Awesome RL with Human Feedback / 2023 / arXiv

Reinforcement Learning from Statistical Feedback: the Journey from AB Testing to ANT Testing

作者：Feiyang Han, Yimin Wei, Zhaofeng Liu, Yanxing Qi · 单位：Shenzhen Tencent computer System Co.Ltd., Shenzhen, Guangdong, 518054, P. R. China · 来源：arXiv · 发布日期：2023

评测/基准人类反馈设计
新标签打开 AlphaXiv
Reinforcement Learning from Statistical Feedback: the Journey from AB Testing to ANT Testing figure
AlphaXiv 中文概览（可滚动查看）