MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning
Abstract
Visual deep reinforcement learning (RL) enables robots to acquire skills from visual input for unstructured tasks. However, current algorithms suffer from low sample efficiency, limiting their practical applicability. In this work, we present MENTOR, a method that improves both the architecture and optimization of RL agents. Specifically, MENTOR replaces the standard multi-layer perceptron (MLP) with a mixture-of-experts (MoE) backbone and introduces a task-oriented perturbation mechanism. MENTOR outperforms state-of-the-art methods across three simulation benchmarks and achieves an average of 83% success rate on three challenging real-world robotic manipulation tasks, significantly surpassing the 32% success rate of the strongest existing model-free visual RL algorithm. These results underscore the importance of sample efficiency in advancing visual RL for real-world robotics. Experimental videos are available at https://suninghuang19.github.io/mentor_page/.
Cite
Text
Huang et al. "MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning." Proceedings of the 42nd International Conference on Machine Learning, 2025.Markdown
[Huang et al. "MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning." Proceedings of the 42nd International Conference on Machine Learning, 2025.](https://mlanthology.org/icml/2025/huang2025icml-mentor/)BibTeX
@inproceedings{huang2025icml-mentor,
title = {{MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning}},
author = {Huang, Suning and Zhang, Zheyu Aqa and Liang, Tianhai and Xu, Yihan and Kou, Zhehao and Lu, Chenhao and Xu, Guowei and Xue, Zhengrong and Xu, Huazhe},
booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
year = {2025},
pages = {26143-26161},
volume = {267},
url = {https://mlanthology.org/icml/2025/huang2025icml-mentor/}
}