Awesome RL with Human Feedback / 2023 / arXiv

Safe RLHF: Safe Reinforcement Learning from Human Feedback

作者：Josef Dai, Xuehai Pan, Ruiyang Sun, Jiaming Ji, Xinbo Xu, Mickel Liu, Yizhou Wang, Yaodong Yang · 单位：Peking University · 来源：arXiv · 发布日期：2023-10-19

安全对齐偏好学习人类反馈设计
新标签打开 AlphaXiv
Safe RLHF: Safe Reinforcement Learning from Human Feedback figure
AlphaXiv 中文概览（可滚动查看）