596 steps:78 total reward:-0.5400000000000009 epsilon:0.00998645168764533
episode:4597 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:4598 steps:69 total reward:-2.3600000000000008 epsilon:0.00998645168764533
episode:4599 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:4600 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:4601 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:4602 steps:55 total reward:-2.0800000000000005 epsilon:0.00998645168764533
episode:4603 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:4604 steps:91 total reward:-0.8000000000000012 epsilon:0.00998645168764533
episode:4605 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:4606 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:4607 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:4608 steps:46 total reward:-1.9000000000000004 epsilon:0.00998645168764533
episode:4609 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4610 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4611 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:4612 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:4613 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:4614 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:4615 steps:69 total reward:-0.36000000000000076 epsilon:0.00998645168764533
episode:4616 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:4617 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:4618 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:4619 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:4620 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:4621 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:4622 steps:84 total reward:-0.660000000000001 epsilon:0.00998645168764533
episode:4623 steps:77 total reward:-0.5200000000000009 epsilon:0.00998645168764533
episode:4624 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4625 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:4626 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:4627 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:4628 steps:100 total reward:-0.9800000000000013 epsilon:0.00998645168764533
episode:4629 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:4630 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4631 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4632 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:4633 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4634 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:4635 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:4636 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:4637 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:4638 steps:50 total reward:-1.9800000000000004 epsilon:0.00998645168764533
episode:4639 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:4640 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:4641 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4642 steps:78 total reward:-0.5400000000000009 epsilon:0.00998645168764533
episode:4643 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4644 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:4645 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:4646 steps:91 total reward:-2.800000000000001 epsilon:0.00998645168764533
episode:4647 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4648 steps:61 total reward:-0.20000000000000062 epsilon:0.00998645168764533
episode:4649 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:4650 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:4651 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:4652 steps:76 total reward:-2.500000000000001 epsilon:0.00998645168764533
episode:4653 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4654 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:4655 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4656 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:4657 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:4658 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:4659 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4660 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:4661 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:4662 steps:72 total reward:-2.420000000000001 epsilon:0.00998645168764533
episode:4663 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:4664 steps:56 total reward:-2.1000000000000005 epsilon:0.00998645168764533
episode:4665 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4666 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:4667 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:4668 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:4669 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:4670 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4671 steps:58 total reward:-2.1400000000000006 epsilon:0.00998645168764533
episode:4672 steps:93 total reward:-2.840000000000001 epsilon:0.00998645168764533
episode:4673 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:4674 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:4675 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:4676 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:4677 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:4678 steps:54 total reward:-2.0600000000000005 epsilon:0.00998645168764533
episode:4679 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:4680 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:4681 steps:64 total reward:-2.2600000000000007 epsilon:0.00998645168764533
episode:4682 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4683 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4684 steps:44 total reward:-1.8600000000000003 epsilon:0.00998645168764533
