Metraipolis › archive › dc_f1bc2d4decf3
Sample Complexity of Equivariant Reinforcement Learning — arXiv:2609.36421
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36421
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:32:37.291Z
- SHA-256 of the archived text
4fbe628589df75dcc62c23d961d6181e550a0e86cf5d003dbad34181cf522994- Stable URL of this page
https://metraipolis.com/documento/dc_f1bc2d4decf3
How to cite
Sample Complexity of Equivariant Reinforcement Learning — arXiv:2609.36421 — arXiv (en), https://arxiv.org/abs/2609.36421 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f1bc2d4decf3 (Metraipolis archive dc_f1bc2d4decf3, sha256 4fbe628589df75dcc62c23d961d6181e550a0e86cf5d003dbad34181cf522994)
BibTeX
@misc{dcf1bc2d4decf3,
title = {Sample Complexity of Equivariant Reinforcement Learning — arXiv:2609.36421},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36421},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f1bc2d4decf3; sha256 4fbe628589df75dcc62c23d961d6181e550a0e86cf5d003dbad34181cf522994},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36421. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG). Categorie arXiv: Computational Complexity (cs.CC) ; Machine Learning (cs.LG); Group Theory (math.GR). Pagina del lavoro: https://arxiv.org/abs/2609.36421 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T16:59:48.494Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).