Awesome RL with Human Feedback / 2026 / arXiv

Learning to summarize user information for personalized reinforcement learning from human feedback

作者：HyunJi Nam, Yanming Wan, Mickel Liu, Peter F. Ahnn, Jianxun Lian, Natasha Jaques · 单位：Stanford University, University of Washington · 来源：arXiv · 发布日期：2025-07-17

奖励建模偏好学习对齐目标设计个性化对齐人类反馈设计
新标签打开 AlphaXiv
Learning to summarize user information for personalized reinforcement learning from human feedback figure
AlphaXiv 中文概览（可滚动查看）