episode:4685 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:4686 steps:65 total reward:-2.2800000000000007 epsilon:0.00998645168764533
episode:4687 steps:39 total reward:-1.7600000000000002 epsilon:0.00998645168764533
episode:4688 steps:65 total reward:-0.2800000000000007 epsilon:0.00998645168764533
episode:4689 steps:92 total reward:-2.820000000000001 epsilon:0.00998645168764533
episode:4690 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:4691 steps:83 total reward:-0.640000000000001 epsilon:0.00998645168764533
episode:4692 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:4693 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:4694 steps:83 total reward:-0.640000000000001 epsilon:0.00998645168764533
episode:4695 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:4696 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:4697 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:4698 steps:90 total reward:-2.780000000000001 epsilon:0.00998645168764533
episode:4699 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:4700 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:4701 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4702 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:4703 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:4704 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:4705 steps:58 total reward:-2.1400000000000006 epsilon:0.00998645168764533
episode:4706 steps:33 total reward:0.35999999999999976 epsilon:0.00998645168764533
episode:4707 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:4708 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:4709 steps:83 total reward:-0.640000000000001 epsilon:0.00998645168764533
episode:4710 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:4711 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:4712 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4713 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:4714 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:4715 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:4716 steps:95 total reward:-0.8800000000000012 epsilon:0.00998645168764533
episode:4717 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:4718 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4719 steps:81 total reward:-2.600000000000001 epsilon:0.00998645168764533
episode:4720 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:4721 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:4722 steps:45 total reward:-1.8800000000000003 epsilon:0.00998645168764533
episode:4723 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:4724 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4725 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:4726 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:4727 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:4728 steps:69 total reward:-0.36000000000000076 epsilon:0.00998645168764533
episode:4729 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:4730 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:4731 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4732 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:4733 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:4734 steps:70 total reward:-0.3800000000000008 epsilon:0.00998645168764533
episode:4735 steps:83 total reward:-0.640000000000001 epsilon:0.00998645168764533
episode:4736 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:4737 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:4738 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4739 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:4740 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:4741 steps:42 total reward:-1.8200000000000003 epsilon:0.00998645168764533
episode:4742 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:4743 steps:55 total reward:-2.0800000000000005 epsilon:0.00998645168764533
episode:4744 steps:44 total reward:-1.8600000000000003 epsilon:0.00998645168764533
episode:4745 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:4746 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4747 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4748 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:4749 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:4750 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:4751 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:4752 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:4753 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:4754 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:4755 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:4756 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:4757 steps:66 total reward:-2.3000000000000007 epsilon:0.00998645168764533
episode:4758 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:4759 steps:90 total reward:-0.7800000000000011 epsilon:0.00998645168764533
episode:4760 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4761 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:4762 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:4763 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:4764 steps:66 total reward:-0.3000000000000007 epsilon:0.00998645168764533
episode:4765 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4766 steps:26 total reward:-1.5 epsilon:0.00998645168764533
episode:4767 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4768 steps:68 total reward:-0.34000000000000075 epsilon:0.00998645168764533
episode:4769 steps:85 total reward:-0.680000000000001 epsilon:0.00998645168764533
episode:4770 steps:43 total reward:-1.8400000000000003 epsilon:0.00998645168764533
episode:4771 steps:87 total reward:-0.7200000000000011 epsilon:0.00998645168764533
