saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-07-21 19:19:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Hotfix PPO/A2C + gSDE

Browse source
This commit is contained in:
Antonin RAFFIN 2020-06-10 18:16:10 +02:00
parent aa94715182
commit 16e8b78cc3
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
stable_baselines3/common/distributions.py
View file

@ -525,7 +525,7 @@ class StateDependentNoiseDistribution(Distribution):
"""
# Stop gradient if we don't want to influence the features
self._latent_sde = latent_sde if self.learn_features else latent_sde.detach()
variance = th.mm(latent_sde ** 2, self.get_std(log_std) ** 2)
variance = th.mm(self._latent_sde ** 2, self.get_std(log_std) ** 2)
self.distribution = Normal(mean_actions, th.sqrt(variance + self.epsilon))
return self