SPPO
The official implementation of Self-Play Preference Optimization (SPPO)
uclaml/SPPO
View on GitHub ↗The official implementation of Self-Play Preference Optimization (SPPO)
SPPO grew +0.0% in the last 30 days, ranks 24th of 82 in Reinforcement Learning / RLHF, last commit 640 days ago.
Star trajectory
115 days tracked2026-07-02589 stars today2026-10-25
Momentum
+0.0% in 30d, below the Reinforcement Learning / RLHF median of +1.1%.
Maintenance
Last commit 640 days ago, staler than the median of 46d.
How it compares in Reinforcement Learning / RLHF
SPPO
589
stars
+0.0% 30d
commit 640 days ago
Reinforcement Learning / RLHF median
309
stars
+1.1% 30d
commit ~46d ago
Leader · OpenRLHF
10.1k
stars
+0.7% 30d
commit 19 days ago
Ranked 24th of 82 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 4
- Forks
- 48
- Watchers
- 28
- Open issues
- 14
- Releases
- 0
- Created
- 2024-06-13
- Stars this week
- +1
You've seen where SPPO stands today.
Get the moves before everyone else: the 5 Reinforcement Learning / RLHF repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.