episode:4772 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:4773 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:4774 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:4775 steps:79 total reward:-0.5600000000000009 epsilon:0.00998645168764533
episode:4776 steps:80 total reward:-2.580000000000001 epsilon:0.00998645168764533
episode:4777 steps:7 total reward:0.88 epsilon:0.00998645168764533
episode:4778 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:4779 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:4780 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:4781 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:4782 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:4783 steps:6 total reward:0.9 epsilon:0.00998645168764533
episode:4784 steps:35 total reward:0.31999999999999973 epsilon:0.00998645168764533
episode:4785 steps:41 total reward:0.19999999999999962 epsilon:0.00998645168764533
episode:4786 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4787 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:4788 steps:50 total reward:-1.9800000000000004 epsilon:0.00998645168764533
episode:4789 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:4790 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:4791 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:4792 steps:7 total reward:-1.12 epsilon:0.00998645168764533
episode:4793 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:4794 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:4795 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:4796 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4797 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4798 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4799 steps:39 total reward:-1.7600000000000002 epsilon:0.00998645168764533
episode:4800 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:4801 steps:15 total reward:-1.28 epsilon:0.00998645168764533
episode:4802 steps:68 total reward:-2.3400000000000007 epsilon:0.00998645168764533
episode:4803 steps:58 total reward:-0.14000000000000057 epsilon:0.00998645168764533
episode:4804 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:4805 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4806 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:4807 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:4808 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4809 steps:11 total reward:0.8 epsilon:0.00998645168764533
episode:4810 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4811 steps:48 total reward:0.0599999999999995 epsilon:0.00998645168764533
episode:4812 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:4813 steps:35 total reward:-1.6800000000000002 epsilon:0.00998645168764533
episode:4814 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:4815 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:4816 steps:49 total reward:0.03999999999999948 epsilon:0.00998645168764533
episode:4817 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:4818 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4819 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:4820 steps:86 total reward:-0.7000000000000011 epsilon:0.00998645168764533
episode:4821 steps:2 total reward:-1.02 epsilon:0.00998645168764533
episode:4822 steps:81 total reward:-2.600000000000001 epsilon:0.00998645168764533
episode:4823 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:4824 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4825 steps:21 total reward:0.5999999999999999 epsilon:0.00998645168764533
episode:4826 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:4827 steps:64 total reward:-0.2600000000000007 epsilon:0.00998645168764533
episode:4828 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:4829 steps:58 total reward:-2.1400000000000006 epsilon:0.00998645168764533
episode:4830 steps:55 total reward:-2.0800000000000005 epsilon:0.00998645168764533
episode:4831 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:4832 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:4833 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:4834 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:4835 steps:30 total reward:-1.58 epsilon:0.00998645168764533
episode:4836 steps:48 total reward:-1.9400000000000004 epsilon:0.00998645168764533
episode:4837 steps:73 total reward:-0.44000000000000083 epsilon:0.00998645168764533
episode:4838 steps:25 total reward:-1.4800000000000002 epsilon:0.00998645168764533
episode:4839 steps:58 total reward:-2.1400000000000006 epsilon:0.00998645168764533
episode:4840 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:4841 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:4842 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:4843 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:4844 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:4845 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:4846 steps:19 total reward:-1.36 epsilon:0.00998645168764533
episode:4847 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:4848 steps:39 total reward:-1.7600000000000002 epsilon:0.00998645168764533
episode:4849 steps:57 total reward:-0.12000000000000055 epsilon:0.00998645168764533
episode:4850 steps:70 total reward:-2.380000000000001 epsilon:0.00998645168764533
episode:4851 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:4852 steps:20 total reward:0.6199999999999999 epsilon:0.00998645168764533
episode:4853 steps:39 total reward:-1.7600000000000002 epsilon:0.00998645168764533
episode:4854 steps:28 total reward:-1.54 epsilon:0.00998645168764533
episode:4855 steps:40 total reward:-1.7800000000000002 epsilon:0.00998645168764533
episode:4856 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:4857 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:4858 steps:18 total reward:-1.34 epsilon:0.00998645168764533
