saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-06-27 03:11:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

LeakyClip not working yet

Browse source
This commit is contained in:
Antonin RAFFIN 2019-12-22 14:38:30 +01:00
parent 3a7508ac16
commit 57c890f3e9
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
torchy_baselines/sac/policies.py
View file

@ -76,9 +76,9 @@ class Actor(BaseNetwork):
log_std_init=log_std_init)
# Avoid saturation by limiting the mean of the gaussian to be in [-1, 1]
# self.mu = nn.Sequential(self.mu, nn.Tanh())
# self.mu = nn.Sequential(self.mu, nn.Hardtanh(min_val=-2.0, max_val=2.0))
self.mu = nn.Sequential(self.mu, nn.Hardtanh(min_val=-2.0, max_val=2.0))
# Small positive slope to have non-zero gradient
self.mu = nn.Sequential(self.mu, LeakyClip())
# self.mu = nn.Sequential(self.mu, LeakyClip())
else:
self.action_dist = SquashedDiagGaussianDistribution(action_dim)
self.mu = nn.Linear(net_arch[-1], action_dim)