RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences
Jie Cheng, Gang Xiong, Xingyuan Dai, Qinghai Miao, Yisheng Lv, Fei-Yue Wang
Abstract
Preference-based Reinforcement Learning (PbRL) circumvents the need for reward engineering by harnessing human preferences as the reward signal. However, current PbRL methods excessively depend on high-quality feedback from domain experts, which results in a lack of robustness. In this paper, we present RIME, a robust PbRL algorithm for effective reward learning from noisy preferences. Our method utilizes a sample selection-based discriminator to dynamically filter out noise and ensure robust training. To counteract the cumulative error stemming from incorrect selection, we suggest a warm start for the reward model, which additionally bridges the performance gap during the transition from pre-training to online training in PbRL. Our experiments on robotic manipulation and locomotion tasks demonstrate that RIME significantly enhances the robustness of the state-of-the-art PbRL method. Code is available at https://github.com/CJReinforce/RIME_ICML2024.
BibTeX
@inproceedings{
cheng2024rime,
title={{RIME}: Robust Preference-based Reinforcement Learning with Noisy Preferences},
author={Jie Cheng and Gang Xiong and Xingyuan Dai and Qinghai Miao and Yisheng Lv and Fei-Yue Wang},
booktitle={Forty-first International Conference on Machine Learning},
year={2024},
url={https://openreview.net/forum?id=BxAvcnlS8O}
}