sail-sg /oat
🌾 OAT:一个面向研究的在线对齐框架,包括强化学习、偏好学习等。
Python674
distributed-rl 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
🌾 OAT:一个面向研究的在线对齐框架,包括强化学习、偏好学习等。
implementation of distributed reinforcement learning with distributed tensorflow
A Collection for Distributed Reinforcement Learning Papers
Deliverable D2.2 | Politecnico di Milano
Deliverable D2.4 | Network distributed Q learning
Asynchronous LLM rollout engine for distributed RL training.