Awesome RL with Human Feedback / 2023 / arXiv

Eureka: Human-Level Reward Design via Coding Large Language Models

作者：Yecheng Jason Ma, William Liang, Guanzhi Wang, De-An Huang, Osbert Bastani, Dinesh Jayaraman, Yuke Zhu, Linxi Fan, Anima Anandkumar · 来源：arXiv · 发布日期：2023-10-19

奖励规范奖励建模
新标签打开 AlphaXiv
Eureka: Human-Level Reward Design via Coding Large Language Models figure
AlphaXiv 中文概览（可滚动查看）