Awesome RL with Human Feedback / 2020 and before / arXiv

Interactive Learning from Policy-Dependent Human Feedback

作者：James MacGlashan, Mark K Ho, Robert Loftin, Bei Peng, Guan Wang, David Roberts, Matthew E. Taylor, Michael L. Littman · 来源：arXiv · 发布日期：2020

鲁棒性/噪声反馈偏好学习策略优化在线人类反馈强化学习人类反馈设计
新标签打开 AlphaXiv
Interactive Learning from Policy-Dependent Human Feedback figure
AlphaXiv 中文概览（可滚动查看）