Awesome RL with Human Feedback / 2023 / arXiv

Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons

作者：Banghua Zhu, Jiantao Jiao, Michael I. Jordan · 单位：Department of Electrical Engineering and Computer Sciences, UC Berkeley, Department of Statistics, UC Berkeley · 来源：arXiv · 发布日期：2023

偏好学习人类反馈设计理论/遗憾界
新标签打开 AlphaXiv
Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons figure
AlphaXiv 中文概览（可滚动查看）