Multi-Goal Dexterous Hand Manipulation using Probabilistic Model-based Reinforcement Learning
On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation
Abstract (arXiv)
This paper tackles the challenge of learning multi-goal dexterous hand manipulation tasks using model-based Reinforcement Learning. We propose Goal-Conditioned Probabilistic Model Predictive Control (GC-PMPC) by designing probabilistic neural network ensembles to describe the high-dimensional dexterous hand dynamics and introducing an asynchronous MPC policy to meet the control frequency requirements in real-world dexterous hand systems. Extensive evaluations on four simulated Shadow Hand manipulation scenarios with randomly generated goals demonstrate GC-PMPC's superior performance over state-of-the-art baselines. It successfully drives a cable-driven Dexterous hand, DexHand 021 with 12 Active DOFs and 5 tactile sensors, to learn manipulating a cubic die to three goal poses within approximately 80 minutes of interactions, demonstrating exceptional learning efficiency and control performance on a cost-effective dexterous hand platform.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 19 of its 25 references that are in the map. First posted on arXiv 30 Apr 2025.
Builds on
19 of 25 references.
References · 19
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
- 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
- 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 774
- 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 773
- 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 715
- 2018Learning Dexterous In-Hand Manipulationcited by 687
- 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
- 2022Temporal Difference Learning for Model Predictive Controlcited by 397
- 2018How Does Batch Normalization Help Optimization?cited by 357
- 2019Deep Dynamics Models for Learning Dexterous Manipulationcited by 206
- 2022Goal-Conditioned Reinforcement Learning: Problems and Solutionscited by 158
- 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 117
7 more
- 2022Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapescited by 101
- 2018Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Costcited by 84
- 2023For SALE: State-Action Representation Learning for Deep Reinforcement Learningcited by 75
- 2023Sampling-based Exploration for Reinforcement Learning of Dexterous Manipulationcited by 24
- 2025Dexterous Manipulation through Imitation Learning: A Surveycited by 21
- 2023Dexterous In-Hand Manipulation of Slender Cylindrical Objects through Deep Reinforcement Learning with Tactile Sensingcited by 14
- 2021MapGo: Model-Assisted Policy Optimization for Goal-Oriented Taskscited by 13
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Real-World Reinforcement Learning with MPC Scaffolding for Dexterous Manipulation
- 2024Sampling-Based Model Predictive Control for Dexterous Manipulation on a Biomimetic Tendon-Driven Hand
- 2024Dexterous Manipulation Based on Prior Dexterous Grasp Pose Knowledge
- 2026LAMP: Latent Motion Prior-Guided Real-World Learning for Dexterous Hand Manipulation
- 2024Benchmarking Reinforcement Learning Methods for Dexterous Robotic Manipulation with a Three-Fingered Gripper
- 2024Object-Centric Dexterous Manipulation from Human Motion Data
- 2025Model-Based Lookahead Reinforcement Learning for in-hand manipulation
- 2025Hierarchical Reinforcement Learning for Articulated Tool Manipulation with Multifingered Hand