Awesome RL with Human Feedback / 2022 / arXiv

Reward Uncertainty for Exploration in Preference-based Reinforcement Learning

作者：Xinran Liang, Katherine Shu, Kimin Lee, Pieter Abbeel · 单位：University of California, Berkeley · 来源：arXiv · 发布日期：2022

鲁棒性/噪声反馈奖励建模偏好学习探索样本效率
新标签打开 AlphaXiv新标签打开 Code
Reward Uncertainty for Exploration in Preference-based Reinforcement Learning figure
AlphaXiv 中文概览（可滚动查看）