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

Purpose of forward_smoothing_weight? #5

Open
trevormcinroe opened this issue May 23, 2022 · 0 comments
Open

Purpose of forward_smoothing_weight? #5

trevormcinroe opened this issue May 23, 2022 · 0 comments

Comments

@trevormcinroe
Copy link

What is the purpose of the forward_smoothing_weight as found in line 98 of the config file? It looks like it is applied during the CEB learning step at line 192 of ceb_task.py.

Based on some quick tests, PI-SAC's performance seems to be very sensitive to the value of forward_smoothing_weight. I couldn't find any mention of this hyperparameter in the PI-SAC paper (perhaps I missed it?).
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@trevormcinroe