35 lines
912 B
Python
35 lines
912 B
Python
#!/usr/bin/env python
|
|
# coding=utf-8
|
|
'''
|
|
Author: John
|
|
Email: johnjim0816@gmail.com
|
|
Date: 2020-11-03 20:45:25
|
|
LastEditor: John
|
|
LastEditTime: 2020-11-07 18:49:09
|
|
Discription:
|
|
Environment:
|
|
'''
|
|
import torch.nn as nn
|
|
from torch.distributions import Categorical
|
|
|
|
class ActorCritic(nn.Module):
|
|
def __init__(self, n_states, n_actions, hidden_dim=256, std=0.0):
|
|
super(ActorCritic, self).__init__()
|
|
self.critic = nn.Sequential(
|
|
nn.Linear(n_states, hidden_dim),
|
|
nn.ReLU(),
|
|
nn.Linear(hidden_dim, 1)
|
|
)
|
|
|
|
self.actor = nn.Sequential(
|
|
nn.Linear(n_states, hidden_dim),
|
|
nn.ReLU(),
|
|
nn.Linear(hidden_dim, n_actions),
|
|
nn.Softmax(dim=1),
|
|
)
|
|
|
|
def forward(self, x):
|
|
value = self.critic(x)
|
|
probs = self.actor(x)
|
|
dist = Categorical(probs)
|
|
return dist, value |