演员-评论家模式永远不会收敛

Question

>我正在尝试使用Keras和Tensorflow实现Actor-Critic。 但是，它永远不会收敛，我不知道为什么。我降低了学习率，但它没有改变。

代码是python3.5.1和tensorflow1.2.1

import gym
import itertools
import matplotlib
import numpy as np
import sys
import tensorflow as tf
import collections
from keras.models import Model
from keras.layers import Input, Dense
from keras.utils import to_categorical
from keras import backend as K
env = gym.make('CartPole-v0')
NUM_STATE = env.env.observation_space.shape[0]
NUM_ACTIONS = env.env.action_space.n
LEARNING_RATE = 0.0005
TARGET_AVG_REWARD = 195
class Actor_Critic():
def __init__(self):
l_input = Input(shape=(NUM_STATE, ))
l_dense = Dense(16, activation='relu')(l_input)
## Policy Network
action_probs = Dense(NUM_ACTIONS, activation='softmax')(l_dense)
policy_network = Model(input=l_input, output=action_probs)
## Value Network
state_value = Dense(1, activation='linear')(l_dense)
value_network = Model(input=l_input, output=state_value)
graph = self._build_graph(policy_network, value_network)
self.state, self.action, self.target, self.action_probs, self.state_value, self.minimize, self.loss = graph
def _build_graph(self, policy_network, value_network):
state = tf.placeholder(tf.float32)
action = tf.placeholder(tf.float32, shape=(None, NUM_ACTIONS))
target = tf.placeholder(tf.float32, shape=(None))
action_probs = policy_network(state)
state_value = value_network(state)[0]
advantage = tf.stop_gradient(target) - state_value
log_prob = tf.log(tf.reduce_sum(action_probs * action, reduction_indices=1))
p_loss = -log_prob * advantage
v_loss = tf.reduce_mean(tf.square(advantage))
loss = p_loss + (0.5 * v_loss)
# optimizer = tf.train.RMSPropOptimizer(LEARNING_RATE, decay=.99)
optimizer = tf.train.AdamOptimizer(LEARNING_RATE)
minimize = optimizer.minimize(loss)
return state, action, target, action_probs, state_value, minimize, loss,
def predict_policy(self, sess, state):
return sess.run(self.action_probs, { self.state: [state] })
def predict_value(self, sess, state):
return sess.run(self.state_value, { self.state: [state] })
def update(self, sess, state, action, target):
feed_dict = {self.state:[state], self.target:target, self.action:to_categorical(action, NUM_ACTIONS)}
_, loss = sess.run([self.minimize, self.loss], feed_dict)
return loss

def train(env, sess, estimator, num_episodes, discount_factor=1.0):
Transition = collections.namedtuple("Transition", ["state", "action", "reward", "loss"])
last_100 = np.zeros(100)
for i_episode in range(num_episodes):
# Reset the environment and pick the fisrst action
state = env.reset()
episode = []
# One step in the environment
for t in itertools.count():
# Take a step
action_probs = estimator.predict_policy(sess, state)[0]
action = np.random.choice(np.arange(len(action_probs)), p=action_probs)
next_state, reward, done, _ = env.step(action)
target = reward + (0 if done else discount_factor * estimator.predict_value(sess, next_state))
# Update our policy estimator
loss = estimator.update(sess, state, action, target)
# Keep track of the transition
episode.append(Transition(state=state, action=action, reward=reward, loss=loss))
if done:
break
state = next_state
total_reward = sum(e.reward for e in episode)
last_100[i_episode % 100] = total_reward
last_100_avg = sum(last_100) / 100
total_loss = sum(e.loss for e in episode)
print('episode %s loss: %f reward: %f last 100: %f' % (i_episode, total_loss, total_reward, last_100_avg))
if last_100_avg >= TARGET_AVG_REWARD:
break
return
estimator = Actor_Critic()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
stats = train(env, sess, estimator, 2000, discount_factor=0.99)

