Copertina

MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Huang, Suning, Zhang, Zheyu, Liang, Tianhai, Xu, Yihan, Kou, Zhehao, Lu, Chenhao, Xu, Guowei, Xue, Zhengrong, Xu, Huazhe
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Robotics Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MoE-DP: An MoE-Enhanced Diffusion Policy for Robust Long-Horizon Robotic Manipulation with Skill Decomposition and Failure Recovery
di: Cheng, Baiye, et al.
Pubblicazione: (2025)

ArrayTac: A Closed-loop Piezoelectric Tactile Platform for Continuously Tunable Rendering of Shape, Stiffness, and Friction
di: Liang, Tianhai, et al.
Pubblicazione: (2026)

RiEMann: Near Real-Time SE(3)-Equivariant Robot Manipulation without Point Cloud Segmentation
di: Gao, Chongkai, et al.
Pubblicazione: (2024)

DemoSpeedup: Accelerating Visuomotor Policies via Entropy-Guided Demonstration Acceleration
di: Guo, Lingxiao, et al.
Pubblicazione: (2025)

Catch It! Learning to Catch in Flight with Mobile Dexterous Hands
di: Zhang, Yuanhang, et al.
Pubblicazione: (2024)

DittoGym: Learning to Control Soft Shape-Shifting Robots
di: Huang, Suning, et al.
Pubblicazione: (2024)

AffordGen: Generating Diverse Demonstrations for Generalizable Object Manipulation with Afford Correspondence
di: Zhang, Jiawei, et al.
Pubblicazione: (2026)

HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation
di: Yuan, Zhecheng, et al.
Pubblicazione: (2025)

DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learning
di: Xue, Zhengrong, et al.
Pubblicazione: (2025)

ArrayBot: Reinforcement Learning for Generalizable Distributed Manipulation through Touch
di: Xue, Zhengrong, et al.
Pubblicazione: (2023)

Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization
di: Lei, Kun, et al.
Pubblicazione: (2023)

H$^3$DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning
di: Lu, Yiyang, et al.
Pubblicazione: (2025)

DA-MMP: Learning Coordinated and Accurate Throwing with Dynamics-Aware Motion Manifold Primitives
di: Chu, Chi, et al.
Pubblicazione: (2025)

MoRI: Mixture of RL and IL Experts for Long-Horizon Manipulation Tasks
di: Xu, Yaohang, et al.
Pubblicazione: (2026)

Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation
di: Pan, Yiyuan, et al.
Pubblicazione: (2025)

Scene-Adaptive Motion Planning with Explicit Mixture of Experts and Interaction-Oriented Optimization
di: Zhu, Hongbiao, et al.
Pubblicazione: (2025)

Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning
di: Yu, Dongjie, et al.
Pubblicazione: (2026)

Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation
di: Ju, Yuanchen, et al.
Pubblicazione: (2024)

Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning
di: Yuan, Zhecheng, et al.
Pubblicazione: (2024)

UniDex: A Robot Foundation Suite for Universal Dexterous Hand Control from Egocentric Human Videos
di: Zhang, Gu, et al.
Pubblicazione: (2026)

FoundationGrasp: Generalizable Task-Oriented Grasping with Foundation Models
di: Tang, Chao, et al.
Pubblicazione: (2024)

DexTOG: Learning Task-Oriented Dexterous Grasp with Language
di: Zhang, Jieyi, et al.
Pubblicazione: (2025)

DTactive: A Vision-Based Tactile Sensor with Active Surface
di: Xu, Jikai, et al.
Pubblicazione: (2024)

FACET: Force-Adaptive Control via Impedance Reference Tracking for Legged Robots
di: Xu, Botian, et al.
Pubblicazione: (2025)

FARM: Frame-Accelerated Augmentation and Residual Mixture-of-Experts for Physics-Based High-Dynamic Humanoid Control
di: Jing, Tan, et al.
Pubblicazione: (2025)

Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation
di: Xue, Han, et al.
Pubblicazione: (2025)

DOGlove: Dexterous Manipulation with a Low-Cost Open-Source Haptic Force Feedback Glove
di: Zhang, Han, et al.
Pubblicazione: (2025)

Learning Visual Quadrupedal Loco-Manipulation from Demonstrations
di: He, Zhengmao, et al.
Pubblicazione: (2024)

Continual Adaptation for Autonomous Driving with the Mixture of Progressive Experts Network
di: Cui, Yixin, et al.
Pubblicazione: (2025)

Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization
di: Wang, Ye, et al.
Pubblicazione: (2026)

Diffusion Reward: Learning Rewards via Conditional Video Diffusion
di: Huang, Tao, et al.
Pubblicazione: (2023)

A Visual Reinforcement Learning-Based Separate Primitive Policy for Peg-in-Hole Tasks
di: Xu, Zichun, et al.
Pubblicazione: (2025)

ExpertAD: Enhancing Autonomous Driving Systems with Mixture of Experts
di: Jiang, Haowen, et al.
Pubblicazione: (2025)

Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation
di: Li, Huanyu, et al.
Pubblicazione: (2026)

Quadruped Parkour Learning: Sparsely Gated Mixture of Experts with Visual Input
di: Ziegltrum, Michael, et al.
Pubblicazione: (2026)

Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLA
di: Tang, Tutian, et al.
Pubblicazione: (2026)

Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping
di: Huang, Ziye, et al.
Pubblicazione: (2024)

LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks
di: Yang, Yi, et al.
Pubblicazione: (2025)

Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation
di: Qi, Yu, et al.
Pubblicazione: (2025)

Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks
di: Joshi, Viraj, et al.
Pubblicazione: (2025)