RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences

Jie Cheng; Gang Xiong; Xingyuan Dai; Qinghai Miao; Yisheng Lv; Fei-Yue Wang

2024 ICML ICML 2024

RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Reinforcement Learning and Robotics

Authors

Jie Cheng, Gang Xiong, Xingyuan Dai, Qinghai Miao, Yisheng Lv, Fei-Yue Wang

Topics

Reinforcement Learning > Methods > Deep RL Reinforcement Learning > Applications > Robotics Robotics > Capabilities > Manipulation

Keywords

robustness reward model preference-based reinforcement learning noisy preference warm start sample selection-based discriminator

Download PDF