GDPO
Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
NVlabs/GDPO
View on GitHub ↗Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
GDPO grew +1.4% in the last 30 days, ranks 27th of 82 in Reinforcement Learning / RLHF, last commit 157 days ago.
Star trajectory
115 days tracked2026-07-02513 stars today2026-10-25
Momentum
+1.4% in 30d, above the Reinforcement Learning / RLHF median of +1.1%.
Maintenance
Last commit 157 days ago, staler than the median of 46d.
How it compares in Reinforcement Learning / RLHF
GDPO
513
stars
+1.4% 30d
commit 157 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 27th of 82 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 2
- Forks
- 38
- Watchers
- 3
- Open issues
- 5
- Releases
- 0
- Created
- 2025-12-09
- Stars this week
- +0
You've seen where GDPO 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.