Awesome RL with Human Feedback / 2024 / arXiv

MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions

作者：Yekun Chai, Haoran Sun, Huang Fang, Shuohuan Wang, Yu Sun, Hua Wu · 单位：Baidu Inc · 来源：arXiv · 发布日期：2024

奖励建模偏好学习样本效率信用分配/密集奖励人类反馈设计
新标签打开 AlphaXiv新标签打开 Code
MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions figure
AlphaXiv 中文概览（可滚动查看）