bacow/easy-rl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update codes

Browse Source
This commit is contained in:
johnjim0816
2021-11-18 15:41:27 +08:00
parent 442e307b01
commit 129c0c65fa
103 changed files with 1025 additions and 558 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
codes/A2C/agent.py
View File

@@ -12,10 +12,10 @@ Environment:
import torch.optim as optim
from A2C.model import ActorCritic
class A2C:
def __init__(self,state_dim,action_dim,cfg) -> None:
def __init__(self,n_states,n_actions,cfg) -> None:
self.gamma = cfg.gamma
self.device = cfg.device
self.model = ActorCritic(state_dim, action_dim, cfg.hidden_size).to(self.device)
self.model = ActorCritic(n_states, n_actions, cfg.hidden_size).to(self.device)
self.optimizer = optim.Adam(self.model.parameters())
def compute_returns(self,next_value, rewards, masks):