Awesome RL with Human Feedback / 2023 / arXiv

Sample Efficient Reinforcement Learning from Human Feedback via Active Exploration

作者：Viraj Mehta, Vikramjeet Das, Ojash Neopane, Yijia Dai, Ilija Bogunovic, Jeff Schneider, Willie Neiswanger · 来源：arXiv · 发布日期：2023

偏好学习探索样本效率人类反馈设计
新标签打开 AlphaXiv
Sample Efficient Reinforcement Learning from Human Feedback via Active Exploration figure
AlphaXiv 中文概览（可滚动查看）