PrototypeCommon
spiral-rl/spiral
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
- Owner
- spiral-rl (organization)
- Stars
- Stars: 211
- Forks
- Forks: 23
- Language
- Python
- License
- MIT
- Created
- 2025
- Topics
- large-language-modelsself-playmulti-agent-reinforcement-learningreinforcement-learning
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- JEen-wang/Adaptive-ragStars: 211PythonPrototype
- empero-org/brewery-aiStars: 211PythonPrototype
- 3yangyang9/DeepTutor-AILearningStars: 211PythonPrototype
- theanti9/PyCrawlerStars: 211PythonPrototype
- jamesturk/scrapelibStars: 211PythonPrototype
- hypernumbers/learn_elisp_the_hard_wayStars: 211PythonPrototype