Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Detach z star p. #13

Merged
merged 1 commit into from
Jul 7, 2018
Merged

Detach z star p. #13

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
2 changes: 1 addition & 1 deletion train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,7 +94,7 @@ def _trust_region_loss(model, distribution, ref_distribution, loss, threshold):
z_star = [g_p - trust_factor.expand_as(k_p) * k_p for g_p, k_p in zip(g, k)]
trust_loss = 0
for param, z_star_p in zip([model.fc_actor.weight, model.fc_actor.bias], z_star):
trust_loss += (param * z_star_p).sum()
trust_loss += (param * z_star_p.detach()).sum()
_isolate_policy_grads(model, False) # Re-enable gradients for other parameters
return trust_loss

Expand Down