Equivariant Policy Learning

Follow this topic Ask about this topic

Latest papers

8 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Sample Complexity of Equivariant Reinforcement Learning
Sep 29, 2026Rayan Mazouz, Haibo Zhao, Chris Hillar +1Equivariant Policy Learning Reinforcement Learning
New Theory AI San Francisco, CA 94110
SAVLA: Symmetry-Aware Vision-Language-Action Models for Robotic Manipulation
Sep 15, 2026Junle Li, Weixian Waylon Li, Fuxiang Wu +2Language-Conditioned Robot Manipulation Vision-Language-Action Models
School of Informatics, University of Edinburgh, Scotland. · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China.
SKooP: Symmetric Koopman Predictions for Faster and More Generalizable Legged Robot Locomotion with Reinforcement Learning
Jul 13, 2026Evelyn D'Elia, Weishu Zhan, Giulio Turrisi +5Reinforcement Learning Koopman Operator Learning
Machine Learning and Optimisation, University of Manchester, M13 9PL Manchester, U.K. · Dynamic Legged Systems Lab, IIT, 16163 Genoa, Italy · Generative Bionics S.R.L, 16163 Genoa, Italy +3
Pix2Act: Image-Space Manipulation Policies with Equivariant Augmentation
Jul 13, 2026Haojie Huang, Linfeng Zhao, Haotian Liu +9Visuomotor Policy Learning Robotic Manipulation
1Northeastern University · 2Stanford University · University of Pennsylvania +2
Morphologically Equivariant Flow Matching for Bimanual Mobile Manipulation
May 12, 2026Max Siebenborn, Daniel Ordoñez Apraez, Sophie Lueth +4Flow Matching Mobile Manipulation
PEARL Lab, Dept. of Computer Science, TU Darmstadt, Germany · 2Istituto Italiano di Tecnologia, 3Hessian.AI, 4Robotics Institute Germany
Equivariant Multi-agent Reinforcement Learning for Multimodal Vehicle-to-Infrastructure Systems
Apr 8, 2026Charbel Bou Chaaya, Mehdi BennisEquivariant Policy Learning Reinforcement Learning
The authors are with the Centre for Wireless Communications, University of Oulu, Finland
EquiBim: Learning Symmetry-Equivariant Policy for Bimanual Manipulation
Mar 9, 2026Zhiyuan Zhang, Aditya Mohan, Seungho Han +3Equivariant Policy Learning Bimanual Robotic Manipulation
PRISM: Parallel Reward Integration with Symmetry for MORL
Feb 20, 2026Finn van der Knaap, Kejiang Qian, Zheng Xu +1Equivariant Policy Learning Reinforcement Learning
University of Edinburgh · Meta Superintelligence Labs.

Sep 29, 2026J/K move · Enter open · S save

Sample Complexity of Equivariant Reinforcement Learning

Rayan Mazouz, Haibo Zhao, Chris Hillar, Christian Shewmake

New Theory AI San Francisco, CA 94110

Equivariant Policy Learning Reinforcement Learning Sample-Efficient RL Robotic RL

Open paper AskPDF arXiv

Reinforcement learning (RL) is a powerful framework for robotic control, yet its practical application is often hindered by high sample complexity. This is particularly restrictive in physical domains where interaction data is costly. While the world often exhibits geometric and physical symmetries, standard RL algorithms typically fail to exploit this structure. In this paper, we demonstrate that exploiting group symmetries significantly reduces the sample complexity of RL. Focusing on finite-horizon Markov decision processes, we find that leveraging homomorphisms induced by group symmetries significantly reduces the theoretical upper and lower bounds on the number of environment interactions required to reach an optimal return. We further extend these bounds to continuous state and action spaces, providing corresponding sample-complexity guarantees under appropriate regularity assumptions. Beyond theory, we validate our findings through controlled experiments and demonstrate the advantages of symmetry-aware policy learning on high-dimensional continuous robotic simulations. Our results show that integrating symmetry into the learning pipeline yields substantial gains in sample efficiency and performance, offering a principled path toward more data-efficient robotics.