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

update

Browse Source
This commit is contained in:
JohnJim0816
2021-03-28 11:18:52 +08:00
parent 2df8d965d2
commit 6e4d966e1f
56 changed files with 497 additions and 165 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
codes/DDPG/agent.py
View File

@@ -19,12 +19,12 @@ from common.memory import ReplayBuffer
class DDPG:
def __init__(self, n_states, n_actions, cfg):
def __init__(self, state_dim, action_dim, cfg):
self.device = cfg.device
self.critic = Critic(n_states, n_actions, cfg.hidden_dim).to(cfg.device)
self.actor = Actor(n_states, n_actions, cfg.hidden_dim).to(cfg.device)
self.target_critic = Critic(n_states, n_actions, cfg.hidden_dim).to(cfg.device)
self.target_actor = Actor(n_states, n_actions, cfg.hidden_dim).to(cfg.device)
self.critic = Critic(state_dim, action_dim, cfg.hidden_dim).to(cfg.device)
self.actor = Actor(state_dim, action_dim, cfg.hidden_dim).to(cfg.device)
self.target_critic = Critic(state_dim, action_dim, cfg.hidden_dim).to(cfg.device)
self.target_actor = Actor(state_dim, action_dim, cfg.hidden_dim).to(cfg.device)
for target_param, param in zip(self.target_critic.parameters(), self.critic.parameters()):
target_param.data.copy_(param.data)