Awesome RL with Human Feedback / 2023 / arXiv

A General Theoretical Paradigm to Understand Learning from Human Preferences

作者：Mohammad Gheshlaghi Azar, Mark Rowland, Bilal Piot, Daniel Guo, Daniele Calandriello, Michal Valko, Rémi Munos · 单位：Google DeepMind · 来源：arXiv · 发布日期：2023

偏好学习理论/遗憾界
新标签打开 AlphaXiv
A General Theoretical Paradigm to Understand Learning from Human Preferences figure
AlphaXiv 中文概览（可滚动查看）