saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-07-28 20:11:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Reformat

Browse source
This commit is contained in:
Antonin Raffin 2020-09-24 14:36:33 +02:00
parent d3a5d49dc3
commit 4112e27a1e
1 changed files with 3 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
stable_baselines3/sac/sac.py
View file

@ -202,7 +202,6 @@ class SAC(OffPolicyAlgorithm):
self.alpha_coef_tensor = th.tensor(float(self.alpha_coef)).to(self.device)
self.log_alpha = th.log(self.alpha_coef_tensor)
def _create_aliases(self) -> None:
self.actor = self.policy.actor
self.critic = self.policy.critic
@ -230,7 +229,9 @@ class SAC(OffPolicyAlgorithm):
policy_actions.append(actions_pi)
n_log_probs.append(log_prob)
# (batch, n, action_dim)
policy_actions = th.cat(policy_actions, dim=1).view(len(replay_data.observations), self.n_action_samples, action_dim)
policy_actions = th.cat(policy_actions, dim=1).view(
len(replay_data.observations), self.n_action_samples, action_dim
)
# assert policy_actions.shape == (len(replay_data.observations), self.n_action_samples, action_dim)
# (batch, n, 1)
n_log_probs = th.cat(n_log_probs).view(len(replay_data.observations), self.n_action_samples, 1)