白话强化学习的DDPG源代码解读

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


class ReplayBuffer(object):
    def __init__(self, max_size=1e6):
        self.storage = []
        self.max_size = max_size
        self.ptr = 0

    def add(self, data):
        if len(self.storage) == self.max_size:
            self.storage[int(self.ptr)] = data
            self.ptr = (self.ptr + 1) % self.max_size
        else:
            self.storage.append(data)

    def sample(self, batch_size):
        ind = np.random.randint(0, len(self.storage), size=batch_size)  # 返回随机数
        x, y, u, r, d = [], [], [], [], []
        for i in ind:
            X, Y, U, R, D = self.storage[i]
            x.append(np.array(X, copy=False))
            y.append(np.array(Y, copy=False))
            u.append(np.array(U, copy=False))
            r.append(np.array(R, copy=False))
            d.append(np.array(D, copy=False))
        return np.array(x), np.array(y), np.array(u), np.array(r).reshape(-1, 1), np.array(d).reshape(-1, 1)


device = torch.device("cuda" if torch.cuda.is_available() else "cpu")


class Actor(nn.Module):
    def __init__(self, state_dim, action_dim, max_action):
        super(Actor, self).__init__()
        self.l1 = nn.Linear(state_dim, 400)
        self.l2 = nn.Linear(400, 300)
        self.l3 = nn.Linear(300, action_dim)
        self.max_action = max_action

    def forward(self, x):
        x = F.relu(self.l1(x))
        x = F.relu(self.l2(x))
        x =