Metraipolis › archive › dc_64bb66ef4b2f

Categorical Internalisation of Environmental Groupoids for Generalisable POMDP Solving — arXiv:2609.27745

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.27745
License (as archived): CC0-1.0
Archived: 2026-10-08T09:11:31.864Z
SHA-256 of the archived text: 91b07dbca38ef84d205964c4b46389b0defc54457a34f1180774bceafe97f4a7
Stable URL of this page: https://metraipolis.com/documento/dc_64bb66ef4b2f

How to cite

Categorical Internalisation of Environmental Groupoids for Generalisable POMDP Solving — arXiv:2609.27745 — arXiv (en), https://arxiv.org/abs/2609.27745 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_64bb66ef4b2f (Metraipolis archive dc_64bb66ef4b2f, sha256 91b07dbca38ef84d205964c4b46389b0defc54457a34f1180774bceafe97f4a7)

BibTeX

@misc{dc64bb66ef4b2f,
  title = {Categorical Internalisation of Environmental Groupoids for Generalisable POMDP Solving — arXiv:2609.27745},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27745},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_64bb66ef4b2f; sha256 91b07dbca38ef84d205964c4b46389b0defc54457a34f1180774bceafe97f4a7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27745. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper advocates category theory as a practical framework for structuring and improving rein- forcement learning in high-dimensional, partially observable environments. We model symmetries between environmental states by partitioning the state space into equivalence classes induced by sym- metry orbits, and organise each such class as a groupoid with a designated canonical representative. This allows the agent to share what it learns across many similar environmental states simultaneously, rather than treating every orientation or position as an entirely new problem. Learning is thus carried out on a symmetry-reduced state space with each orbit represented once, preserving structure while eliminating redundancy and improving sample efficiency. We implement this framework within standard reinforcement learning pipelines and evaluate two different approaches on partially observable benchmarks, demonstrating that orbit-based partitioning yields consistent performance improvements in environments exhibiting latent symmetry. Beyond these empirical results, our approach illustrates how categorical structure provides a principled bridge between abstract reinforcement learning formulations and their computational application, thereby establishing a pathway toward more structured and scalable learning systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.27745 — 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 2026-10-08T08:13:26.527Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).