Skip to content

Compute discriminator output with policy and expert states #22

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.

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

Merged
merged 3 commits into from
Jul 3, 2025

Conversation

GiulioRomualdi
Copy link
Member

Concatenate policy and expert observations for the discriminator input to enhance its performance. This change introduces a new loss function for the discriminator.

@GiulioRomualdi GiulioRomualdi self-assigned this Jul 2, 2025
@GiulioRomualdi GiulioRomualdi requested a review from Giulero July 2, 2025 14:17
@GiulioRomualdi
Copy link
Member Author

Tested in a training that it is working as expected

@GiulioRomualdi GiulioRomualdi merged commit 4086172 into main Jul 3, 2025
@GiulioRomualdi GiulioRomualdi deleted the discriminator_at_once branch July 3, 2025 14:17
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants