Files
easy-rl/codes/A2C/model.py
JohnJim0816 bf0f2990cf update
2021-03-23 16:10:11 +08:00

36 lines
920 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: 2021-03-20 17:41:33
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):
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)
print(x)
probs = self.actor(x)
dist = Categorical(probs)
return dist, value