Awesome RL with Human Feedback / 2025 / arXiv

Towards Efficient Online Exploration for Reinforcement Learning with Human Feedback

作者：Gen Li, Yuling Yan · 来源：arXiv · 发布日期：2025

偏好学习在线人类反馈强化学习探索样本效率人类反馈设计
新标签打开 AlphaXiv
Towards Efficient Online Exploration for Reinforcement Learning with Human Feedback figure
AlphaXiv 中文概览（可滚动查看）