{"id":"https://openalex.org/W3162263071","doi":"https://doi.org/10.1109/tac.2022.3183564","title":"Entropy Maximization for Partially Observable Markov Decision Processes","display_name":"Entropy Maximization for Partially Observable Markov Decision Processes","publication_year":2022,"publication_date":"2022-06-16","ids":{"openalex":"https://openalex.org/W3162263071","doi":"https://doi.org/10.1109/tac.2022.3183564","mag":"3162263071"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2022.3183564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2022.3183564","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/A5075328109","display_name":"Yagiz Savas","orcid":"https://orcid.org/0000-0003-2976-0786"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yagiz Savas","raw_affiliation_strings":["Department of Aerospace Engineering and Engineering Mechanics, Oden Institute for Computational Engineering and Sciences, University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-2976-0786","affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering and Engineering Mechanics, Oden Institute for Computational Engineering and Sciences, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103067990","display_name":"Michael Hibbard","orcid":"https://orcid.org/0000-0002-4697-4551"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Hibbard","raw_affiliation_strings":["Department of Aerospace Engineering and Engineering Mechanics, Oden Institute for Computational Engineering and Sciences, University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-4697-4551","affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering and Engineering Mechanics, Oden Institute for Computational Engineering and Sciences, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100672632","display_name":"Bo Wu","orcid":"https://orcid.org/0000-0002-7199-6525"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Wu","raw_affiliation_strings":["Department of Aerospace Engineering and Engineering Mechanics, Oden Institute for Computational Engineering and Sciences, University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-7199-6525","affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering and Engineering Mechanics, Oden Institute for Computational Engineering and Sciences, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082230661","display_name":"Takashi Tanaka","orcid":"https://orcid.org/0000-0001-7424-0064"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takashi Tanaka","raw_affiliation_strings":["Department of Aerospace Engineering and Engineering Mechanics, Oden Institute for Computational Engineering and Sciences, University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0001-7424-0064","affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering and Engineering Mechanics, Oden Institute for Computational Engineering and Sciences, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068441112","display_name":"Ufuk Topcu","orcid":"https://orcid.org/0000-0003-0819-9985"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ufuk Topcu","raw_affiliation_strings":["Department of Aerospace Engineering and Engineering Mechanics, Oden Institute for Computational Engineering and Sciences, University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-0819-9985","affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering and Engineering Mechanics, Oden Institute for Computational Engineering and Sciences, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.1495,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79425184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"67","issue":"12","first_page":"6948","last_page":"6955"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11125","display_name":"Petri Nets in System Modeling","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"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":0.9128156304359436},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.7039536833763123},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6124809980392456},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5959633588790894},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.57106614112854},{"id":"https://openalex.org/keywords/entropy-maximization","display_name":"Entropy maximization","score":0.547508955001831},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5435599684715271},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.542327880859375},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5221431851387024},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.502025842666626},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4752882719039917},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4553123712539673},{"id":"https://openalex.org/keywords/entropy-rate","display_name":"Entropy rate","score":0.4396982491016388},{"id":"https://openalex.org/keywords/maximum-entropy-markov-model","display_name":"Maximum-entropy Markov model","score":0.43793734908103943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.43024811148643494},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.31277143955230713},{"id":"https://openalex.org/keywords/binary-entropy-function","display_name":"Binary entropy function","score":0.2563541531562805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2219034731388092},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.14941859245300293},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11212033033370972},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08510395884513855}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.9128156304359436},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.7039536833763123},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6124809980392456},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5959633588790894},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.57106614112854},{"id":"https://openalex.org/C127233936","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Entropy