强化学习(DQN)Pytorch实现

最新推荐文章于 2025-06-25 16:10:46 发布

SinGaln

最新推荐文章于 2025-06-25 16:10:46 发布

阅读量4k

点赞数 2

CC 4.0 BY-SA版权

分类专栏：深度学习（deep learning） python编程文章标签： pytorch;DQN

本文链接：https://blog.youkuaiyun.com/qq_27492735/article/details/95334779

本文通过Pytorch实现了一种深度强化学习算法——DQN，并展示了实验效果。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

直接上代码：

#coding = utf-8

import torch
import torch.optim as optim
from torch.autograd import Variable
import torch.nn.functional as F
import torch.nn as nn
import numpy as np
import gym

#parameters
Batch_size = 32
Lr = 0.01
Epsilon = 0.9           #greedy policy
Gamma = 0.9             #reward discount
Target_replace_iter = 100  #target update frequency
Memory_capacity = 2000
env = gym.make('CartPole-v0')
env = env.unwrapped
N_actions = env.action_space.n
N_states = env.observation_space.shape[0]
ENV_A_SHAPE = 0 if isinstance(env.action_space.sample(), int) else env.action_space.sample().shape

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(N_states,50)
        self.fc1.weight.data.normal_(0,0.1)
        self.out = nn.Linear(50,N_actions)
        self.out.weight.data.normal_(0,0.1)


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