Metraipolis › archive › dc_2a2043ea047f

Groupoid-Based Internal State Representations for Reinforcement Learning with Local Symmetries — arXiv:2609.13035

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13035
License (as archived)
CC0-1.0
Archived
2026-10-16T03:03:45.662Z
SHA-256 of the archived text
3c3890afc07966b85b87c78703fea7bf2eaf7fd1e0b6e49c882556db901213f6
Stable URL of this page
https://metraipolis.com/documento/dc_2a2043ea047f

How to cite

Groupoid-Based Internal State Representations for Reinforcement Learning with Local Symmetries — arXiv:2609.13035 — arXiv (en), https://arxiv.org/abs/2609.13035 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2a2043ea047f (Metraipolis archive dc_2a2043ea047f, sha256 3c3890afc07966b85b87c78703fea7bf2eaf7fd1e0b6e49c882556db901213f6)
BibTeX
@misc{dc2a2043ea047f,
  title = {Groupoid-Based Internal State Representations for Reinforcement Learning with Local Symmetries — arXiv:2609.13035},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13035},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2a2043ea047f; sha256 3c3890afc07966b85b87c78703fea7bf2eaf7fd1e0b6e49c882556db901213f6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13035. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Symmetries play a central role in reducing the complexity of reinforcement learning problems, yet most existing approaches rely on fixed group actions or predefined state abstractions. Classical reinforcement learning algorithms typically assume a globally structured Markov decision process with uniformly applicable actions and transitions, an assumption that limits their ability to exploit modularity and local, context-dependent regularities present in many realistic environments. We propose a reinforcement learning framework using groupoids to capture local, state-dependent symmetries and support the dy- namic discovery of equivalence structures during interaction. The agent maintains orbit representatives together with transporters that map raw states to canonical forms, enabling learning and decision-making to be performed in a symmetry-reduced space while preserving local distinctions. Empirical results demonstrate that the proposed groupoid-based approach improves sample efficiency and convergence in dense and large-scale environments exhibiting strong partial symmetries, yielding substantial performance gains over standard Q-learning. These findings show that dynamically exploiting local symmetry provides a practical and mathematically principled route to scalable and generalisable reinforcement learning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.13035 — 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 2026-10-16T02:51:27.970Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).