{"id":"https://openalex.org/W4414360490","doi":"https://doi.org/10.24963/ijcai.2025/958","title":"A Finite-State Controller Based Offline Solver for Deterministic POMDPs","display_name":"A Finite-State Controller Based Offline Solver for Deterministic POMDPs","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360490","doi":"https://doi.org/10.24963/ijcai.2025/958"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/958","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109153721","display_name":"Andrejs Sch\u00fctz","orcid":"https://orcid.org/0000-0002-7597-5684"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Alex Schutz","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658703","display_name":"Yang You","orcid":"https://orcid.org/0000-0003-0125-0792"},"institutions":[{"id":"https://openalex.org/I47367911","display_name":"United Kingdom Atomic Energy Authority","ror":"https://ror.org/0361bwx64","country_code":"GB","type":"funder","lineage":["https://openalex.org/I2802373619","https://openalex.org/I4210110861","https://openalex.org/I47367911"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang You","raw_affiliation_strings":["UK Atomic Energy Authority"],"affiliations":[{"raw_affiliation_string":"UK Atomic Energy Authority","institution_ids":["https://openalex.org/I47367911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090942522","display_name":"Mat\u00edas Mattamala","orcid":"https://orcid.org/0000-0001-6128-7808"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mat\u00edas Mattamala","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064499277","display_name":"Ipek Caliskanelli","orcid":"https://orcid.org/0000-0002-2641-3570"},"institutions":[{"id":"https://openalex.org/I47367911","display_name":"United Kingdom Atomic Energy Authority","ror":"https://ror.org/0361bwx64","country_code":"GB","type":"funder","lineage":["https://openalex.org/I2802373619","https://openalex.org/I4210110861","https://openalex.org/I47367911"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ipek Caliskanelli","raw_affiliation_strings":["UK Atomic Energy Authority"],"affiliations":[{"raw_affiliation_string":"UK Atomic Energy Authority","institution_ids":["https://openalex.org/I47367911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053556869","display_name":"Bruno Lacerda","orcid":"https://orcid.org/0000-0003-0862-331X"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bruno Lacerda","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059686746","display_name":"Nick Hawes","orcid":"https://orcid.org/0000-0002-7556-6098"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nick Hawes","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5109153721"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31494873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8617","last_page":"8625"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9722999930381775,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9722999930381775,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10046","display_name":"Stability and Control of Uncertain Systems","score":0.9472000002861023,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11081","display_name":"Advanced Control Systems Design","score":0.909500002861023,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6686999797821045},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.6039999723434448},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5925999879837036},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5576000213623047},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5335999727249146},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.4927999973297119},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.45719999074935913},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.38690000772476196},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3813000023365021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7188000082969666},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6686999797821045},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.6039999723434448},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5925999879837036},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5576000213623047},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5335999727249146},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5178999900817871},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.4927999973297119},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3813000023365021},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C2985963534","wikidata":"https://www.wikidata.org/wiki/Q7603704","display_name":"State information","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2669000029563904},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.25130000710487366},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2025/958","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:34560af2-b4e1-4bed-82f3-d57c6c348077","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deterministic":[0],"partially":[1],"observable":[2],"Markov":[3],"decision":[4],"processes":[5],"(DetPOMDPs)":[6],"often":[7],"arise":[8],"in":[9,48,77],"planning":[10],"problems":[11,58],"where":[12],"the":[13,36,49,72,75],"agent":[14],"is":[15],"uncertain":[16],"about":[17],"its":[18],"environmental":[19],"state":[20],"but":[21],"can":[22],"act":[23],"and":[24],"observe":[25],"deterministically.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30],"propose":[31],"DetMCVI,":[32],"an":[33],"adaptation":[34],"of":[35,51,74],"Monte":[37],"Carlo":[38],"Value":[39],"Iteration":[40],"(MCVI)":[41],"algorithm":[42,76],"for":[43,67],"DetPOMDPs,":[44],"which":[45],"builds":[46],"policies":[47],"form":[50],"finite-state":[52],"controllers":[53],"(FSCs).":[54],"DetMCVI":[55],"solves":[56],"large":[57],"with":[59],"a":[60,78],"high":[61],"success":[62],"rate,":[63],"outperforming":[64],"existing":[65],"baselines":[66],"DetPOMDPs.":[68],"We":[69],"also":[70],"verify":[71],"performance":[73],"real-world":[79],"mobile":[80],"robot":[81],"forest":[82],"mapping":[83],"scenario.":[84]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}