maximization","level":3,"score":0.547508955001831},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5435599684715271},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.542327880859375},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5221431851387024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.502025842666626},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4752882719039917},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4553123712539673},{"id":"https://openalex.org/C125252325","wikidata":"https://www.wikidata.org/wiki/Q1345213","display_name":"Entropy rate","level":4,"score":0.4396982491016388},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.43793734908103943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43024811148643494},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.31277143955230713},{"id":"https://openalex.org/C44415725","wikidata":"https://www.wikidata.org/wiki/Q4913893","display_name":"Binary entropy function","level":3,"score":0.2563541531562805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2219034731388092},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.14941859245300293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11212033033370972},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08510395884513855},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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.2022.3183564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2022.3183564","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G3433098100","display_name":null,"funder_award_id":"1944318","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G3775629894","display_name":null,"funder_award_id":"D19AP00078","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4908315546","display_name":null,"funder_award_id":"D19AP00004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7128843908","display_name":null,"funder_award_id":"FOA-AFRL-AFOSR-2019-0003","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7377845663","display_name":null,"funder_award_id":"FA9550-19-1-0169","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1494689917","https://openalex.org/W1522308973","https://openalex.org/W1542709260","https://openalex.org/W1563965851","https://openalex.org/W1640774615","https://openalex.org/W1701684472","https://openalex.org/W1984338812","https://openalex.org/W1988622494","https://openalex.org/W1998783985","https://openalex.org/W2003031375","https://openalex.org/W2010220123","https://openalex.org/W2011418219","https://openalex.org/W2016130656","https://openalex.org/W2032100464","https://openalex.org/W2070469928","https://openalex.org/W2082014790","https://openalex.org/W2087992130","https://openalex.org/W2099111195","https://openalex.org/W2119567691","https://openalex.org/W2142477416","https://openalex.org/W2144283793","https://openalex.org/W2147102238","https://openalex.org/W2158082107","https://openalex.org/W2166765763","https://openalex.org/W2168359464","https://openalex.org/W2221524898","https://openalex.org/W2288506839","https://openalex.org/W2321105680","https://openalex.org/W2594103415","https://openalex.org/W2611807022","https://openalex.org/W2798766386","https://openalex.org/W2809011908","https://openalex.org/W2847132741","https://openalex.org/W2949561945","https://openalex.org/W2963307044","https://openalex.org/W2963403593","https://openalex.org/W2995644129","https://openalex.org/W3002804771","https://openalex.org/W3011869378","https://openalex.org/W3024652448","https://openalex.org/W3034426742","https://openalex.org/W3103220184","https://openalex.org/W3105306379","https://openalex.org/W6629836980","https://openalex.org/W6633696232","https://openalex.org/W6636894280","https://openalex.org/W6637465547","https://openalex.org/W6681633084","https://openalex.org/W6683354572","https://openalex.org/W6699797690","https://openalex.org/W6734517396","https://openalex.org/W6749714691","https://openalex.org/W6752328880","https://openalex.org/W6773433563","https://openalex.org/W6776824048"],"related_works":["https://openalex.org/W1945850644","https://openalex.org/W2949456575","https://openalex.org/W94274217","https://openalex.org/W2145913509","https://openalex.org/W1636292289","https://openalex.org/W202303397","https://openalex.org/W2951493954","https://openalex.org/W3125883986","https://openalex.org/W2803693972","https://openalex.org/W4320878858"],"abstract_inverted_index":{"We":[0,110],"study":[1],"the":[2,10,25,33,45,67,77,81,96,107,122,130,142],"problem":[3,99,105],"of":[4,12,35,47,70,80,124,133,144],"synthesizing":[5],"a":[6,13,22,30,48,52,71,101,125,137,156,161],"controller":[7,31],"that":[8,66,119,153],"maximizes":[9,121],"entropy":[11,69,79,97,123],"partially":[14],"observable":[15],"Markov":[16,83],"decision":[17],"process":[18],"(POMDP)":[19],"subject":[20],"to":[21,39,94,115],"constraint":[23],"on":[24,56],"expected":[26],"total":[27],"reward.":[28],"Such":[29],"minimizes":[32],"predictability":[34],"an":[36,40,113,117,146,151],"agent\u2019s":[37],"trajectories":[38],"outside":[41],"observer":[42],"while":[43],"guaranteeing":[44],"completion":[46],"task":[49],"expressed":[50],"by":[51,76,87],"reward":[53],"function.":[54],"Focusing":[55],"finite-state":[57],"controllers":[58],"(FSCs)":[59],"with":[60,129,150],"deterministic":[61],"memory":[62,134],"transitions,":[63],"we":[64,140],"show":[65],"maximum":[68,78],"POMDP":[72,126],"is":[73],"lower":[74],"bounded":[75],"parameteric":[82],"chain":[84],"(pMC)":[85],"induced":[86,108],"such":[88],"FSCs.":[89],"This":[90],"relationship":[91],"allows":[92],"us":[93],"recast":[95],"maximization":[98],"as":[100],"so-called":[102],"parameter":[103],"synthesis":[104],"for":[106,159],"pMC.":[109],"then":[111],"present":[112],"algorithm":[114],"synthesize":[116],"FSC":[118,148,152],"locally":[120],"over":[127],"FSCs":[128],"same":[131],"number":[132],"states.":[135],"In":[136],"numerical":[138],"example,":[139],"highlight":[141],"benefit":[143],"using":[145],"entropy-maximizing":[147],"compared":[149],"simply":[154],"finds":[155],"feasible":[157],"policy":[158],"accomplishing":[160],"task.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}