【强化学习】算法实践-策略梯度PG

0 引言

策略梯度根据策略为softmax策略或者高斯策略，可以解决离散动作空间或者连续动作空间的问题。当使用softmax策略时，网络便会根据状态输出执行每个动作的概率，这时候可以直接选择最大概率的动作；而当使用高斯策略时，网络会根据状态输出执行每个动作的概率分布。

1 离散动作空间

离散动作空间的例子有很多，比如说CartPole、MountainCar或者PuckWorld等。这些例子的特点是状态空间连续、动作空间离散。
为了解决这个问题，首先定义策略梯度类。

import numpy as np
import tensorflow as tf

# reproducible
np.random.seed(1)
tf.set_random_seed(1)


class PolicyGradient:
    def __init__(
            self,
            n_actions,
            n_features,
            learning_rate=0.01,
            reward_decay=0.95,
            output_graph=False,
    ):
        self.n_actions = n_actions
        self.n_features = n_features
        self.lr = learning_rate
        self.gamma = reward_decay

        self.ep_obs, self.ep_as, self.ep_rs = [], [], []

        self._build_net()

        self.sess = tf.Session()

        if output_graph:
            # $ tensorboard --logdir=logs
            # http://0.0.0.0:6006/
            # tf.train.SummaryWriter soon be deprecated, use following
            tf.summary.FileWriter("logs/", self.sess.graph)

        self.sess.run(tf.global_variables_initializer())

    def _build_net(self):
        with tf.name_scope('inputs'):
            self.tf_obs = tf.placeholder(tf.float32, [None, self.n_features], name="observations")
            self.tf_acts = tf.placeholder(tf.int32, [None, ], name="actions_num")
            self.tf_vt = tf.placeholder(tf.float32, [None, ], name="actions_value")
        # fc1
        layer = tf.layers.dense(
            inputs=self.tf_obs,
            units=10,
            activation=tf.nn.tanh,  # tanh activation
            kernel_initializer=tf.random_normal_initializer(mean=0, stddev=0.3),
            bias_initializer=tf.constant_initializer(0.1),
            name='fc1'
        )
        # fc2
        all_act = tf.layers.dense(
            inputs=layer,
            units=self.n_actions,
            activation=None,
            kernel_initializer=tf.random_normal_initializer(mean=0, stddev=0.3),
            bias_initializer=tf.constant_initializer(0.1),
            name='fc2'
        )

        self.all_act_prob = tf.nn.softmax(all_act, name='act_prob')  # use softmax to convert to probability

        # 很关键的损失函数定义
        with tf.name_scope('loss'):
            # to maximize total reward (log_p * R) is to minimize -(log_p * R), and the tf only have minimize(loss)
            neg_log_prob = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=all_act, labels=self.tf_acts)   # this is negative log of chosen action
            # or in this way:
            # neg_log_prob = tf.reduce_sum(-tf.log(self.all_act_prob)*tf.one_hot(self.tf_acts, self.n_actions), axis=1)
            loss = tf.reduce_mean(neg_log_prob * self.tf_vt)  # reward guided loss

        with tf.name_scope('train'):
            self.train_op = tf.train.AdamOptimizer(self.lr).minimize(loss)

    def choose_action(self, observation):
        prob_weights = self.sess.run(self.all_act_prob, feed_dict={self.tf_obs: observation[np.newaxis, :]})
        action = np.random.choice(range(prob_weights.shape[1]), p=prob_weights.ravel())  # select action w.r.t the actions prob
        return action

    def store_transition(self, s, a, r):
        self.ep_obs.append(s)
        self.ep_as.append(a)
        self.ep_rs.append(r)

    def learn(self):
        # discount and normalize episode reward
        discounted_ep_rs_norm = self._discount_and_norm_rewards()

        # train on episode
        self.sess.run(self.train_op, feed_dict={
             self.tf_obs: np.vstack(self.ep_obs),  # shape=[None, n_obs]
             self.tf_acts: np.array(self.ep_as),  # shape=[None, ]
             self.tf_vt: discounted_ep_rs_norm,  # shape=[None, ]
        })

        self.ep_obs, self.ep_as, self.ep_rs = [], [], []    # empty episode data
        return discounted_ep_rs_norm

    def _discount_and_norm_rewards(self):
        # discount episode rewards
        discounted_ep_rs = np.zeros_like(self.ep_rs)
        running_add = 0
        for t in reversed(range(0, len(self.ep_rs))):
            running_add = running_add * self.gamma + self.ep_rs[t]
            discounted_ep_rs[t] = running_add

        # normalize episode rewards
        discounted_ep_rs -= np.mean(discounted_ep_rs)
        discounted_ep_rs /= np.std(discounted_ep_rs)
        return discounted_ep_rs

然后就是利用策略梯度测试环境的代码：

import gym
from RL_brain import PolicyGradient
import matplotlib.pyplot as plt

DISPLAY_REWARD_THRESHOLD = 400  # renders environment if total episode reward is greater then this threshold
RENDER = False  # rendering wastes time

env = gym.make('CartPole-v0')
env.seed(1)     # reproducible, general Policy gradient has high variance
env = env.unwrapped

print(env.action_space)
print(env.observation_space)
print(env.observation_space.high)
print(env.observation_space.low)

RL = PolicyGradient(
    n_actions=env.action_space.n,
    n_features=env.observation_space.shape[0],
    learning_rate=0.02,
    reward_decay=0.99,
    # output_graph=True,
)

for i_episode in range(3000):

    observation = env.reset()

    while True:
        if RENDER: env.render()

        action = RL.choose_action(observation)

        observation_, reward, done, info = env.step(action)

        RL.store_transition(observation, action, reward)

        if done:
            ep_rs_sum = sum(RL.ep_rs)

            if 'running_reward' not in globals():
                running_reward = ep_rs_sum
            else:
                running_reward = running_reward * 0.99 + ep_rs_sum * 0.01
            if running_reward > DISPLAY_REWARD_THRESHOLD: RENDER = True     # rendering
            print("episode:", i_episode, "  reward:", int(running_reward))

            vt = RL.learn()

            if i_episode == 0:
                plt.plot(vt)    # plot the episode vt
                plt.xlabel('episode steps')
                plt.ylabel('normalized state-action value')
                plt.show()
            break

        observation = observation_

2 连续动作空间

使用策略梯度的一个主要目的就是解决连续动作空间的问题。那么首先要找一个连续动作空间的问题。

参考文献

[1] Morvan 强化学习教程 策略梯度