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
dueling-bandits 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。
Robust contextual dueling bandits with post-serving context, delayed feedback, and adversarial corruption (RLHF / preference learning) — ICML 2026
A python library for (finite) Partial Monitoring algorithms
An interactive book on Bayesian optimization and learning from human preferences, from first principles to the research frontier.