小编Yil*_* L.的帖子

这是我对 CartPole-v0 的 DQN 和 DDQN 的实现，我认为这是正确的。

import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import gym
import torch.optim as optim
import random
import os
import time


class NETWORK(torch.nn.Module):
    def __init__(self, input_dim: int, output_dim: int, hidden_dim: int) -> None:

        super(NETWORK, self).__init__()

        self.layer1 = torch.nn.Sequential(
            torch.nn.Linear(input_dim, hidden_dim),
            torch.nn.ReLU()
        )

        self.layer2 = torch.nn.Sequential(
            torch.nn.Linear(hidden_dim, hidden_dim),
            torch.nn.ReLU()
        )

        self.final = torch.nn.Linear(hidden_dim, output_dim)

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.final(x) …