[{"external_id":{"arxiv":["2511.13134"]},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_updated":"2026-09-16T07:28:33Z","title":"Revealing POMDPs: Qualitative and quantitative analysis for parity objectives","article_processing_charge":"No","conference":{"location":"Singapore, Singapore","name":"AAAI: Conference on Artificial Intelligence","start_date":"2026-01-20","end_date":"2026-01-27"},"author":[{"last_name":"Asadi","first_name":"Ali","id":"02d96aae-000e-11ec-b801-cadd0a5eefbb","full_name":"Asadi, Ali"},{"full_name":"Chatterjee, Krishnendu","orcid":"0000-0002-4561-241X","id":"2E5DCA20-F248-11E8-B48F-1D18A9856A87","first_name":"Krishnendu","last_name":"Chatterjee"},{"full_name":"Lurie, David","id":"579a6c20-34cf-11f1-acbd-8c2f19cdb4da","first_name":"David","last_name":"Lurie"},{"full_name":"Saona Urmeneta, Raimundo J","orcid":"0000-0001-5103-038X","id":"BD1DF4C4-D767-11E9-B658-BC13E6697425","first_name":"Raimundo J","last_name":"Saona Urmeneta"}],"_id":"21722","scopus_import":"1","volume":40,"OA_type":"green","department":[{"_id":"KrCh"}],"date_published":"2026-03-14T00:00:00Z","ec_funded":1,"quality_controlled":"1","doi":"10.1609/aaai.v40i43.40932","status":"public","publication":"Proceedings of the AAAI Conference on Artificial Intelligence","month":"03","fulldoi":"https://doi.org/10.1609/aaai.v40i43.40932","intvolume":"        40","oa":1,"oa_version":"Preprint","type":"conference","arxiv":1,"issue":"43","date_created":"2026-04-12T22:01:52Z","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2511.13134","open_access":"1"}],"project":[{"name":"Formal Methods for Stochastic Models: Algorithms and Applications","grant_number":"863818","_id":"0599E47C-7A3F-11EA-A408-12923DDC885E","call_identifier":"H2020"},{"grant_number":"COE12","name":"Bilateral Artificial Intelligence (Chatterjee)","_id":"4029cfc7-b034-11f1-9e55-88ab2ff3b6ee"}],"citation":{"short":"A. Asadi, K. Chatterjee, D. Lurie, R.J. Saona Urmeneta, in:, Proceedings of the AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence, 2026, pp. 36146–36154.","chicago":"Asadi, Ali, Krishnendu Chatterjee, David Lurie, and Raimundo J Saona Urmeneta. “Revealing POMDPs: Qualitative and Quantitative Analysis for Parity Objectives.” In <i>Proceedings of the AAAI Conference on Artificial Intelligence</i>, 40:36146–54. Association for the Advancement of Artificial Intelligence, 2026. <a href=\"https://doi.org/10.1609/aaai.v40i43.40932\">https://doi.org/10.1609/aaai.v40i43.40932</a>.","mla":"Asadi, Ali, et al. “Revealing POMDPs: Qualitative and Quantitative Analysis for Parity Objectives.” <i>Proceedings of the AAAI Conference on Artificial Intelligence</i>, vol. 40, no. 43, Association for the Advancement of Artificial Intelligence, 2026, pp. 36146–54, doi:<a href=\"https://doi.org/10.1609/aaai.v40i43.40932\">10.1609/aaai.v40i43.40932</a>.","ama":"Asadi A, Chatterjee K, Lurie D, Saona Urmeneta RJ. Revealing POMDPs: Qualitative and quantitative analysis for parity objectives. In: <i>Proceedings of the AAAI Conference on Artificial Intelligence</i>. Vol 40. Association for the Advancement of Artificial Intelligence; 2026:36146-36154. doi:<a href=\"https://doi.org/10.1609/aaai.v40i43.40932\">10.1609/aaai.v40i43.40932</a>","ieee":"A. Asadi, K. Chatterjee, D. Lurie, and R. J. Saona Urmeneta, “Revealing POMDPs: Qualitative and quantitative analysis for parity objectives,” in <i>Proceedings of the AAAI Conference on Artificial Intelligence</i>, Singapore, Singapore, 2026, vol. 40, no. 43, pp. 36146–36154.","ista":"Asadi A, Chatterjee K, Lurie D, Saona Urmeneta RJ. 2026. Revealing POMDPs: Qualitative and quantitative analysis for parity objectives. Proceedings of the AAAI Conference on Artificial Intelligence. AAAI: Conference on Artificial Intelligence vol. 40, 36146–36154.","apa":"Asadi, A., Chatterjee, K., Lurie, D., &#38; Saona Urmeneta, R. J. (2026). Revealing POMDPs: Qualitative and quantitative analysis for parity objectives. In <i>Proceedings of the AAAI Conference on Artificial Intelligence</i> (Vol. 40, pp. 36146–36154). Singapore, Singapore: Association for the Advancement of Artificial Intelligence. <a href=\"https://doi.org/10.1609/aaai.v40i43.40932\">https://doi.org/10.1609/aaai.v40i43.40932</a>"},"publication_status":"published","acknowledgement":"This work was partially supported by the ANRT under the French CIFRE Ph.D program in collaboration between NyxAir and Paris-Dauphine University (Contract: CIFRE N° 2022/0513), by the French Agence Nationale de la Recherche (ANR) under reference ANR-21-CE40-\r\n0020 (CONVERGENCE project), by Austrian Science Fund (FWF) 10.55776/COE12, and by the ERC CoG 863818 (ForM-SMArt) grant.","language":[{"iso":"eng"}],"page":"36146-36154","publisher":"Association for the Advancement of Artificial Intelligence","abstract":[{"lang":"eng","text":"Partially observable Markov decision processes (POMDPs) are a central model for uncertainty in sequential decision making. The most basic objective is the reachability objective, where a target set must be eventually visited, and the more general parity objectives can model all omega-regular specifications. For such objectives, the computational analysis problems are the following: (a) qualitative analysis that asks whether the objective can be satisfied with probability 1 (almost-sure winning) or probability arbitrarily close to 1 (limit-sure winning); and (b) quantitative analysis that asks for the approximation of the optimal probability of satisfying the objective. For general POMDPs, almost-sure analysis for reachability objectives is EXPTIME-complete, but limit-sure and quantitative analyses for reachability objectives are undecidable; almost-sure, limit-sure, and quantitative analyses for parity objectives are all undecidable. A special class of POMDPs, called revealing POMDPs, has been studied recently in several works, and for this subclass the almost-sure analysis for parity objectives was shown to be EXPTIME-complete. In this work, we show that for revealing POMDPs the limit-sure analysis for parity objectives is EXPTIME-complete, and even the quantitative analysis for parity objectives can be achieved in EXPTIME."}],"OA_place":"repository","corr_author":"1","year":"2026","day":"14","publication_identifier":{"issn":["2159-5399"],"eissn":["2374-3468"]}}]