{"id":"https://openalex.org/W2912924301","doi":"https://doi.org/10.1109/allerton.2018.8636066","title":"Entropy Maximization for Constrained Markov Decision Processes","display_name":"Entropy Maximization for Constrained Markov Decision Processes","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2912924301","doi":"https://doi.org/10.1109/allerton.2018.8636066","mag":"2912924301"},"language":"en","primary_location":{"id":"doi:10.1109/allerton.2018.8636066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2018.8636066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","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/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, University of Texas at Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering, University of Texas at Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070897457","display_name":"Melkior Ornik","orcid":"https://orcid.org/0000-0002-8510-8787"},"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":"Melkior Ornik","raw_affiliation_strings":["Institute for Computational Engineering and Sciences, University of Texas at Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Computational Engineering and Sciences, University of Texas at Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050465036","display_name":"Murat Cubuktepe","orcid":"https://orcid.org/0000-0002-0409-2403"},"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":"Murat Cubuktepe","raw_affiliation_strings":["Department of Aerospace Engineering, University of Texas at Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering, University of Texas at 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, University of Texas at Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering, University of Texas at Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6896,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88558022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"911","last_page":"918"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9549999833106995,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9502999782562256,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/entropy-maximization","display_name":"Entropy maximization","score":0.7505154013633728},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7401989698410034},{"id":"https://openalex.org/keywords/predictability","display_name":"Predictability","score":0.7292336225509644},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6919717788696289},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.594708263874054},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5841220021247864},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5675923228263855},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.4930228888988495},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4106563329696655},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.408795028924942},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13388678431510925}],"concepts":[{"id":"https://openalex.org/C127233936","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Entropy maximization","level":3,"score":0.7505154013633728},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7401989698410034},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.7292336225509644},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6919717788696289},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.594708263874054},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5841220021247864},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5675923228263855},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.4930228888988495},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4106563329696655},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.408795028924942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13388678431510925},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/allerton.2018.8636066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2018.8636066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1498432697","https://openalex.org/W1515851193","https://openalex.org/W1518931405","https://openalex.org/W1576452626","https://openalex.org/W1632601927","https://openalex.org/W1736896304","https://openalex.org/W1948859648","https://openalex.org/W1998783985","https://openalex.org/W2059470663","https://openalex.org/W2060108852","https://openalex.org/W2099111195","https://openalex.org/W2119567691","https://openalex.org/W2122597713","https://openalex.org/W2128480458","https://openalex.org/W2149808183","https://openalex.org/W2288174618","https://openalex.org/W2321105680","https://openalex.org/W2478708596","https://openalex.org/W2594103415","https://openalex.org/W2949561945","https://openalex.org/W2949979136","https://openalex.org/W3103220184","https://openalex.org/W4205326910","https://openalex.org/W4297825594","https://openalex.org/W4298023569","https://openalex.org/W6696497002","https://openalex.org/W6699797690","https://openalex.org/W6734517396","https://openalex.org/W6785936046"],"related_works":["https://openalex.org/W3102188974","https://openalex.org/W4287870705","https://openalex.org/W3004810941","https://openalex.org/W3199097846","https://openalex.org/W4297193174","https://openalex.org/W2951493954","https://openalex.org/W2576492542","https://openalex.org/W1952656308","https://openalex.org/W2267645079","https://openalex.org/W2137556923"],"abstract_inverted_index":{"We":[0,42,58,77],"study":[1],"the":[2,10,27,30,46,66,88,109,112,117,133,143,146,151,154],"problem":[3,102],"of":[4,12,29,49,69,90,111,148,153],"synthesizing":[5],"a":[6,13,24,84,99],"policy":[7,25,85],"that":[8,45,86],"maximizes":[9,87],"entropy":[11,48,68,89],"Markov":[14],"decision":[15],"process":[16],"(MDP)":[17],"subject":[18,122],"to":[19,82,119,123],"expected":[20,124],"reward":[21,40,126],"constraints.":[22,127],"Such":[23],"minimizes":[26],"predictability":[28,147],"paths":[31,149],"it":[32],"generates":[33],"in":[34,105,108],"an":[35,50,70,80,91,120],"MDP":[36,51,71,121],"while":[37],"attaining":[38],"certain":[39],"thresholds.":[41],"first":[43],"show":[44],"maximum":[47,67],"can":[52],"be":[53],"finite,":[54,73],"infinite":[55,74],"or":[56,75],"unbounded.":[57,76],"provide":[59],"necessary":[60],"and":[61,103,141,150],"sufficient":[62],"conditions":[63],"under":[64],"which":[65],"is":[72,96],"then":[78],"present":[79],"algorithm":[81,95,118],"synthesize":[83],"MDP.":[92,113],"The":[93],"proposed":[94,134],"based":[97],"on":[98,136],"convex":[100],"optimization":[101],"runs":[104],"time":[106],"polynomial":[107],"size":[110],"Finally,":[114],"we":[115,131],"extend":[116],"total":[125],"In":[128],"numerical":[129],"examples,":[130],"demonstrate":[132],"method":[135],"different":[137],"motion":[138],"planning":[139],"scenarios":[140],"illustrate":[142],"trade-off":[144],"between":[145],"level":[152],"collected":[155],"reward.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}