NVlabs/
Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
by NVIDIA Research Projects Python Apache-2.0 licence 38 forks Created Dec 2025 View on GitHub
- Stars
- 516
- <1% of NVlabs's stars
- Rank
- #122,440
- of 852,180 repos, top 15%
- In Python
- #22,817
- of 173,254 repos, top 14%
Among 852,180 repos
400–630 stars: 51,567 repos, including GDPO
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #122,239
- Next milestone
- +251 stars to reach the top 10%
- Popular
- One of 490,958 repos with 100+ stars