1 个仓库
Awesome GitHub RepositoriesRL Training Loops
Executes the entire reinforcement learning pipeline—simulation, model inference, and gradient updates—within a single process to eliminate synchronization bottlenecks.
Distinct from Single-Process Servers: Distinct from Single-Process Servers: specifically targets RL training loops, not general server architectures.
Explore 1 awesome GitHub repository matching devops & infrastructure · RL Training Loops. Refine with filters or upvote what's useful.
Awesome RL Training Loops GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- pufferai/pufferlib
PufferAI/PufferLib
6,039在 GitHub 上查看PufferLib is a reinforcement learning framework built around high-speed environment simulation and automatic hyperparameter optimization. It is designed to accelerate the entire RL training pipeline by running simulations at near-native speed and enabling the training of tiny models to super-human performance within seconds. The framework achieves its speed through a single-process training loop that eliminates inter-process communication overhead, vectorized batched simulation for parallel environment execution, and compiled C extensions that offload performance-critical computations. It als
Executes simulation, model inference, and gradient updates in a single process to eliminate synchronization bottlenecks.
Creinforcement-learning
