# Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping

arXiv: https://arxiv.org/abs/2410.02475 · HTML: https://mlsanity.com/paper/2410.02475/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in MoE in reinforcement learning and robotics, one of 12 directions in Mixture-of-experts.
- Builds on 37 of its 49 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Placed in

- Mixture-of-experts / [MoE in reinforcement learning and robotics](https://mlsanity.com/moe/moe-in-reinforcement-learning-and-robotics/)

## Builds on (most cited first, 30 of 37)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [DexYCB: A Benchmark for Capturing Hand Grasping of Objects](https://mlsanity.com/paper/2104.04631/) (2021)
- [Residual Reinforcement Learning for Robot Control](https://mlsanity.com/paper/1812.03201/) (2018)
- [MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training](https://mlsanity.com/paper/2403.09611/) (2024)
- [DexMV: Imitation Learning for Dexterous Manipulation from Human Videos](https://mlsanity.com/paper/2108.05877/) (2021)
- [Residual Policy Learning](https://mlsanity.com/paper/1812.06298/) (2018)
- [Hand-Object Contact Consistency Reasoning for Human Grasps Generation](https://mlsanity.com/paper/2104.03304/) (2021)
- [DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation](https://mlsanity.com/paper/2210.02697/) (2022)
- [UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy](https://mlsanity.com/paper/2303.00938/) (2023)
- [MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies](https://mlsanity.com/paper/1905.09808/) (2019)
- [UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning](https://mlsanity.com/paper/2304.00464/) (2023)
- [DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video](https://mlsanity.com/paper/2202.00164/) (2022)
- [ContactGrasp: Functional Multi-finger Grasp Synthesis from Contact](https://mlsanity.com/paper/1904.03754/) (2019)
- [DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation](https://mlsanity.com/paper/2211.09423/) (2022)
- [LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning](https://mlsanity.com/paper/2309.06440/) (2023)
- [Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards](https://mlsanity.com/paper/1906.05841/) (2019)
- [TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction](https://mlsanity.com/paper/2405.10315/) (2024)
- [Dexterous Functional Grasping](https://mlsanity.com/paper/2312.02975/) (2023)
- [Physics-Based Dexterous Manipulations with Estimated Hand Poses and Residual Reinforcement Learning](https://mlsanity.com/paper/2008.03285/) (2020)
- [Residual Reinforcement Learning from Demonstrations](https://mlsanity.com/paper/2106.08050/) (2021)
- [Residual Learning from Demonstration: Adapting DMPs for Contact-rich Manipulation](https://mlsanity.com/paper/2008.07682/) (2020)
- [GraspGF: Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping](https://mlsanity.com/paper/2309.06038/) (2023)

## Built on by (most cited first, 10 of 10)

- [Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos](https://mlsanity.com/paper/2507.15597/) (2025)
- [ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning](https://mlsanity.com/paper/2503.21860/) (2025)
- [Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills](https://mlsanity.com/paper/2503.12533/) (2025)
- [Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos](https://mlsanity.com/paper/2512.13080/) (2025)
- [Universal Dexterous Functional Grasping via Demonstration-Editing Reinforcement Learning](https://mlsanity.com/paper/2512.13380/) (2025)
- [Efficient Real-World Autonomous Racing via Attenuated Residual Policy Optimization](https://mlsanity.com/paper/2603.12960/) (2026)
- [EAGG: Embodiment-Aligned Grasp Generation via Geometry-Aware Graph Conditioning](https://mlsanity.com/paper/2606.18092/) (2026)
- [SECOND-Grasp: Semantic Contact-guided Dexterous Grasping](https://mlsanity.com/paper/2605.13117/) (2026)
- [V2P-Manip: Learning Dexterous Manipulation from Monocular Human Videos](https://mlsanity.com/paper/2606.16436/) (2026)
- [ResSafe: Learning Safety Filtering with Residual Reinforcement Learning for Humanoids](https://mlsanity.com/paper/2609.15988/) (2026)

## Abstract (arXiv)

Universal dexterous grasping across diverse objects presents a fundamental yet formidable challenge in robot learning. Existing approaches using reinforcement learning (RL) to develop policies on extensive object datasets face critical limitations, including complex curriculum design for multi-task learning and limited generalization to unseen objects. To overcome these challenges, we introduce ResDex, a novel approach that integrates residual policy learning with a mixture-of-experts (MoE) framework. ResDex is distinguished by its use of geometry-unaware base policies that are efficiently acquired on individual objects and capable of generalizing across a wide range of unseen objects. Our MoE framework incorporates several base policies to facilitate diverse grasping styles suitable for various objects. By learning residual actions alongside weights that combine these base policies, ResDex enables efficient multi-task RL for universal dexterous grasping. ResDex achieves state-of-the-art performance on the DexGraspNet dataset comprising 3,200 objects with an 88.8% success rate. It exhibits no generalization gap with unseen objects and demonstrates superior training efficiency, mastering all tasks within only 12 hours on a single GPU.