aiqbench analysis
EigenDEXplore addresses the high-dimensional optimization challenge in dexterous robotics by structuring reinforcement learning exploration using human-derived motion priors. The method induces correlated joint perturbations along specific eigenvectors without altering the action representation, significantly improving performance in grasping and contact-rich tasks compared to standard independent noise strategies. This advancement demonstrates how leveraging human data can effectively guide AI agents to discover complex coordinated behaviors that are otherwise difficult to find through random search alone.
EigenDEXplore: Structured Exploration for Dexterous Manipulation with Human Priors
arXiv:2610.07681v1 Announce Type: cross Abstract: Dexterous manipulation poses a challenging high-dimensional optimization problem, as useful behaviors require coordinated motion across many hand joints. In reinforcement learning (RL) and sampling-based trajectory optimization, exploration commonly relies on independent robot joint perturbations, making coordinated behaviors difficult to discover. Prior work reduces this search space for grasp learning using low-dimensional spaces of coordinated joint motions learned from human hand data, but this restricts the expressivity required for general manipulation. Some combine learned and joint-space actions to restore expressivity, but this increases dimensionality and introduces redundancy. We study these effects across diverse manipulation settings, varying action dimensionality, exploration strategy, and the source of human data. Our experiments suggest that human-motion priors are most effective when used to structure exploration rather than change the action representation. Motivated by this finding, we propose EigenDEXplore, which induces correlated exploration by adding perturbations along human-derived eigenvectors to independent joint-space noise, leaving the action space unchanged. Across multiple dexterous hands, EigenDEXplore consistently outperforms joint-space and learned action-space baselines in grasping, in-hand reorientation, and contact-rich manipulation. These gains span unstructured and reference-guided RL, trajectory optimization, and sim-to-real deployment, and are largest in settings with less reward shaping and curriculum design.
Abstract:Dexterous manipulation poses a challenging high-dimensional optimization problem, as useful behaviors require coordinated motion across many hand joints. In reinforcement learning (RL) and sampling-based trajectory optimization, exploration commonly relies on independent robot joint perturbations, making coordinated behaviors difficult to discover. Prior work reduces this search space for grasp learning using low-dimensional spaces of coordinated joint motions learned from human hand data, but this restricts the expressivity required for general manipulation. Some combine learned and joint-space actions to restore expressivity, but this increases dimensionality and introduces redundancy. We study these effects across diverse manipulation settings, varying action dimensionality, exploration strategy, and the source of human data. Our experiments suggest that human-motion priors are most effective when used to structure exploration rather than change the action representation. Motivated by this finding, we propose EigenDEXplore, which induces correlated exploration by adding perturbations along human-derived eigenvectors to independent joint-space noise, leaving the action space unchanged. Across multiple dexterous hands, EigenDEXplore consistently outperforms joint-space and learned action-space baselines in grasping, in-hand reorientation, and contact-rich manipulation. These gains span unstructured and reference-guided RL, trajectory optimization, and sim-to-real deployment, and are largest in settings with less reward shaping and curriculum design.
15 pages, 12 figures. Project page: this https URL
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2610.07681 [cs.RO]
(or arXiv:2610.07681v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.07681 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 299 words
Related coverage
2026 BAIR Graduate Showcase
BAIR Blog · Jul 1, 2026
The Machines that Make the Machines
NVIDIA · Oct 7, 2026
Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?
arXiv · Sep 9, 2026
Real-World Reinforcement Learning with MPC Scaffolding for Dexterous Manipulation
arXiv · Sep 15, 2026