← 트렌딩
Tangerine Index는 ChatGPT 이후 나온 프로덕트와 사람들의 반응을 싣습니다.
Relax
github.com
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
오픈소스
반응 (1)
비슷한 프로덕트
설명이 비슷한 순
openrl
Unified Reinforcement Learning Framework
Earl
a framework for scalable reinforcement learning research
rlhf-book
Textbook on reinforcement learning from human feedback
rl-tools
The Fastest Deep Reinforcement Learning Library
UniRL
UniRL is a Framework for Unified Multimodal Model Reinforcement Learning
