{"id":"https://openalex.org/W2070469928","doi":"https://doi.org/10.1109/tac.2017.2775960","title":"Infinite Time Horizon Maximum Causal Entropy Inverse Reinforcement Learning","display_name":"Infinite Time Horizon Maximum Causal Entropy Inverse Reinforcement Learning","publication_year":2017,"publication_date":"2017-11-20","ids":{"openalex":"https://openalex.org/W2070469928","doi":"https://doi.org/10.1109/tac.2017.2775960","mag":"2070469928"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2017.2775960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2017.2775960","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/A5088606320","display_name":"Zhengyuan Zhou","orcid":"https://orcid.org/0000-0002-0005-9411"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhengyuan Zhou","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA, USA","Department of Electrical Engineering, Stanford University Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068955929","display_name":"Michael Bloem","orcid":"https://orcid.org/0000-0001-5864-7753"},"institutions":[{"id":"https://openalex.org/I54606842","display_name":"Steelcase (United States)","ror":"https://ror.org/03d8jhc95","country_code":"US","type":"company","lineage":["https://openalex.org/I54606842"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Bloem","raw_affiliation_strings":["Advanced Analytics, Steelcase, Inc., Grand Rapids, MI, USA","[Advanced Analytics, Steelcase, Inc., Grand Rapids, MI, USA]"],"affiliations":[{"raw_affiliation_string":"Advanced Analytics, Steelcase, Inc., Grand Rapids, MI, USA","institution_ids":["https://openalex.org/I54606842"]},{"raw_affiliation_string":"[Advanced Analytics, Steelcase, Inc., Grand Rapids, MI, USA]","institution_ids":["https://openalex.org/I54606842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002056995","display_name":"Nicholas Bambos","orcid":"https://orcid.org/0000-0001-9250-4553"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Bambos","raw_affiliation_strings":["Department of Electrical Engineering and Department of Management Science & Engineering, Stanford University, CA, USA","[Department of Electrical Engineering and Department of Management Science & Engineering, Stanford University, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Department of Management Science & Engineering, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"[Department of Electrical Engineering and Department of Management Science & Engineering, Stanford University, CA, USA]","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088606320"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":8.9911,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.9804011,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"63","issue":"9","first_page":"2787","last_page":"2802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9872999787330627,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6816807985305786},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6667248606681824},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5957883596420288},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5538889765739441},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5219851732254028},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5127971768379211},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4287595748901367},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.41736748814582825},{"id":"https://openalex.org/keywords/simultaneous-perturbation-stochastic-approximation","display_name":"Simultaneous perturbation stochastic approximation","score":0.41375401616096497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37421369552612305},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33865422010421753},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.2613064646720886}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6816807985305786},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6667248606681824},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5957883596420288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5538889765739441},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5219851732254028},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5127971768379211},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4287595748901367},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.41736748814582825},{"id":"https://openalex.org/C2779880469","wikidata":"https://www.wikidata.org/wiki/Q17084424","display_name":"Simultaneous perturbation stochastic approximation","level":3,"score":0.41375401616096497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37421369552612305},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33865422010421753},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2613064646720886},{"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/tac.2017.2775960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2017.2775960","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":[{"score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W64088143","https://openalex.org/W1489262227","https://openalex.org/W1496462336","https://openalex.org/W1590693676","https://openalex.org/W1999874108","https://openalex.org/W2001136571","https://openalex.org/W2051944318","https://openalex.org/W2064076655","https://openalex.org/W2069855531","https://openalex.org/W2070406545","https://openalex.org/W2091638851","https://openalex.org/W2094796089","https://openalex.org/W2098432798","https://openalex.org/W2098774185","https://openalex.org/W2102847492","https://openalex.org/W2113023245","https://openalex.org/W2115318338","https://openalex.org/W2133068870","https://openalex.org/W2134491302","https://openalex.org/W2140834544","https://openalex.org/W2142477416","https://openalex.org/W2147544021","https://openalex.org/W2165131254","https://openalex.org/W2169498096","https://openalex.org/W2210387432","https://openalex.org/W2296319761","https://openalex.org/W2321545103","https://openalex.org/W2765927108","https://openalex.org/W4232512588","https://openalex.org/W4295207485","https://openalex.org/W6629237864","https://openalex.org/W6674884181","https://openalex.org/W6676728370","https://openalex.org/W6677373437","https://openalex.org/W6679958247","https://openalex.org/W6681478256","https://openalex.org/W6703436554","https://openalex.org/W6745104711","https://openalex.org/W6903351479"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":{"Inverse":[0],"reinforcement":[1],"learning":[2],"(IRL)":[3],"attempts":[4],"to":[5,17,47,149,181],"use":[6],"demonstrations":[7],"of":[8,28,110,163,175],"\u201cexpert\u201d":[9],"decision":[10,15],"making":[11],"in":[12,45,77,119,135,143,198],"a":[13,19,42,95,114,131,160,189],"Markov":[14],"process":[16],"infer":[18],"corresponding":[20],"policy":[21],"that":[22,74,80,105,116],"shares":[23],"the":[24,29,37,48,68,99,107,126,136,167],"\u201cstructured,":[25],"purposeful\u201d":[26],"qualities":[27],"expert's":[30],"actions.":[31],"In":[32],"this":[33,176],"paper,":[34],"we":[35,171],"extend":[36],"maximum":[38,62,100],"causal":[39,59,64,102],"entropy":[40,60,103],"framework,":[41],"notable":[43],"paradigm":[44],"IRL,":[46],"infinite":[49,69],"time":[50],"horizon":[51,70],"setting.":[52],"We":[53,92,124],"consider":[54],"two":[55,182],"formulations":[56],"(maximum":[57],"discounted":[58,101],"and":[61,72,139,178],"average":[63],"entropy)":[65],"appropriate":[66],"for":[67,98,165],"case":[71],"show":[73],"both":[75],"result":[76],"optimization":[78,86],"programs":[79],"can":[81],"be":[82],"reformulated":[83],"as":[84],"convex":[85],"problems;":[87],"thus,":[88],"admitting":[89],"efficient":[90],"computation.":[91],"then":[93],"develop":[94],"gradient-based":[96,137,168],"algorithm":[97],"formulation":[104],"enjoys":[106],"desired":[108],"feature":[109],"being":[111],"model":[112,194],"agnostic,":[113],"property":[115],"is":[117],"absent":[118],"many":[120],"previous":[121],"IRL":[122],"algorithms.":[123],"propose":[125],"stationary":[127],"soft":[128],"Bellman":[129],"policy,":[130],"key":[132],"building":[133],"block":[134],"algorithm,":[138],"study":[140],"its":[141,153],"properties":[142],"depth,":[144],"which":[145],"not":[146],"only":[147],"lead":[148],"theoretical":[150],"insight":[151],"into":[152],"analytical":[154],"properties,":[155],"but":[156],"also":[157],"help":[158],"motivate":[159],"large":[161],"toolkit":[162],"methods":[164],"implementing":[166],"algorithm.":[169],"Finally,":[170],"select":[172],"three":[173],"algorithms":[174],"type":[177],"apply":[179],"them":[180],"problem":[183],"instances":[184],"involving":[185],"demonstration":[186],"data":[187],"from":[188],"simple":[190],"controlled":[191],"queuing":[192],"network":[193],"inspired":[195],"by":[196],"problems":[197],"air":[199],"traffic":[200],"management.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}