这是开头的日志：(最后 100 是最近 100 集的平均奖励。它在前 100 集中自动增加，所以忽略它。

episode 0 loss: 17.662344 reward: 15.000000 last 100: 0.150000
episode 1 loss: 15.319713 reward: 13.000000 last 100: 0.280000
episode 2 loss: 38.097054 reward: 32.000000 last 100: 0.600000
episode 3 loss: 22.229492 reward: 19.000000 last 100: 0.790000
episode 4 loss: 31.027534 reward: 26.000000 last 100: 1.050000
episode 5 loss: 21.037663 reward: 18.000000 last 100: 1.230000
episode 6 loss: 18.750641 reward: 16.000000 last 100: 1.390000
episode 7 loss: 23.268227 reward: 20.000000 last 100: 1.590000
episode 8 loss: 27.251028 reward: 23.000000 last 100: 1.820000
episode 9 loss: 20.008078 reward: 17.000000 last 100: 1.990000
episode 10 loss: 28.213932 reward: 24.000000 last 100: 2.230000
episode 11 loss: 28.109922 reward: 23.000000 last 100: 2.460000
episode 12 loss: 25.068121 reward: 21.000000 last 100: 2.670000
episode 13 loss: 59.581238 reward: 50.000000 last 100: 3.170000
episode 14 loss: 26.618759 reward: 22.000000 last 100: 3.390000
episode 15 loss: 28.847467 reward: 24.000000 last 100: 3.630000
episode 16 loss: 22.534216 reward: 17.000000 last 100: 3.800000
episode 17 loss: 19.760979 reward: 15.000000 last 100: 3.950000
episode 18 loss: 31.018209 reward: 25.000000 last 100: 4.200000
episode 19 loss: 22.938683 reward: 16.000000 last 100: 4.360000
episode 20 loss: 30.372072 reward: 24.000000 last 100: 4.600000

500集之后，不仅没有好转，反而比开始更糟糕。

episode 501 loss: 97.043335 reward: 8.000000 last 100: 13.500000
episode 502 loss: 101.957603 reward: 11.000000 last 100: 13.510000
episode 503 loss: 100.277809 reward: 11.000000 last 100: 13.520000
episode 504 loss: 96.754257 reward: 9.000000 last 100: 13.510000
episode 505 loss: 99.436943 reward: 11.000000 last 100: 13.530000
episode 506 loss: 105.161621 reward: 16.000000 last 100: 13.580000
episode 507 loss: 65.993591 reward: 12.000000 last 100: 13.610000
episode 508 loss: 59.837429 reward: 9.000000 last 100: 13.600000
episode 509 loss: 92.478806 reward: 9.000000 last 100: 13.570000
episode 510 loss: 96.697289 reward: 14.000000 last 100: 13.620000
episode 511 loss: 94.611366 reward: 10.000000 last 100: 13.620000
episode 512 loss: 100.259460 reward: 15.000000 last 100: 13.680000
episode 513 loss: 88.776451 reward: 10.000000 last 100: 13.690000
episode 514 loss: 86.659203 reward: 9.000000 last 100: 13.700000
episode 515 loss: 105.494476 reward: 17.000000 last 100: 13.770000
episode 516 loss: 90.662186 reward: 12.000000 last 100: 13.770000
episode 517 loss: 90.777634 reward: 12.000000 last 100: 13.810000
episode 518 loss: 91.290558 reward: 14.000000 last 100: 13.860000
episode 519 loss: 94.902023 reward: 11.000000 last 100: 13.870000
episode 520 loss: 86.746582 reward: 12.000000 last 100: 13.900000

另一方面，普通的政策梯度确实收敛。

import gym
import itertools
import matplotlib
import numpy as np
import sys
import tensorflow as tf
import collections
from keras.models import Model
from keras.layers import Input, Dense
from keras.utils import to_categorical
from keras import backend as K
env = gym.make('CartPole-v0')
NUM_STATE = env.env.observation_space.shape[0]
NUM_ACTIONS = env.env.action_space.n
LEARNING_RATE = 0.0005
TARGET_AVG_REWARD = 195
class PolicyEstimator():
"""
Policy Function approximator. 
"""
def __init__(self):
l_input = Input(shape=(NUM_STATE, ))
l_dense = Dense(16, activation='relu')(l_input)
action_probs = Dense(NUM_ACTIONS, activation='softmax')(l_dense)
model = Model(inputs=[l_input], outputs=[action_probs])
self.state, self.action, self.target, self.action_probs, self.minimize, self.loss = self._build_graph(model)
def _build_graph(self, model):
state = tf.placeholder(tf.float32)
action = tf.placeholder(tf.float32, shape=(None, NUM_ACTIONS))
target = tf.placeholder(tf.float32, shape=(None))
action_probs = model(state)
log_prob = tf.log(tf.reduce_sum(action_probs * action, reduction_indices=1))
loss = -log_prob * target
# optimizer = tf.train.RMSPropOptimizer(LEARNING_RATE, decay=.99)
optimizer = tf.train.AdamOptimizer(LEARNING_RATE)
minimize = optimizer.minimize(loss)
return state, action, target, action_probs, minimize, loss
def predict(self, sess, state):
return sess.run(self.action_probs, { self.state: [state] })
def update(self, sess, state, action, target):
feed_dict = {self.state:[state], self.target:[target], self.action:to_categorical(action, NUM_ACTIONS)}
_, loss = sess.run([self.minimize, self.loss], feed_dict)
return loss

