{"id":"https://openalex.org/W4362500618","doi":"https://doi.org/10.1109/tac.2023.3264177","title":"Entropy-Regularized Partially Observed Markov Decision Processes","display_name":"Entropy-Regularized Partially Observed Markov Decision Processes","publication_year":2023,"publication_date":"2023-04-03","ids":{"openalex":"https://openalex.org/W4362500618","doi":"https://doi.org/10.1109/tac.2023.3264177"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2023.3264177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2023.3264177","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-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/A5078645226","display_name":"Timothy L. Molloy","orcid":"https://orcid.org/0000-0002-6797-5617"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Timothy L. Molloy","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, University of Melbourne, Melbourne, VIC, Australia","CIICADA Lab, School of Engineering, The Australian National University (ANU), Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Melbourne, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"CIICADA Lab, School of Engineering, The Australian National University (ANU), Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021984276","display_name":"Girish N. Nair","orcid":"https://orcid.org/0000-0002-4342-209X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Girish N. Nair","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, University of Melbourne, Melbourne, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Melbourne, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078645226"],"corresponding_institution_ids":["https://openalex.org/I118347636","https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":0.9143,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7340385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"69","issue":"1","first_page":"379","last_page":"386"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.8712000250816345,"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":0.8712000250816345,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.869700014591217,"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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.8141239881515503},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5939759016036987},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5265665054321289},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5206631422042847},{"id":"https://openalex.org/keywords/joint-entropy","display_name":"Joint entropy","score":0.5192165970802307},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.49452659487724304},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4609883427619934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4466882348060608},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4440818428993225},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4340575933456421},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4311067461967468},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3544437885284424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23756438493728638},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15790948271751404},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09258416295051575},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08533236384391785},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.07296249270439148}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.8141239881515503},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5939759016036987},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5265665054321289},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5206631422042847},{"id":"https://openalex.org/C106752470","wikidata":"https://www.wikidata.org/wiki/Q1364826","display_name":"Joint entropy","level":3,"score":0.5192165970802307},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.49452659487724304},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4609883427619934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4466882348060608},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4440818428993225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4340575933456421},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4311067461967468},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3544437885284424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23756438493728638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15790948271751404},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09258416295051575},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08533236384391785},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07296249270439148},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2023.3264177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2023.3264177","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1010395839","display_name":null,"funder_award_id":"AUSMURIB000001","funder_id":"https://openalex.org/F4320315885","funder_display_name":"Australian Government"}],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W48257500","https://openalex.org/W1489262227","https://openalex.org/W1684737195","https://openalex.org/W1988757690","https://openalex.org/W2014018052","https://openalex.org/W2044522110","https://openalex.org/W2075872878","https://openalex.org/W2098432798","https://openalex.org/W2099111195","https://openalex.org/W2099294566","https://openalex.org/W2099430963","https://openalex.org/W2101484286","https://openalex.org/W2119940423","https://openalex.org/W2145729159","https://openalex.org/W2336416123","https://openalex.org/W2586428935","https://openalex.org/W2596585349","https://openalex.org/W2847132741","https://openalex.org/W2941237017","https://openalex.org/W2962689882","https://openalex.org/W2962948942","https://openalex.org/W2962986088","https://openalex.org/W2963338932","https://openalex.org/W2964163353","https://openalex.org/W2999905431","https://openalex.org/W3103220184","https://openalex.org/W3119773585","https://openalex.org/W3150105804","https://openalex.org/W3196212238","https://openalex.org/W4239466562","https://openalex.org/W4285445987","https://openalex.org/W4295855141","https://openalex.org/W6629237864","https://openalex.org/W6674818212","https://openalex.org/W6734517396","https://openalex.org/W6754390661"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247","https://openalex.org/W3169161914","https://openalex.org/W3208638985"],"abstract_inverted_index":{"We":[0],"investigate":[1],"partially":[2],"observed":[3],"Markov":[4],"decision":[5],"processes":[6],"(POMDPs)":[7],"with":[8,34],"cost":[9],"functions":[10],"regularized":[11],"by":[12],"entropy":[13,44],"terms":[14],"describing":[15],"state,":[16,47],"observation,":[17,48],"and":[18,49],"control":[19,50],"uncertainty.":[20],"Standard":[21],"POMDP":[22],"techniques":[23],"are":[24],"shown":[25],"to":[26,30],"offer":[27],"bounded-error":[28],"solutions":[29,36],"these":[31],"entropy-regularized":[32],"POMDPs,":[33],"exact":[35],"possible":[37],"when":[38],"the":[39,42,46],"regularization":[40],"involves":[41],"joint":[43],"of":[45,65],"trajectories.":[51],"Our":[52],"joint-entropy":[53],"result":[54],"is":[55],"particularly":[56],"surprising":[57],"since":[58],"it":[59],"constitutes":[60],"a":[61],"novel,":[62],"tractable":[63],"formulation":[64],"active":[66],"state":[67],"estimation.":[68]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
