参考Morvan文章和代码
简单介绍一下Actor-Critic算法,Actor-Critic算法是为了解决PC算法中每个episode更新神经网络这一缺陷而提出来的,它希望和Q-learning一样可以实现单步更新,所以引进了Critic。PC算法是走完整个episode后对策略更新,也就是对神经网络的参数进行更新,AC算法是让Critic在Actor每行动一次后指导Actor去更新自己的参数。具体代码实现如下:
代码
import numpy as np
import tensorflow as tf
import gym
np.random.seed(2)
tf.set_random_seed(2) # reproducible
# Superparameters
OUTPUT_GRAPH = False
MAX_EPISODE = 3000
DISPLAY_REWARD_THRESHOLD = 200 # renders environment if total episode reward is greater then this threshold
MAX_EP_STEPS = 1000 # maximum time step in one episode
RENDER = False # rendering wastes time
GAMMA = 0.9 # reward discount in TD error
LR_A = 0.001 # learning rate for actor
LR_C = 0.01 # learning rate for critic
env = gym.make('CartPole-v0')
env.seed(1) # reproducible
env = env.unwrapped
N_F = env.observation_space.shape[0]
N_A = env.action_space.n
class Actor(object):
def __init__(self, sess, n_features, n_actions, lr=0.001):
self.sess = sess
self.s = tf.placeholder(tf.float32, [1, n_features], "state")
self.a = tf.placeholder(tf.int32, None, "act")
self.td_error = tf.placeholder(tf.float32, None, "td_error") # TD_error
with tf.variable_scope('Actor'):
l1 = tf.layers.dense(
inputs=self.s,
units=20, # number of hidden units
activation=tf.nn.relu,
kernel_initializer=tf.random_normal_initializer(0., .1), # weights
bias_initializer=tf.constant_initializer(0.1), # biases
name='l1'
)
self.acts_prob = tf.layers.dense(
inputs=l1,
units=n_actions, # output units
activation=tf.nn.softmax, # get action probabilities
kernel_initializer=tf.random_normal_initializer(0., .1), # weights
bias_initializer=tf.constant_initializer(0.1), # biases
name='acts_prob'
)
with tf.variable_scope('exp_v'):
log_prob = tf.log(self.acts_prob[0, self.a])
self.exp_v = tf.reduce_mean(log_prob * self.td_error) # advantage (TD_error) guided loss
with tf.variable_scope('train'):
self.train_op = tf.train.AdamOptimizer(lr).minimize(-self.exp_v) # minimize(-exp_v) = maximize(exp_v)
def learn(self, s, a, td):
s = s[np.newaxis, :]
feed_dict = {self.s: s, self.a: a, self.td_error: td}
_, exp_v = self.sess.run([self.train_op, self.exp_v], feed_dict)
return exp_v
def choose_action(self, s):
s = s[np.newaxis, :]
probs = self.sess.run(self.acts_prob, {self.s: s}) # get probabilities for all actions
return np.random.choice(np.arange(probs.shape[1]), p=probs.ravel()) # return a int
class Critic(object):
def __init__(self, sess, n_features, lr=0.01):
self.sess = sess
self.s = tf.placeholder(tf.float32, [1, n_features], "state")
self.v_ = tf.placeholder(tf.float32, [1, 1], "v_next")
self.r = tf.placeholder(tf.float32, None, 'r')
with tf.variable_scope('Critic'):
l1 = tf.layers.dense(
inputs=self.s,
units=20, # number of hidden units
activation=tf.nn.relu, # None
# have to be linear to make sure the convergence of actor.
# But linear approximator seems hardly learns the correct Q.
kernel_initializer=tf.random_normal_initializer(0., .1), # weights
bias_initializer=tf.constant_initializer(0.1), # biases
name='l1'
)
self.v = tf.layers.dense(
inputs=l1,
units=1, # output units
activation=None,
kernel_initializer=tf.random_normal_initializer(0., .1), # weights
bias_initializer=tf.constant_initializer(0.1), # biases
name='V'
)
with tf.variable_scope('squared_TD_error'):
self.td_error = self.r + GAMMA * self.v_ - self.v
self.loss = tf.square(self.td_error) # TD_error = (r+gamma*V_next) - V_eval
with tf.variable_scope('train'):
self.train_op = tf.train.AdamOptimizer(lr).minimize(self.loss)
def learn(self, s, r, s_):
s, s_ = s[np.newaxis, :], s_[np.newaxis, :]
v_ = self.sess.run(self.v, {self.s: s_})
td_error, _ = self.sess.run([self.td_error, self.train_op],
{self.s: s, self.v_: v_, self.r: r})
return td_error
sess = tf.Session()
actor = Actor(sess, n_features=N_F, n_actions=N_A, lr=LR_A)
critic = Critic(sess, n_features=N_F, lr=LR_C) # we need a good teacher, so the teacher should learn faster than the actor
sess.run(tf.global_variables_initializer())
if OUTPUT_GRAPH:
tf.summary.FileWriter("logs/", sess.graph)
for i_episode in range(MAX_EPISODE):
s = env.reset()
t = 0
track_r = []
while True:
if RENDER:
env.render()
a = actor.choose_action(s)
s_, r, done, info = env.step(a)
if done:
r = -20
track_r.append(r)
td_error = critic.learn(s, r, s_) # gradient = grad[r + gamma * V(s_) - V(s)]
actor.learn(s, a, td_error) # true_gradient = grad[logPi(s,a) * td_error]
s = s_
t += 1
if done or t >= MAX_EP_STEPS:
ep_rs_sum = sum(track_r)
if 'running_reward' not in globals():
running_reward = ep_rs_sum
else:
running_reward = running_reward * 0.95 + ep_rs_sum * 0.05
if running_reward > DISPLAY_REWARD_THRESHOLD:
RENDER = True # rendering
print("episode:", i_episode, " reward:", int(running_reward))
break
理解
结合自己的理解,给出代码实现的结构图,如有错误欢迎指出讨论:
图中有两个神经网络,分别对应着Actor和Critic,具体的流程:Actor在状态S下,根据行动概率P做出行动A,得到神经网络R和S’的输出,将其输出反馈给Critic,经过Critic神经网络计算得出误差td_error(这个计算公式和Q-learning中的类似),误差用来更新Critic自身的神经网络,同时也将传输给Actor神经网络,结合概率P计算更新Actor的神经网络参数。
评价
Actor-Critic算法在实现中可以看出非常的不稳定,很难收敛,这应该很容易懂,就比如:Critic作为老师,他对某习题都不是很清楚就去教学生解题(Critic对误差不精确的计算也将反馈给Actor),等他拿回家在仔细研究一下发现自己的解法有问题(下一个episode对误差的计算),再去教导学生,学生根据老师再去修改解法,如果这个过程一直重复,那整个学习过程效率就很低,对于系统来说自然也很不稳定。