Awesome RL with Human Feedback / 2024 / arXiv

Dense Reward for Free in Reinforcement Learning from Human Feedback

作者：Alex J. Chan, Hao Sun, Samuel Holt, Mihaela van der Schaar · 来源：arXiv · 发布日期：2024

奖励建模偏好学习信用分配/密集奖励人类反馈设计
新标签打开 AlphaXiv新标签打开 Code
Dense Reward for Free in Reinforcement Learning from Human Feedback figure
AlphaXiv 中文概览（可滚动查看）