{"id":"https://openalex.org/W3200276130","doi":"https://doi.org/10.1109/tnnls.2021.3106635","title":"Inverse Reinforcement Q-Learning Through Expert Imitation for Discrete-Time Systems","display_name":"Inverse Reinforcement Q-Learning Through Expert Imitation for Discrete-Time Systems","publication_year":2021,"publication_date":"2021-09-14","ids":{"openalex":"https://openalex.org/W3200276130","doi":"https://doi.org/10.1109/tnnls.2021.3106635","mag":"3200276130","pmid":"https://pubmed.ncbi.nlm.nih.gov/34520364"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3106635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3106635","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5102973745","display_name":"Wenqian Xue","orcid":"https://orcid.org/0000-0002-3670-3854"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenqian Xue","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001862814","display_name":"Bosen Lian","orcid":"https://orcid.org/0000-0002-3275-9551"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bosen Lian","raw_affiliation_strings":["UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033960992","display_name":"Jialu Fan","orcid":"https://orcid.org/0000-0001-7585-1166"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialu Fan","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065878109","display_name":"Patrik Kolaric","orcid":"https://orcid.org/0000-0002-4332-3462"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrik Kolaric","raw_affiliation_strings":["UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042520521","display_name":"Tianyou Chai","orcid":"https://orcid.org/0000-0002-4623-1483"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyou Chai","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102973745"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":6.3602,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.97020906,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"34","issue":"5","first_page":"2386","last_page":"2399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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":0.9972000122070312,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.980400025844574,"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/imitation","display_name":"Imitation","score":0.6818777918815613},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.6152242422103882},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5109032988548279},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4978358745574951},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.4849574565887451},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4647485613822937},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4240744709968567},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23529177904129028},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2099599838256836},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10510388016700745},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.07127061486244202},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06939142942428589}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6818777918815613},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.6152242422103882},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5109032988548279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4978358745574951},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.4849574565887451},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4647485613822937},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4240744709968567},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23529177904129028},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2099599838256836},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10510388016700745},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.07127061486244202},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06939142942428589},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3106635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3106635","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:34520364","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34520364","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1460833335","display_name":null,"funder_award_id":"61533015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3474679019","display_name":null,"funder_award_id":"61991400","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4867859608","display_name":null,"funder_award_id":"61991403","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5409562055","display_name":null,"funder_award_id":"B08015","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"},{"id":"https://openalex.org/G5898287775","display_name":null,"funder_award_id":"61991404","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1603698551","https://openalex.org/W1614417283","https://openalex.org/W1968908471","https://openalex.org/W1970916399","https://openalex.org/W1972243698","https://openalex.org/W1999874108","https://openalex.org/W2005437559","https://openalex.org/W2006263815","https://openalex.org/W2013895638","https://openalex.org/W2027161089","https://openalex.org/W2035608030","https://openalex.org/W2037539475","https://openalex.org/W2058857176","https://openalex.org/W2121196039","https://openalex.org/W2134491302","https://openalex.org/W2146824685","https://openalex.org/W2148439597","https://openalex.org/W2165726932","https://openalex.org/W2166302491","https://openalex.org/W2181849516","https://openalex.org/W2290104316","https://openalex.org/W2410842990","https://openalex.org/W2484646121","https://openalex.org/W2580629550","https://openalex.org/W2734548765","https://openalex.org/W2771641782","https://openalex.org/W2912832158","https://openalex.org/W2942515073","https://openalex.org/W2950989964","https://openalex.org/W2963277051","https://openalex.org/W2996540228","https://openalex.org/W3044756857","https://openalex.org/W3085531353","https://openalex.org/W3156476459","https://openalex.org/W3170519291","https://openalex.org/W4214717370","https://openalex.org/W4287692910","https://openalex.org/W4301018745","https://openalex.org/W4388319978","https://openalex.org/W6632235069","https://openalex.org/W6677631742","https://openalex.org/W6685962732","https://openalex.org/W6696380822","https://openalex.org/W6718092244","https://openalex.org/W6781315541","https://openalex.org/W6782915976","https://openalex.org/W6794270814"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2920061524"],"abstract_inverted_index":{"In":[0,59],"inverse":[1,123,153,172],"reinforcement":[2,173],"learning":[3],"(RL),":[4],"there":[5],"are":[6,199,214],"two":[7],"agents.":[8],"An":[9],"expert":[10,76],"target":[11,77],"agent":[12,29,78,191],"has":[13],"a":[14,25,73,82,98,127,140,157],"performance":[15,35,70],"cost":[16,36,99,141],"function":[17,37,100,142],"and":[18,21,48,111,152,156,197],"exhibits":[19],"control":[20,158],"state":[22],"behaviors":[23,47,53],"to":[24,40,50,81,96,130,216],"learner.":[26],"The":[27,136],"learner":[28,94],"does":[30,185],"not":[31,186],"know":[32],"the":[33,45,68,88,93,103,109,114,118,132,205,218,221],"expert's":[34,46,90],"but":[38],"seeks":[39,95],"reconstruct":[41],"it":[42],"by":[43,55],"observing":[44],"tries":[49],"imitate":[51],"these":[52],"optimally":[54],"its":[56],"own":[57],"response.":[58],"this":[60,167],"article,":[61],"we":[62,169],"formulate":[63],"an":[64,122,146,171,178],"imitation":[65,134],"problem":[66],"where":[67],"optimal":[69,105,115,154,163],"intent":[71],"of":[72,117,139,148,180,190,194,220],"discrete-time":[74],"(DT)":[75],"is":[79,177,208],"unknown":[80],"DT":[83],"Learner":[84],"agent.":[85],"Using":[86],"only":[87],"observed":[89],"behavior":[91,133],"trajectory,":[92],"determine":[97],"that":[101],"yields":[102],"same":[104],"feedback":[106],"gain":[107],"as":[108],"expert's,":[110],"thus,":[112],"imitates":[113],"response":[116],"expert.":[119],"We":[120],"develop":[121,170],"RL":[124,149,181],"approach":[125,137],"with":[126],"new":[128,222],"scheme":[129],"solve":[131],"problem.":[135],"consists":[138],"update":[143,160],"based":[144,161],"on":[145,162],"extension":[147,179],"policy":[150,159],"iteration":[151],"control,":[155],"control.":[164],"Then,":[165],"under":[166],"scheme,":[168],"Q-learning":[174],"algorithm,":[175],"which":[176],"Q-learning.":[182],"This":[183],"algorithm":[184],"require":[187],"any":[188],"knowledge":[189],"dynamics.":[192],"Proofs":[193],"stability,":[195],"convergence,":[196],"optimality":[198],"given.":[200],"A":[201],"key":[202],"property":[203],"about":[204],"nonunique":[206],"solution":[207],"also":[209],"shown.":[210],"Finally,":[211],"simulation":[212],"experiments":[213],"presented":[215],"show":[217],"effectiveness":[219],"approach.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":3}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}