Awesome RL with Human Feedback / 2024 / arXiv

RIME: Robust Preference-based Reinforcement Learning with Noisy Human Preferences

作者：Jie Cheng, Gang Xiong, Xingyuan Dai, Qinghai Miao, Yisheng Lv, Fei-Yue Wang · 来源：arXiv · 发布日期：2024

鲁棒性/噪声反馈偏好学习
新标签打开 AlphaXiv新标签打开 Code
RIME: Robust Preference-based Reinforcement Learning with Noisy Human Preferences figure
AlphaXiv 中文概览（可滚动查看）