A3C经典源码

dlphay

于 2017-10-26 11:05:30 发布

阅读量1.4k

点赞数 1

CC 4.0 BY-SA版权

分类专栏： RL algorithm python

本文链接：https://blog.youkuaiyun.com/dlphay/article/details/78351176

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
import matplotlib.pyplot as plt
import numpy as np
import math
import random
import os
import gym

# Hyper Parameters
STATE_DIM = 4
ACTION_DIM = 2
STEP = 2000
SAMPLE_NUMS = 30

class ActorNetwork(nn.Module):

    def __init__(self,input_size,hidden_size,action_size):
        super(ActorNetwork, self).__init__()
        self.fc1 = nn.Linear(input_size,hidden_size)
        self.fc2 = nn.Linear(hidden_size,hidden_size)
        self.fc3 = nn.Linear(hidden_size,action_size)

    def forward(self,x):
        out = F.relu(self.fc1(x))
        out = F.relu(self.fc2(out))
        out = F.log_softmax(self.fc3(out))
        return out

class ValueNetwork(nn.Module):

    def __init__(self,input_size,hidden_size,output_size):
        super(ValueNetwork, self).__init__()
        self.fc1 = nn.Linear(input_size,hidden_size)
        self.fc2 = nn.Linear(hidden_size