Summary of Rime: Robust Preference-based Reinforcement Learning with Noisy Preferences, by Jie Cheng et al.
RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences
by Jie Cheng, Gang Xiong, Xingyuan Dai, Qinghai Miao, Yisheng Lv, Fei-Yue Wang
First submitted to arxiv on: 27 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Robotics (cs.RO)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers propose a novel approach to Preference-based Reinforcement Learning (PbRL) that addresses the issue of relying heavily on high-quality feedback from domain experts. The proposed algorithm, RIME, utilizes a sample selection-based discriminator to filter out noise and ensure robust training. Additionally, a warm start is suggested for the reward model to counteract cumulative error. Experimental results demonstrate improved robustness in robotic manipulation and locomotion tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary PbRL lets robots learn from what humans like or dislike! But current methods need expert help to work well. This paper fixes that by creating an algorithm called RIME. It’s like a filter that helps the robot ignore bad advice and only listen to good feedback. The researchers tested it on robots doing tasks, and it worked better than before! |
Keywords
* Artificial intelligence * Reinforcement learning