episode:4859 steps:37 total reward:-1.7200000000000002 epsilon:0.00998645168764533
episode:4860 steps:83 total reward:-0.640000000000001 epsilon:0.00998645168764533
episode:4861 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:4862 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:4863 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4864 steps:63 total reward:-2.2400000000000007 epsilon:0.00998645168764533
episode:4865 steps:27 total reward:-1.52 epsilon:0.00998645168764533
episode:4866 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
episode:4867 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:4868 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4869 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:4870 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:4871 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4872 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:4873 steps:98 total reward:-2.9400000000000013 epsilon:0.00998645168764533
episode:4874 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:4875 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:4876 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:4877 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:4878 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:4879 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4880 steps:38 total reward:0.2599999999999997 epsilon:0.00998645168764533
episode:4881 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4882 steps:10 total reward:-1.18 epsilon:0.00998645168764533
episode:4883 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:4884 steps:38 total reward:-1.7400000000000002 epsilon:0.00998645168764533
episode:4885 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:4886 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:4887 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4888 steps:84 total reward:-0.660000000000001 epsilon:0.00998645168764533
episode:4889 steps:29 total reward:-1.56 epsilon:0.00998645168764533
episode:4890 steps:71 total reward:-0.4000000000000008 epsilon:0.00998645168764533
episode:4891 steps:44 total reward:-1.8600000000000003 epsilon:0.00998645168764533
episode:4892 steps:45 total reward:0.11999999999999955 epsilon:0.00998645168764533
episode:4893 steps:12 total reward:-1.22 epsilon:0.00998645168764533
episode:4894 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:4895 steps:23 total reward:-1.4400000000000002 epsilon:0.00998645168764533
episode:4896 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:4897 steps:16 total reward:-1.3 epsilon:0.00998645168764533
episode:4898 steps:5 total reward:-1.08 epsilon:0.00998645168764533
episode:4899 steps:42 total reward:0.1799999999999996 epsilon:0.00998645168764533
episode:4900 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:4901 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4902 steps:40 total reward:0.21999999999999964 epsilon:0.00998645168764533
episode:4903 steps:56 total reward:-0.10000000000000053 epsilon:0.00998645168764533
episode:4904 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:4905 steps:95 total reward:-0.8800000000000012 epsilon:0.00998645168764533
episode:4906 steps:65 total reward:-0.2800000000000007 epsilon:0.00998645168764533
episode:4907 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:4908 steps:50 total reward:0.019999999999999463 epsilon:0.00998645168764533
episode:4909 steps:84 total reward:-0.660000000000001 epsilon:0.00998645168764533
episode:4910 steps:82 total reward:-0.620000000000001 epsilon:0.00998645168764533
episode:4911 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4912 steps:30 total reward:0.4199999999999998 epsilon:0.00998645168764533
episode:4913 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:4914 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:4915 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:4916 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:4917 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4918 steps:59 total reward:-0.1600000000000006 epsilon:0.00998645168764533
episode:4919 steps:47 total reward:-1.9200000000000004 epsilon:0.00998645168764533
episode:4920 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:4921 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4922 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:4923 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4924 steps:19 total reward:0.6399999999999999 epsilon:0.00998645168764533
episode:4925 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:4926 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4927 steps:24 total reward:0.5399999999999998 epsilon:0.00998645168764533
episode:4928 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:4929 steps:17 total reward:-1.32 epsilon:0.00998645168764533
episode:4930 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:4931 steps:10 total reward:0.8200000000000001 epsilon:0.00998645168764533
episode:4932 steps:52 total reward:-0.020000000000000462 epsilon:0.00998645168764533
episode:4933 steps:39 total reward:0.23999999999999966 epsilon:0.00998645168764533
episode:4934 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:4935 steps:54 total reward:-0.0600000000000005 epsilon:0.00998645168764533
episode:4936 steps:39 total reward:-1.7600000000000002 epsilon:0.00998645168764533
episode:4937 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:4938 steps:8 total reward:-1.1400000000000001 epsilon:0.00998645168764533
episode:4939 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4940 steps:6 total reward:-1.1 epsilon:0.00998645168764533
episode:4941 steps:16 total reward:0.7 epsilon:0.00998645168764533
