文章转载自《动手学强化学习》https://hrl.boyuai.com/chapter/intro

1.理论

本节介绍的是REINFORCE算法，其在估计每个状态动作对的奖励时不使用整个回合的奖励，而是该时刻开始之后的累计奖励作为权值。
$${\nabla }_{\theta }J(\theta )={\mathbb{E}}_{{\pi }_{\theta }}\left[\sum _{t=0}^T\left(\sum _{t^{\prime }=t}^T{\gamma }^{t^{\prime }-t}{r}_{t^{\prime }}\right){\nabla }_{\theta }\log {\pi }_{\theta }\left(a_t\mid s_t\right)\right]$$
算法流程：

在下面的代码实现中，先实现一个episode然后从后往前计算回报，损失函数是负的回报乘于log的该状态下采取该动作的概率。每个状态动作对对应算一次loss，然后反向传播计算梯度。最后整个episode完之后进行梯度下降。

2.代码实践

import gym
import torch
import torch.nn.functional as F
import numpy as np
import matplotlib.pyplot as plt
from tqdm import tqdm
import rl_utils

class PolicyNet(torch.nn.Module):
    def __init__(self, state_dim, hidden_dim, action_dim):
        super(PolicyNet, self).__init__()
        self.fc1 = torch.nn.Linear(state_dim, hidden_dim)
        self.fc2 = torch.nn.Linear(hidden_dim, action_dim)

    def forward(self, x):
        x = F.relu(self.fc1(x))
        return F.softmax(self.fc2(x), dim=1)  # 0是对列做归一化，1是对行做归一化

class REINFORCE:
    def __init__(self, state_dim, hidden_dim, action_dim, learning_rate, gamma,
                 device):
        self.policy_net = PolicyNet(state_dim, hidden_dim,
                                    action_dim).to(device)
        self.optimizer = torch.optim.Adam(self.policy_net.parameters(),
                                          lr=learning_rate)  # 使用Adam优化器
        self.gamma = gamma  # 折扣因子
        self.device = device

    def take_action(self, state):  # 根据动作概率分布随机采样
        state = torch.tensor([state], dtype=torch.float).to(self.device) # 1*4
        probs = self.policy_net(state)  # 1*2
        action_dist = torch.distributions.Categorical(probs)
        action = action_dist.sample()
        return action.item()

    def update(self, transition_dict):
        reward_list = transition_dict['rewards']
        state_list = transition_dict['states']
        action_list = transition_dict['actions']

        G = 0
        self.optimizer.zero_grad()
        for i in reversed(range(len(reward_list))):  # 从最后一步算起
            reward = reward_list[i]
            state = torch.tensor([state_list[i]],  # 1*4
                                 dtype=torch.float).to(self.device)
            action = torch.tensor([action_list[i]]).view(-1, 1).to(self.device) # 1*1
            log_prob = torch.log(self.policy_net(state).gather(1, action)) # 1*1
            G = self.gamma * G + reward
            loss = -log_prob * G  # 每一步的损失函数
            loss.backward()  # 反向传播计算梯度
        self.optimizer.step()  # 梯度下降


learning_rate = 1e-3
num_episodes = 1000
hidden_dim = 128
gamma = 0.98
device = torch.device("cuda") if torch.cuda.is_available() else torch.device(
    "cpu")

env_name = "CartPole-v0"
env = gym.make(env_name)
env.seed(0)
torch.manual_seed(0)
state_dim = env.observation_space.shape[0]
action_dim = env.action_space.n
agent = REINFORCE(state_dim, hidden_dim, action_dim, learning_rate, gamma,
                  device)

return_list = []
for i in range(10):
    with tqdm(total=int(num_episodes / 10), desc='Iteration %d' % i) as pbar:
        for i_episode in range(int(num_episodes / 10)):
            episode_return = 0
            transition_dict = {
                'states': [],
                'actions': [],
                'next_states': [],
                'rewards': [],
                'dones': []
            }
            state = env.reset()
            done = False
            while not done:
                action = agent.take_action(state)
                next_state, reward, done, _ = env.step(action)
                transition_dict['states'].append(state)
                transition_dict['actions'].append(action)
                transition_dict['next_states'].append(next_state)
                transition_dict['rewards'].append(reward)
                transition_dict['dones'].append(done)
                state = next_state
                episode_return += reward
            return_list.append(episode_return)
            agent.update(transition_dict)
            if (i_episode + 1) % 10 == 0:
                pbar.set_postfix({
                    'episode':
                    '%d' % (num_episodes / 10 * i + i_episode + 1),
                    'return':
                    '%.3f' % np.mean(return_list[-10:])
                })
            pbar.update(1)

episodes_list = list(range(len(return_list)))
plt.plot(episodes_list, return_list)
plt.xlabel('Episodes')
plt.ylabel('Returns')
plt.title('REINFORCE on {}'.format(env_name))
plt.show()

mv_return = rl_utils.moving_average(return_list, 9)
plt.plot(episodes_list, mv_return)
plt.xlabel('Episodes')
plt.ylabel('Returns')
plt.title('REINFORCE on {}'.format(env_name))
plt.show()