saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-07-23 19:32:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix exp_ln computation

Browse source
This commit is contained in:
Antonin Raffin 2019-12-20 18:02:01 +01:00
parent 9b3b34c9c4
commit 7f34108ed6
1 changed files with 5 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
torchy_baselines/common/distributions.py
View file

@ -272,10 +272,11 @@ class StateDependentNoiseDistribution(Distribution):
if self.use_expln:
# From SDE paper, it allows to keep variance
# above zero and prevent it from growing too fast
if log_std <= 0:
std = th.exp(log_std)
else:
std = th.log(log_std + 1.0) + 1.0
below_threshold = th.exp(log_std) * (log_std <= 0)
# Avoid NaN: zeros values that are below zero
safe_log_std = log_std * (log_std > 0) + self.epsilon
above_threshold = (th.log1p(safe_log_std) + 1.0) * (log_std > 0)
std = below_threshold + above_threshold
else:
# Use normal exponential
std = th.exp(log_std)