Metraipolis › archive › dc_950f4562feb5

Neurosymbolic Action Model Learning under Partial Observability — arXiv:2609.25766

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25766
License (as archived)
CC0-1.0
Archived
2026-10-08T13:45:17.096Z
SHA-256 of the archived text
13ca84f2c41e87fd7d73529868a4823bba7a1eca37d9bcec4e68ba4a6f629171
Stable URL of this page
https://metraipolis.com/documento/dc_950f4562feb5

How to cite

Neurosymbolic Action Model Learning under Partial Observability — arXiv:2609.25766 — arXiv (en), https://arxiv.org/abs/2609.25766 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_950f4562feb5 (Metraipolis archive dc_950f4562feb5, sha256 13ca84f2c41e87fd7d73529868a4823bba7a1eca37d9bcec4e68ba4a6f629171)
BibTeX
@misc{dc950f4562feb5,
  title = {Neurosymbolic Action Model Learning under Partial Observability — arXiv:2609.25766},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25766},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_950f4562feb5; sha256 13ca84f2c41e87fd7d73529868a4823bba7a1eca37d9bcec4e68ba4a6f629171},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25766. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI planning studies how an agent can reach a goal by executing a sequence of actions. To plan correctly, the agent needs an action model describing when each action can be executed and how it changes the world. Constructing such models by hand requires domain expertise, and can be costly and error-prone. Action models can instead be learned from available data using existing neurosymbolic approaches, but they currently assume access to complete traces of fully observable images . These approaches fail to learn action models under partial observability where some of the images might not be present or are not fully informative of the current state of the world. Hence, this paper proposes NeSyAM, a novel neurosymbolic modeling paradigm for action model learning under partial observability. In addition, the paper presents a unified variational framework for theoretically analysing the limitations of existing methods compared to our proposed approach. NeSyAM is then tested extensively on six visual planning domains and three observation regimes to show it consistently recovers relevant parts of the true action model under partial observability.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.25766 — 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 2026-10-08T13:18:38.121Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).