Awesome RL with Human Feedback / 2024 / arXiv

A Theoretical Analysis of Nash Learning from Human Feedback under General KL-Regularized Preference

作者：Chenlu Ye, Wei Xiong, Yuheng Zhang, Nan Jiang, Tong Zhang · 来源：arXiv · 发布日期：2024

奖励建模偏好学习对齐目标设计训练稳定性策略优化
新标签打开 AlphaXiv
A Theoretical Analysis of Nash Learning from Human Feedback under General KL-Regularized Preference figure
AlphaXiv 中文概览（可滚动查看）