MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning
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/.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep Reinforcement LearningMixture-of-ExpertsReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Many Hands Make Light Work: Task-Oriented Dialogue System with Module-Based Mixture-of-Experts
Task-oriented dialogue systems are broadly used in virtual assistants and other automated services, providing interfaces between users and machines to facilitate specific tasks. Nowadays, task-oriented dialogue systems h…
Dialogue State TrackingMixture-of-ExpertsResponse GenerationTask-Oriented Dialogue SystemsAPPLE: Adversarial Privacy-aware Perturbations on Latent Embedding for Unfairness Mitigation
Ensuring fairness in deep-learning-based segmentors is crucial for health equity. Much effort has been dedicated to mitigating unfairness in the training datasets or procedures. However, with the increasing prevalence of…
DecoderFairnessMedical Image AnalysisLLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring System
Intelligent Tutoring Systems (ITSs) have revolutionized education by offering personalized learning experiences. However, as goal-oriented learning, which emphasizes efficiently achieving specific objectives, becomes inc…
RoME: Robust Mixture of Low-Rank Experts against Multiple Adversarial Perturbations
Multi-perturbation adversarial training (MAT) aims to achieve robustness against multiple $\ell_p$ perturbations but suffers from robustness trade-offs between different threats. To address this, we employ a mixture of e…
Beyond Factual QA: Mentorship-Oriented Question Answering over Long-Form Multilingual Content
Question answering systems are typically evaluated on factual correctness, yet many real-world applications-such as education and career guidance-require mentorship: responses that provide reflection and guidance. Existi…
Question Answering