{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T12:18:43Z","timestamp":1794917923074,"version":"4.9.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:p>Partially observable Markov decision processes (POMDPs) form a prominent model for uncertainty in sequential decision making. We are interested in constructing algorithms with theoretical guarantees to determine whether the agent has a strategy ensuring a given specification with probability 1. This well-studied problem is known to be undecidable already for very simple omega-regular objectives, because of the difficulty of reasoning on uncertain events.\nWe introduce a revelation mechanism which restricts information loss by requiring that, almost surely, the agent has eventually full information about the current state. Our main technical results are to construct exact algorithms for two classes of POMDPs called weakly and strongly revealing. Importantly, the decidable cases reduce to the analysis of a finite belief-support Markov decision process. This yields a conceptually simple and exact algorithm for a large class of POMDPs.<\/jats:p>","DOI":"10.24963\/ijcai.2026\/916","type":"proceedings-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T22:01:13Z","timestamp":1789596073000},"page":"8221-8226","source":"Crossref","is-referenced-by-count":0,"title":["Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives (Extended Abstract)"],"prefix":"10.24963","author":[{"given":"Marius","family":"Belly","sequence":"first","affiliation":[{"name":"LaBRI, CNRS, University of Bordeaux"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nathana\u00ebl","family":"Fijalkow","sequence":"additional","affiliation":[{"name":"LaBRI, CNRS, University of Bordeaux"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hugo","family":"Gimbert","sequence":"additional","affiliation":[{"name":"LaBRI, CNRS, University of Bordeaux"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Horn","sequence":"additional","affiliation":[{"name":"IRIF, CNRS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillermo A.","family":"Perez","sequence":"additional","affiliation":[{"name":"University of Antwerp"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierre","family":"Vandenhove","sequence":"additional","affiliation":[{"name":"University of Mons"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Thirty-Fifth International Joint Conference on Artificial Intelligence {IJCAI-26}","theme":"Artificial Intelligence","location":"Bremen, Germany","acronym":"IJCAI-2026","number":"35","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2026,8,15]]},"end":{"date-parts":[[2026,8,21]]}},"container-title":["Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T11:32:24Z","timestamp":1794915144000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2026\/916"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2026\/916","relation":{},"subject":[],"published":{"date-parts":[[2026,9]]}}}