TREND: Tri-teaching for Robust Preference-based Reinforcement Learning with Demonstrations
Shuaiyi Huang, Mara Levy, Anubhav Gupta, Daniel Ekpo, Ruijie Zheng, Abhinav Shrivastava
- Year
- 2025
- Access
- Open access
Abstract
Preference feedback collected by human or VLM annotators is often noisy, presenting a significant challenge for preference-based reinforcement learning that relies on accurate preference labels. To address this challenge, we propose TREND, a novel framework that integrates few-shot expert demonstrations with a tri-teaching strategy for effective noise mitigation. Our method trains three reward models simultaneously, where each model views its small-loss preference pairs as useful knowledge and teaches such useful pairs to its peer network for updating the parameters. Remarkably, our approach requires as few as one to three expert demonstrations to achieve high performance. We evaluate TREND on various robotic manipulation tasks, achieving up to 90% success rates even with noise levels as high as 40%, highlighting its effective robustness in handling noisy preference feedback. Project page: https://shuaiyihuang.github.io/publications/TREND.
Keywords
Related papers
Real-Time Obstacle Avoidance for Manipulators and Mobile Robots
Oussama Khatib
1986
A Mathematical Introduction to Robotic Manipulation
Richard M. Murray, Zexiang Li, Shankar Sastry
2017
Robot dynamics and control
Mark W. Spong
1989
A tutorial on visual servo control
Seth Hutchinson, Gregory D. Hager, Peter Corke
1996