Metraipolis › archive › dc_517bb5830378

Inner-Learning: From Hand-Coded Beliefs to Declarative Knowledge in Trick-Taking Games — arXiv:2610.38304

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.38304
License (as archived)
CC0-1.0
Archived
2026-10-31T06:08:50.842Z
SHA-256 of the archived text
63add7aa37c16e2c365d340c72a46fb3b6e0da7b011c0ddbd579a628a0405702
Stable URL of this page
https://metraipolis.com/documento/dc_517bb5830378

How to cite

Inner-Learning: From Hand-Coded Beliefs to Declarative Knowledge in Trick-Taking Games — arXiv:2610.38304 — arXiv (en), https://arxiv.org/abs/2610.38304 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_517bb5830378 (Metraipolis archive dc_517bb5830378, sha256 63add7aa37c16e2c365d340c72a46fb3b6e0da7b011c0ddbd579a628a0405702)
BibTeX
@misc{dc517bb5830378,
  title = {Inner-Learning: From Hand-Coded Beliefs to Declarative Knowledge in Trick-Taking Games — arXiv:2610.38304},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38304},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_517bb5830378; sha256 63add7aa37c16e2c365d340c72a46fb3b6e0da7b011c0ddbd579a628a0405702},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38304. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present a declarative approach to belief-state modeling in trick-taking card games. Starting from a state-of-the-art Skat player, we automatically extract its hand-coded inference rules into a domain-specific language built on the primitive $\neg\mathsf{holds}(P,C)$, denoting that player $P$ cannot hold any card in set $C$. Round-trip code generation verifies that the extracted rules reproduce the original engine's intended behavior, up to three audited bugs in the original that the declarative engine corrects. We then grow the rule base through symmetric derivation and annotation of an expert strategy document---unifying code, symmetry, and expertise in one representation. We extend the knowledge representation with \emph{cardinality constraints}: at-most-$k$ and at-least-$k$ bounds on the cards a player holds from a named group, expressed in the same declarative language and enforced at world-generation time. Confidence parameters connect symbolic rules to probabilistic belief updates. Self-play evaluation shows the declarative engine measurably improving winning percentage and score over the original hand-coded engine, with the extracted rules, the human-annotated rules, and the cardinality constraints each contributing to the effect.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.38304 — 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 2026-10-31T06:07:08.466Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).