强化学习记录-PPO

PPO-截断：在目标函数中进行限制，以保证新的参数和旧的参数的差距不会太大。

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


class PolicyNetContinuous(torch.nn.Module):
    def __init__(self, state_dim, hidden_dim, action_dim):
        super(PolicyNetContinuous, self).__init__()
        self.fc1 = torch.nn.Linear(state_dim, hidden_dim)
        self.fc_mu = torch.nn.Linear(hidden_dim, action_dim)
        self.fc_std = torch.nn.Linear(hidden_dim, action_dim)

    def forward(self, x):
        x = F.relu(self.fc1(x))
        mu = 2.0 * torch.tanh(self.fc_mu(x))
        std = F.softplus(self.fc_std(x))
        return mu, std


class ValueNet(torch.nn.Module):
    def __init__(self, state_dim, hidden_dim):
        super(ValueNet, self).__init__()
        self.fc1 = torch.nn.Linear(state_dim, hidden_dim)
        self.fc2 = torch.nn.Linear(hidden_dim, 1)

    def forward(self, x):
        x = F.relu(self.fc1(x))
        return self.fc2(x)


class PPOContinuous:
    ''' 处理连续动作的PPO算法 '''
    def __init__(self, state_dim, hidden_dim, action_dim, actor_lr, critic_lr,
                 lmbda, epochs, eps, gamma, device):
        self.actor = PolicyNetContinuous(state_dim, hidden_dim,
                                         action_dim).to(device)
        self.critic = ValueNet(state_dim, hidden_dim).to(device)
        self.actor_optimizer = torch.optim.Adam(self.actor.parameters(),
                                                lr=actor_lr)
        self.critic_optimizer = torch.optim.Adam(self.critic.parameters(),
                                                 lr=critic_lr)
        self.gamma = gamma
        self.lmbda = lmbda
        self.epochs = epochs
        self.eps = eps
        self.device = device

    def take_action(self, state):
        state = torch.tensor([state], dtype=torch.float).to(self.device)
        mu, sigma = self.actor(state)
        action_dist = torch.distributions.Normal(mu, sigma)
        action = action_dist.sample()
        return [action.item()]

    def update(self, transition_dict):
        states = torch.tensor(transition_dict['states'],
                              dtype=torch.float).to(self.device)
        actions = torch.tensor(transition_dict['actions'],
                               dtype=torch.float).view(-1, 1).to(self.device)
        rewards = torch.tensor(transition_dict['rewards'],
                               dtype=torch.float).view(-1, 1).to(self.device)
        next_states = torch.tensor(transition_dict['next_states'],
                                   dtype=torch.float).to(self.device)
        dones = torch.tensor(transition_dict['dones'],
                             dtype=torch.float).view(-1, 1).to(self.device)
        rewards = (rewards + 8.0) / 8.0  # 和TRPO一样,对奖励进行修改,方便训练
        td_target = rewards + self.gamma * self.critic(next_states) * (1 -
                                                                       dones)
        td_delta = td_target - self.critic(states)
        advantage = rl_utils.compute_advantage(self.gamma, self.lmbda,
                                               td_delta.cpu()).to(self.device)
        mu, std = self.actor(states)
        action_dists = torch.distributions.Normal(mu.detach(), std.detach())
        # 动作是正态分布
        old_log_probs = action_dists.log_prob(actions)

        for _ in range(self.epochs):
            mu, std = self.actor(states)
            action_dists = torch.distributions.Normal(mu, std)
            log_probs = action_dists.log_prob(actions)
            ratio = torch.exp(log_probs - old_log_probs)
            surr1 = ratio * advantage
            surr2 = torch.clamp(ratio, 1 - self.eps, 1 + self.eps) * advantage
            actor_loss = torch.mean(-torch.min(surr1, surr2))
            critic_loss = torch.mean(
                F.mse_loss(self.critic(states), td_target.detach()))
            self.actor_optimizer.zero_grad()
            self.critic_optimizer.zero_grad()
            actor_loss.backward()
            critic_loss.backward()
            self.actor_optimizer.step()
            self.critic_optimizer.step()

actor_lr = 1e-4
critic_lr = 5e-3
num_episodes = 2000
hidden_dim = 128
gamma = 0.9
lmbda = 0.9
epochs = 10
eps = 0.2
device = torch.device("cuda") if torch.cuda.is_available() else torch.device(
    "cpu")

env_name = 'Pendulum-v1'
env = gym.make(env_name)
env.seed(0)
torch.manual_seed(0)
state_dim = env.observation_space.shape[0]
action_dim = env.action_space.shape[0]  # 连续动作空间
agent = PPOContinuous(state_dim, hidden_dim, action_dim, actor_lr, critic_lr,
                      lmbda, epochs, eps, gamma, device)

return_list = rl_utils.train_on_policy_agent(env, agent, num_episodes)

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

mv_return = rl_utils.moving_average(return_list, 21)
plt.plot(episodes_list, mv_return)
plt.xlabel('Episodes')
plt.ylabel('Returns')
plt.title('PPO on {}'.format(env_name))
plt.show()