Skip to content

Conversation

LuanBrt
Copy link

@LuanBrt LuanBrt commented Sep 5, 2025

Description

This PR adds rollout filtering to the Trainer, following the RAGEN approach. It helps prevent model collapse by retaining only the top N% of tasks with the highest outcome uncertainty.

Type of Change

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • Documentation update
  • Test improvement

Testing

  • All existing tests pass
  • New tests have been added to cover the changes
  • Tests have been run locally with python -m pytest tests/

Test Coverage

  • Current coverage: 100%
  • Coverage after changes: 100%

Checklist

  • My code follows the style guidelines of this project
  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas
  • I have made corresponding changes to the documentation
  • My changes generate no new warnings
  • Any dependent changes have been merged and published

Additional Notes

@CLAassistant
Copy link

CLAassistant commented Sep 5, 2025

CLA assistant check
All committers have signed the CLA.

@LuanBrt LuanBrt marked this pull request as draft September 24, 2025 15:39
@LuanBrt LuanBrt marked this pull request as ready for review September 24, 2025 16:03
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