Skip to content

Move RLOO advantage estimator from GRPOLearner to AgenticGRPOLearner.#1340

Open
copybara-service[bot] wants to merge 1 commit intomainfrom
test_893027684
Open

Move RLOO advantage estimator from GRPOLearner to AgenticGRPOLearner.#1340
copybara-service[bot] wants to merge 1 commit intomainfrom
test_893027684

Conversation

@copybara-service
Copy link
Copy Markdown

Move RLOO advantage estimator from GRPOLearner to AgenticGRPOLearner.
Enable rloo for deepswe

Enable rloo for deepswe

PiperOrigin-RevId: 893027684
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