PrototypeCommon
yifanzhang-pro/FlashREINFORCE
FlashREINFORCE: Critic-Free, Single-Rollout, Asynchronous RL for Agentic Language Models
- Owner
- yifanzhang-pro (personal account)
- Stars
- Stars: 105
- Forks
- Forks: 10
- Language
- Python
- License
- Apache-2.0
- Created
- 2026
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by yifanzhang-pro
All 5 repos by yifanzhang-pro- yifanzhang-pro/recurrent-looped-tranformerStars: 1,138HTMLBeta
- yifanzhang-pro/deep-delta-learningStars: 363PythonAlpha
- yifanzhang-pro/KLPOStars: 190PythonPrototype
- yifanzhang-pro/HLAStars: 104HTMLPrototype
Nearby in Python
All Python repos- ozguradmin/ahenk-turkish-ttsStars: 105PythonPrototype
- SuperBigFatDog/mcd-nearest-dealStars: 105PythonPrototype
- Mosina1102/MouiStars: 105PythonPrototype
- infogami/infogamiStars: 105PythonPrototype
- lig/pystardictStars: 105PythonPrototype
- mattball/doxycleanStars: 105PythonPrototype