episode:4942 steps:33 total reward:-1.6400000000000001 epsilon:0.00998645168764533
episode:4943 steps:74 total reward:-2.460000000000001 epsilon:0.00998645168764533
episode:4944 steps:82 total reward:-2.620000000000001 epsilon:0.00998645168764533
episode:4945 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:4946 steps:12 total reward:0.78 epsilon:0.00998645168764533
episode:4947 steps:47 total reward:0.07999999999999952 epsilon:0.00998645168764533
episode:4948 steps:52 total reward:-2.0200000000000005 epsilon:0.00998645168764533
episode:4949 steps:24 total reward:-1.4600000000000002 epsilon:0.00998645168764533
episode:4950 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:4951 steps:54 total reward:-2.0600000000000005 epsilon:0.00998645168764533
episode:4952 steps:67 total reward:-0.32000000000000073 epsilon:0.00998645168764533
episode:4953 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:4954 steps:26 total reward:0.4999999999999999 epsilon:0.00998645168764533
episode:4955 steps:69 total reward:-2.3600000000000008 epsilon:0.00998645168764533
episode:4956 steps:14 total reward:-1.26 epsilon:0.00998645168764533
episode:4957 steps:40 total reward:-1.7800000000000002 epsilon:0.00998645168764533
episode:4958 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
episode:4959 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:4960 steps:31 total reward:0.3999999999999998 epsilon:0.00998645168764533
episode:4961 steps:20 total reward:-1.3800000000000001 epsilon:0.00998645168764533
episode:4962 steps:55 total reward:-0.08000000000000052 epsilon:0.00998645168764533
episode:4963 steps:29 total reward:0.43999999999999984 epsilon:0.00998645168764533
episode:4964 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4965 steps:56 total reward:-2.1000000000000005 epsilon:0.00998645168764533
episode:4966 steps:14 total reward:0.74 epsilon:0.00998645168764533
episode:4967 steps:65 total reward:-0.2800000000000007 epsilon:0.00998645168764533
episode:4968 steps:46 total reward:0.09999999999999953 epsilon:0.00998645168764533
episode:4969 steps:9 total reward:0.84 epsilon:0.00998645168764533
episode:4970 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4971 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:4972 steps:9 total reward:-1.16 epsilon:0.00998645168764533
episode:4973 steps:65 total reward:-2.2800000000000007 epsilon:0.00998645168764533
episode:4974 steps:25 total reward:0.5199999999999998 epsilon:0.00998645168764533
episode:4975 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:4976 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:4977 steps:13 total reward:-1.24 epsilon:0.00998645168764533
episode:4978 steps:99 total reward:-0.9600000000000013 epsilon:0.00998645168764533
episode:4979 steps:34 total reward:0.33999999999999975 epsilon:0.00998645168764533
episode:4980 steps:13 total reward:0.76 epsilon:0.00998645168764533
episode:4981 steps:18 total reward:0.6599999999999999 epsilon:0.00998645168764533
episode:4982 steps:43 total reward:0.1599999999999996 epsilon:0.00998645168764533
episode:4983 steps:28 total reward:0.45999999999999985 epsilon:0.00998645168764533
episode:4984 steps:22 total reward:-1.4200000000000002 epsilon:0.00998645168764533
episode:4985 steps:27 total reward:0.47999999999999987 epsilon:0.00998645168764533
episode:4986 steps:21 total reward:-1.4000000000000001 epsilon:0.00998645168764533
episode:4987 steps:76 total reward:-0.5000000000000009 epsilon:0.00998645168764533
episode:4988 steps:63 total reward:-2.2400000000000007 epsilon:0.00998645168764533
episode:4989 steps:65 total reward:-0.2800000000000007 epsilon:0.00998645168764533
episode:4990 steps:81 total reward:-0.600000000000001 epsilon:0.00998645168764533
episode:4991 steps:17 total reward:0.6799999999999999 epsilon:0.00998645168764533
episode:4992 steps:15 total reward:0.72 epsilon:0.00998645168764533
episode:4993 steps:32 total reward:0.3799999999999998 epsilon:0.00998645168764533
episode:4994 steps:8 total reward:0.86 epsilon:0.00998645168764533
episode:4995 steps:22 total reward:0.5799999999999998 epsilon:0.00998645168764533
episode:4996 steps:63 total reward:-0.24000000000000066 epsilon:0.00998645168764533
episode:4997 steps:100 total reward:-2.9800000000000013 epsilon:0.00998645168764533
[2017-07-16 15:19:37,935] Starting new video recorder writing to C:\Users\Abdul\Documents\My Projects\Deep learning nano degree\my-experiments\reinforcement learning\monitor\openaigym.video.2.12772.video005000.json
episode:4998 steps:36 total reward:0.2999999999999997 epsilon:0.00998645168764533
episode:4999 steps:23 total reward:0.5599999999999998 epsilon:0.00998645168764533
episode:5000 steps:37 total reward:0.2799999999999997 epsilon:0.00998645168764533
In [30]:
import matplotlib.pyplot as plt
%matplotlib inline
def running_mean(x, N):
cumsum = np.cumsum(np.insert(x, 0, 0))
return (cumsum[N:] - cumsum[:-N]) / N
smoothed_rews = running_mean(reward_list, 10)
plt.plot(reward_list, color='grey', alpha=0.3)
plt.plot(smoothed_rews)
Out[30]:
[<matplotlib.lines.Line2D at 0x27268a2d198>]
In [29]:
env.close()
gym.upload('./monitor', api_key='')
[2017-07-16 15:20:32,132] [FrozenLake-v0] Uploading 5000 episodes of training data
[2017-07-16 15:20:35,422] [FrozenLake-v0] Uploading videos of 15 training episodes (1706 bytes)
[2017-07-16 15:20:36,031] [FrozenLake-v0] Creating evaluation object from ./monitor with learning curve and training video
[2017-07-16 15:20:36,641]
****************************************************
You successfully uploaded your evaluation on FrozenLake-v0 to
OpenAI Gym! You can find it at:
https://gym.openai.com/evaluations/eval_i7IBk5tTPOFM0a714aFrg
****************************************************
Content source: y2ee201/Deep-Learning-Nanodegree
Similar notebooks: