wassname/pytorch-soft-actor-critic
1
0
Fork 0
mirror of https://github.com/wassname/pytorch-soft-actor-critic.git synced 2026-06-27 17:01:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix error with DeterministicPolicy

Browse Source 
More pytorch-native way would be to use `Module.register_buffer()` method. In that case, buffer won't be used in parameters(), but will be converted to CUDA and CPU with `to()` call transparently.
This commit is contained in:
Max Lapan
2019-11-24 18:00:57 +03:00
committed by GitHub
parent cc42a1f31c
commit 3664ba4e60
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
@@ -148,4 +148,5 @@ class DeterministicPolicy(nn.Module):
def to(self, device):
self.action_scale = self.action_scale.to(device)
self.action_bias = self.action_bias.to(device)
return super(GaussianPolicy, self).to(device)
self.noise = self.noise.to(device)
return super(DeterministicPolicy, self).to(device)