python强化学习代码

基于Python的强化学习代码通常使用强化学习框架来实现。其中比较常用的框架包括OpenAI Gym和PyTorch等。下面是一个使用PyTorch实现DQN算法的强化学习代码示例：

import gym
import torch
import random
import numpy as np
from collections import deque
from torch import nn, optim

class DQN(nn.Module):
    def __init__(self, state_dim, action_dim):
        super(DQN, self).__init__()
        self.fc1 = nn.Linear(state_dim, 64)
        self.fc2 = nn.Linear(64, 64)
        self.fc3 = nn.Linear(64, action_dim)

    def forward(self, x):
        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = self.fc3(x)
        return x

class ReplayBuffer:
    def __init__(self, capacity):
        self.buffer = deque(maxlen=capacity)

    def push(self, state, action, reward, next_state, done):
        self.buffer.append((state, action, reward, next_state, done))

    def sample(self, batch_size):
        state, action, reward, next_state, done = zip(*random.sample(self.buffer, batch_size))
        return np.array(state), np.array(action), np.array(reward, dtype=np.float32), np.array(next_state), np.array(done, dtype=np.uint8)

    def __len__(self):
        return len(self.buffer)

class Agent:
    def __init__(self, state_dim, action_dim, lr, gamma, epsilon, buffer_capacity, batch_size):
        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
        self.action_dim = action_dim
        self.gamma = gamma
        self.epsilon = epsilon
        self.batch_size = batch_size
        self.buffer = ReplayBuffer(buffer_capacity)

        self.policy_net = DQN(state_dim, action_dim).to(self.device)
        self.target_net = DQN(state_dim, action_dim).to(self.device)
        self.target_net.load_state_dict(self.policy_net.state_dict())
        self.target_net.eval()

        self.optimizer = optim.Adam(self.policy_net.parameters(), lr=lr)

    def act(self, state):
        if random.random() < self.epsilon:
            return random.randint(0, self.action_dim - 1)
        state = torch.FloatTensor(state).unsqueeze(0).to(self.device)
        with torch.no_grad():
            q_value = self.policy_net(state)
        return q_value.argmax(dim=1).item()

    def update(self):
        if len(self.buffer) < self.batch_size:
            return
        state, action, reward, next_state, done = self.buffer.sample(self.batch_size)
        state = torch.FloatTensor(state).to(self.device)
        action = torch.LongTensor(action).to(self.device)
        reward = torch.FloatTensor(reward).to(self.device)
        next_state = torch.FloatTensor(next_state).to(self.device)
        done = torch.FloatTensor(done).to(self.device)

        q_value = self.policy_net(state).gather(1, action.unsqueeze(1)).squeeze(1)
        next_q_value = self.target_net(next_state).max(1)[0]
        expected_q_value = reward + self.gamma * next_q_value * (1 - done)
        loss = nn.MSELoss()(q_value, expected_q_value.detach())

        self.optimizer.zero_grad()
        loss.backward()
        self.optimizer.step()

    def update_target(self):
        self.target_net.load_state_dict(self.policy_net.state_dict())

    def save(self, path):
        torch.save(self.policy_net.state_dict(), path)

    def load(self, path):
        self.policy_net.load_state_dict(torch.load(path))

env = gym.make('CartPole-v0')
state_dim = env.observation_space.shape[0]
action_dim = env.action_space.n
agent = Agent(state_dim, action_dim, lr=0.001, gamma=0.99, epsilon=0.1, buffer_capacity=10000, batch_size=64)

for episode in range(1000):
    state = env.reset()
    total_reward = 0
    while True:
        action = agent.act(state)
        next_state, reward, done, _ = env.step(action)
        agent.buffer.push(state, action, reward, next_state, done)
        total_reward += reward
        state = next_state
        agent.update()
        if done:
            break
    agent.update_target()
    print("Episode: {}, total reward: {}".format(episode, total_reward))

agent.save("dqn.pth")

该代码实现了一个使用DQN算法解决CartPole-v0环境的强化学习任务的智能体。其中，DQN类定义了一个三层全连接神经网络，ReplayBuffer类定义了一个经验回放缓存，Agent类定义了一个智能体，包含了策略网络和目标网络，并实现了动作选择、经验回放和网络更新等功能。在主函数中，我们使用该智能体在CartPole-v0环境中进行了1000个episode的训练，并将训练好的策略网络保存到了文件"dqn.pth"中。