Actor Critic

我们有了像 Q-learning这么伟大的算法, 为什么还要瞎折腾出一个 Actor-Critic? 原来 Actor-Critic 的 Actor 的前生是 Policy Gradients, 这能让它毫不费力地在连续动作中选取合适的动作, 而 Q-learning 做这件事会瘫痪. 那为什么不直接用 Policy Gradients 呢? 原来 Actor Critic 中的 Critic 的前生是 Q-learning 或者其他的 以值为基础的学习法 , 能进行单步更新, 而传统的 Policy Gradients 则是回合更新, 这降低了学习效率.

"""
Actor-Critic using TD-error as the Advantage, Reinforcement Learning.
The cart pole example. Policy is oscillated.
View more on my tutorial page: https://morvanzhou.github.io/tutorials/
Using:
tensorflow,gym
"""

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 = 100
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
        #actor进行单词训练，输入的只需要是一个状态一个动作和一个奖励
        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
        #Actor的神经网络结构和我们的Policy Gradient定义的是一样的，是一个双层的全链接神经网络
        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)
    #Actor的训练只需要将状态，动作以及时间差分值喂给网络就可以。
    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
    #选择动作和Policy Gradient一样，根据计算出的softmax值来选择动作
    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

#Critic要反馈给Actor一个时间差分值，来决定Actor选择动作的好坏，如果时间差分值大的话，
# 说明当前Actor选择的这个动作的惊喜度较高，需要更多的出现来使得时间差分值减小。
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'
            )
        #Critic的损失定义为时间差分值的平方值
        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)
    #Critic的任务就是告诉Actor当前选择的动作好不好，所以我们只要训练得到TD并返回给Actor就好
    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