Release Highlights
What's Changed
- Release version
0.5.2(#457) - Remove openpipe dependency (#456)
- Add
strip_logprobsutility function (#455) - fix: Handle RULER rewards when all trajectories are identical (#454)
- Make copy.copy work for trajectories (#453)
- Fix lint (#451)
- feat: Add OpenEnv integration example (#445)
- Release v0.5.1 (#442)
Full Changelog: v0.5.1...v0.5.3