{"tmp":{"short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"file":[{"creator":"dernst","file_name":"2025_UAI_AsadiAli.pdf","checksum":"1a37ebe7ba73ab6985765bf0d17a0acc","file_id":"20315","date_updated":"2025-09-09T08:19:41Z","relation":"main_file","access_level":"open_access","file_size":307458,"success":1,"content_type":"application/pdf","date_created":"2025-09-09T08:19:41Z"}],"abstract":[{"text":"A standard model that arises in several applications in sequential decision-making is partially observable Markov decision processes (POMDPs) where a decision-making agent interacts with an uncertain environment. A basic objective in POMDPs is the reachability objective, where given a target set of states, the goal is to eventually arrive at one of them.\r\n\r\nThe limit-sure problem asks whether reachability can be ensured with probability arbitrarily close to 1. In general, the limit-sure reachability problem for POMDPs is undecidable. However, in many practical cases, the most relevant question is the existence of policies with a small amount of memory. In this work, we study the limit-sure reachability problem for POMDPs with a fixed amount of memory. We establish that the computational complexity of the problem is NP-complete.","lang":"eng"}],"intvolume":"       286","publisher":"ML Research Press","publication":"The 41st Conference on Uncertainty in Artificial Intelligence","volume":286,"ec_funded":1,"has_accepted_license":"1","OA_place":"publisher","oa_version":"Published Version","arxiv":1,"corr_author":"1","month":"07","conference":{"name":"UAI: Conference on Uncertainty in Artificial Intelligence","end_date":"2025-07-25","start_date":"2025-07-21","location":"Rio de Janeiro, Brazil"},"acknowledgement":"This research was partially supported by Austrian Science Fund (FWF) 10.55776/COE12, the support of the French Agence Nationale de la Recherche (ANR) under reference ANR-21-CE40-0020 (CONVERGENCE project), and the ERC CoG 863818 (ForM-SMArt) grant.","_id":"20297","alternative_title":["PMLR"],"scopus_import":"1","oa":1,"publication_status":"published","OA_type":"diamond","title":"Limit-sure reachability for small memory policies in POMDPs is NP-complete","external_id":{"arxiv":["2412.00941"]},"file_date_updated":"2025-09-09T08:19:41Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","status":"public","page":"238-247","quality_controlled":"1","language":[{"iso":"eng"}],"article_processing_charge":"No","author":[{"last_name":"Asadi","full_name":"Asadi, Ali","id":"02d96aae-000e-11ec-b801-cadd0a5eefbb","first_name":"Ali"},{"full_name":"Chatterjee, Krishnendu","last_name":"Chatterjee","orcid":"0000-0002-4561-241X","id":"2E5DCA20-F248-11E8-B48F-1D18A9856A87","first_name":"Krishnendu"},{"first_name":"Raimundo J","id":"BD1DF4C4-D767-11E9-B658-BC13E6697425","orcid":"0000-0001-5103-038X","last_name":"Saona Urmeneta","full_name":"Saona Urmeneta, Raimundo J"},{"full_name":"Shafiee, Ali","last_name":"Shafiee","id":"2783031a-7378-11f0-b2d0-f17f1db2ebad","first_name":"Ali"}],"type":"conference","day":"01","project":[{"call_identifier":"H2020","grant_number":"863818","name":"Formal Methods for Stochastic Models: Algorithms and Applications","_id":"0599E47C-7A3F-11EA-A408-12923DDC885E"}],"citation":{"short":"A. Asadi, K. Chatterjee, R.J. Saona Urmeneta, A. Shafiee, in:, The 41st Conference on Uncertainty in Artificial Intelligence, ML Research Press, 2025, pp. 238–247.","ista":"Asadi A, Chatterjee K, Saona Urmeneta RJ, Shafiee A. 2025. Limit-sure reachability for small memory policies in POMDPs is NP-complete. The 41st Conference on Uncertainty in Artificial Intelligence. UAI: Conference on Uncertainty in Artificial Intelligence, PMLR, vol. 286, 238–247.","apa":"Asadi, A., Chatterjee, K., Saona Urmeneta, R. J., &#38; Shafiee, A. (2025). Limit-sure reachability for small memory policies in POMDPs is NP-complete. In <i>The 41st Conference on Uncertainty in Artificial Intelligence</i> (Vol. 286, pp. 238–247). Rio de Janeiro, Brazil: ML Research Press.","ieee":"A. Asadi, K. Chatterjee, R. J. Saona Urmeneta, and A. Shafiee, “Limit-sure reachability for small memory policies in POMDPs is NP-complete,” in <i>The 41st Conference on Uncertainty in Artificial Intelligence</i>, Rio de Janeiro, Brazil, 2025, vol. 286, pp. 238–247.","chicago":"Asadi, Ali, Krishnendu Chatterjee, Raimundo J Saona Urmeneta, and Ali Shafiee. “Limit-Sure Reachability for Small Memory Policies in POMDPs Is NP-Complete.” In <i>The 41st Conference on Uncertainty in Artificial Intelligence</i>, 286:238–47. ML Research Press, 2025.","ama":"Asadi A, Chatterjee K, Saona Urmeneta RJ, Shafiee A. Limit-sure reachability for small memory policies in POMDPs is NP-complete. In: <i>The 41st Conference on Uncertainty in Artificial Intelligence</i>. Vol 286. ML Research Press; 2025:238-247.","mla":"Asadi, Ali, et al. “Limit-Sure Reachability for Small Memory Policies in POMDPs Is NP-Complete.” <i>The 41st Conference on Uncertainty in Artificial Intelligence</i>, vol. 286, ML Research Press, 2025, pp. 238–47."},"publication_identifier":{"eissn":["2640-3498"]},"date_published":"2025-07-01T00:00:00Z","ddc":["000"],"department":[{"_id":"KrCh"},{"_id":"GradSch"}],"date_updated":"2025-09-09T08:21:45Z","date_created":"2025-09-07T22:01:34Z","year":"2025"}