def train(env, sess, estimator_policy, num_episodes, discount_factor=1.0):
Transition = collections.namedtuple("Transition", ["state", "action", "reward"])
last_100 = np.zeros(100)
for i_episode in range(num_episodes):
# Reset the environment and pick the fisrst action
state = env.reset()
episode = []
# One step in the environment
for t in itertools.count():
# Take a step
action_probs = estimator_policy.predict(sess, state)[0]
action = np.random.choice(np.arange(len(action_probs)), p=action_probs)
next_state, reward, done, _ = env.step(action)
# Keep track of the transition
episode.append(Transition(state=state, action=action, reward=reward))
if done:
break
state = next_state
# Go through the episode and make policy updates
for t, transition in enumerate(episode):
# The return after this timestep
target = sum(discount_factor**i * t2.reward for i, t2 in enumerate(episode[t:]))
# Update our policy estimator
loss = estimator_policy.update(sess, transition.state, transition.action, target)
total_reward = sum(e.reward for e in episode)
last_100[i_episode % 100] = total_reward
last_100_avg = sum(last_100) / 100
print('episode %s reward: %f last 100: %f' % (i_episode, total_reward, last_100_avg))
if last_100_avg >= TARGET_AVG_REWARD:
break
return
policy_estimator = PolicyEstimator()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
stats = train(env, sess, policy_estimator, 2000, discount_factor=1.0)

参考代码

https://github.com/jaara/AI-blog/blob/master/CartPole-A3C.py

https://github.com/coreylynch/async-rl

任何帮助，不胜感激。

[更新]

我将_build_graph中的代码从

advantage = tf.stop_gradient(target) - state_value
log_prob = tf.log(tf.reduce_sum(action_probs * action, reduction_indices=1))
p_loss = -log_prob * advantage
v_loss = tf.reduce_mean(tf.square(advantage))
loss = p_loss + (0.5 * v_loss)

自

advantage = target - state_value
log_prob = tf.log(tf.reduce_sum(action_probs * action, reduction_indices=1))
p_loss = -log_prob * tf.stop_gradient(advantage)
v_loss = 0.5 * tf.reduce_mean(tf.square(advantage))
loss = p_loss + v_loss

它变得更好了，并达到了 200 奖励(最高(。然而，在4000集之后，它仍然没有达到195的平均水平。

Answer 1

第一个明显的事情是错误的梯度被阻止在优势中：

advantage = tf.stop_gradient(target) - state_value

应该是

advantage = target - tf.stop_gradient(state_value)

由于无论哪种方式都没有目标梯度(它是一个常量(，并且您想要实现的是策略梯度缺乏流经价值网络(基线(的梯度。基线有一个单独的损失(看起来不错(。

另一个可能的错误是减少损失的方式。你明确地呼唤reduce_mean v_loss，但从不呼唤p_loss。因此，缩放是关闭的，你的价值网络可能会学习得更慢(因为你在第一个 - 可能是时间 - 维度上平均(。

Answer 2

几个建议：

• 负奖励。你需要以某种方式"惩罚"终端状态。(例如，您可以使用if done: reward = -10对奖励进行硬编码。否则，批评者永远不会估计终端状态的负值。没有负面价值观，不良行为永远不会被阻止。
• 尽量减少损失。 您应该有两个minimize操作：一个用于参与者，一个用于评论家。 理想情况下，评论家的学习速度应该比演员快。