redai-studio/Relax · AI Repo StatsREredai-studio/Relax
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
Huấn luyện & fine-tunePython Apache-2.0 207tạo 2026-04-13 #agentic-rl#distributed-training#grpo#multi-agent#multimodal#post-training#ray-serve#reinforcement-learning#rlhf