In [1]:
# This code creates a virtual display to draw game images on.
# If you are running locally, just ignore it
import os
if type(os.environ.get("DISPLAY")) is not str or len(os.environ.get("DISPLAY")) == 0:
!bash ../xvfb start
os.environ['DISPLAY'] = ':1'
In [2]:
import gym
import numpy as np, pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
env = gym.make("CartPole-v0")
# gym compatibility: unwrap TimeLimit
if hasattr(env,'env'):
env=env.env
env.reset()
n_actions = env.action_space.n
state_dim = env.observation_space.shape
plt.imshow(env.render("rgb_array"))
Out[2]:
For REINFORCE algorithm, we'll need a model that predicts action probabilities given states.
For numerical stability, please do not include the softmax layer into your network architecture.
We'll use softmax or log-softmax where appropriate.
In [3]:
import tensorflow as tf
tf.reset_default_graph()
# create input variables. We only need <s,a,R> for REINFORCE
states = tf.placeholder('float32', (None,)+state_dim, name="states")
actions = tf.placeholder('int32', name="action_ids")
cumulative_rewards = tf.placeholder('float32', name="cumulative_returns")
In [4]:
import keras
import keras.layers as L
#sess = tf.InteractiveSession()
#keras.backend.set_session(sess)
#<define network graph using raw tf or any deep learning library>
#network = keras.models.Sequential()
#network.add(L.InputLayer(state_dim))
#network.add(L.Dense(200, activation='relu'))
#network.add(L.Dense(200, activation='relu'))
#network.add(L.Dense(n_actions, activation='linear'))
network = keras.models.Sequential()
network.add(L.Dense(256, activation="relu", input_shape=state_dim, name="layer_1"))
network.add(L.Dense(n_actions, activation="linear", name="layer_2"))
print(network.summary())
#question: counting from the beginning of the model, the logits are in layer #9: model.layers[9].output
#logits = network.layers[2].output #<linear outputs (symbolic) of your network>
logits = network(states)
policy = tf.nn.softmax(logits)
log_policy = tf.nn.log_softmax(logits)
In [5]:
# utility function to pick action in one given state
def get_action_proba(s):
return policy.eval({states: [s]})[0]
We now need to define objective and update over policy gradient.
Our objective function is
$$ J \approx { 1 \over N } \sum _{s_i,a_i} \pi_\theta (a_i | s_i) \cdot G(s_i,a_i) $$Following the REINFORCE algorithm, we can define our objective as follows:
$$ \hat J \approx { 1 \over N } \sum _{s_i,a_i} log \pi_\theta (a_i | s_i) \cdot G(s_i,a_i) $$When you compute gradient of that function over network weights $ \theta $, it will become exactly the policy gradient.
In [6]:
# select log-probabilities for chosen actions, log pi(a_i|s_i)
indices = tf.stack([tf.range(tf.shape(log_policy)[0]), actions], axis=-1)
log_policy_for_actions = tf.gather_nd(log_policy, indices)
In [7]:
# REINFORCE objective function
# hint: you need to use log_policy_for_actions to get log probabilities for actions taken
J = tf.reduce_mean((log_policy_for_actions * cumulative_rewards), axis=-1)# <policy objective as in the last formula. Please use mean, not sum.>
In [8]:
# regularize with entropy
entropy = tf.reduce_mean(policy*log_policy) # <compute entropy. Don't forget the sign!>
In [9]:
# all network weights
all_weights = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES) #<a list of all trainable weights in your network>
# weight updates. maximizing J is same as minimizing -J. Adding negative entropy.
loss = -J - 0.1*entropy
update = tf.train.AdamOptimizer().minimize(loss, var_list=all_weights)
In [26]:
def get_cumulative_rewards(rewards, # rewards at each step
gamma=0.99 # discount for reward
):
"""
take a list of immediate rewards r(s,a) for the whole session
compute cumulative rewards R(s,a) (a.k.a. G(s,a) in Sutton '16)
R_t = r_t + gamma*r_{t+1} + gamma^2*r_{t+2} + ...
The simple way to compute cumulative rewards is to iterate from last to first time tick
and compute R_t = r_t + gamma*R_{t+1} recurrently
You must return an array/list of cumulative rewards with as many elements as in the initial rewards.
"""
#<your code here>
cumulative_rewards = np.zeros((len(rewards)))
cumulative_rewards[-1] = rewards[-1]
for t in range(len(rewards)-2, -1, -1):
cumulative_rewards[t] = rewards[t] + gamma * cumulative_rewards[t + 1]
return cumulative_rewards #< array of cumulative rewards>
In [27]:
assert len(get_cumulative_rewards(range(100))) == 100
assert np.allclose(get_cumulative_rewards([0, 0, 1, 0, 0, 1, 0], gamma=0.9),
[1.40049, 1.5561, 1.729, 0.81, 0.9, 1.0, 0.0])
assert np.allclose(get_cumulative_rewards([0, 0, 1, -2, 3, -4, 0], gamma=0.5),
[0.0625, 0.125, 0.25, -1.5, 1.0, -4.0, 0.0])
assert np.allclose(get_cumulative_rewards([0, 0, 1, 2, 3, 4, 0], gamma=0),
[0, 0, 1, 2, 3, 4, 0])
print("looks good!")
In [28]:
def train_step(_states, _actions, _rewards):
"""given full session, trains agent with policy gradient"""
_cumulative_rewards = get_cumulative_rewards(_rewards)
update.run({states: _states, actions: _actions,
cumulative_rewards: _cumulative_rewards})
In [41]:
def generate_session(t_max=1000):
"""play env with REINFORCE agent and train at the session end"""
# arrays to record session
states, actions, rewards = [], [], []
s = env.reset()
for t in range(t_max):
# action probabilities array aka pi(a|s)
action_probas = get_action_proba(s)
a = np.random.choice(a=len(action_probas), p=action_probas) #<pick random action using action_probas>
new_s, r, done, info = env.step(a)
# record session history to train later
states.append(s)
actions.append(a)
rewards.append(r)
s = new_s
if done:
break
train_step(states, actions, rewards)
# technical: return session rewards to print them later
return sum(rewards)
In [42]:
s = tf.InteractiveSession()
s.run(tf.global_variables_initializer())
for i in range(100):
rewards = [generate_session() for _ in range(100)] # generate new sessions
print("mean reward:%.3f" % (np.mean(rewards)))
if np.mean(rewards) > 300:
print("You Win!") # but you can train even further
break
In [43]:
# record sessions
import gym.wrappers
env = gym.wrappers.Monitor(gym.make("CartPole-v0"),
directory="videos", force=True)
sessions = [generate_session() for _ in range(100)]
env.close()
In [44]:
# show video
from IPython.display import HTML
import os
video_names = list(
filter(lambda s: s.endswith(".mp4"), os.listdir("./videos/")))
HTML("""
<video width="640" height="480" controls>
<source src="{}" type="video/mp4">
</video>
""".format("./videos/"+video_names[-1])) # this may or may not be _last_ video. Try other indices
Out[44]:
In [46]:
from submit import submit_cartpole
submit_cartpole(generate_session, "tonatiuh_rangel@hotmail.com", "Cecc5rcVxaVUYtsQ")
In [ ]:
# That's all, thank you for your attention!
# Not having enough? There's an actor-critic waiting for you in the honor section.
# But make sure you've seen the videos first.