wassname/pytorch-soft-actor-critic
1
0
Fork 0
mirror of https://github.com/wassname/pytorch-soft-actor-critic.git synced 2026-06-27 16:46:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

small fix

Browse Source
This commit is contained in:
pranz24
2019-09-10 22:29:35 +05:30
parent 6b6f64db37
commit c2d50837db
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
model.py
+2 -1
View File
@@ -102,7 +102,8 @@ class GaussianPolicy(nn.Module):
# Enforcing Action Bound
log_prob -= torch.log(self.action_scale * (1 - y_t.pow(2)) + epsilon)
log_prob = log_prob.sum(1, keepdim=True)
return action, log_prob, torch.tanh(mean)
mean = torch.tanh(mean) * self.action_scale + self.action_bias
return action, log_prob, mean
def to(self, device):
self.action_scale = self.action_scale.to(device)