{"id":"https://openalex.org/W4283835015","doi":"https://doi.org/10.1109/tnnls.2022.3186229","title":"Data-Driven Inverse Reinforcement Learning Control for Linear Multiplayer Games","display_name":"Data-Driven Inverse Reinforcement Learning Control for Linear Multiplayer Games","publication_year":2022,"publication_date":"2022-07-04","ids":{"openalex":"https://openalex.org/W4283835015","doi":"https://doi.org/10.1109/tnnls.2022.3186229","pmid":"https://pubmed.ncbi.nlm.nih.gov/35786561"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3186229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3186229","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/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":true,"raw_author_name":"Bosen Lian","raw_affiliation_strings":["Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080358912","display_name":"Vrushabh S. Donge","orcid":"https://orcid.org/0000-0003-0606-2803"},"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":"Vrushabh S. Donge","raw_affiliation_strings":["Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","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":["Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, 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/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]},{"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 and the International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries and the International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053089078","display_name":"Ali Davoudi","orcid":"https://orcid.org/0000-0003-2951-442X"},"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":"Ali Davoudi","raw_affiliation_strings":["Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001862814"],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":9.9132,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.98632841,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"35","issue":"2","first_page":"2028","last_page":"2041"},"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":0.9825000166893005,"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":0.9556999802589417,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6975803375244141},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6769040822982788},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5746943354606628},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5585485100746155},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5434175133705139},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4915047585964203},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.4812071621417999},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4797312319278717},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4583761692047119},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4576077163219452},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.36272647976875305},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2793818712234497},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26762717962265015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2435925304889679},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20847854018211365},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.0917564332485199}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6975803375244141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769040822982788},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5746943354606628},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5585485100746155},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5434175133705139},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4915047585964203},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.4812071621417999},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4797312319278717},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4583761692047119},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4576077163219452},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.36272647976875305},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2793818712234497},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26762717962265015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2435925304889679},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20847854018211365},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0917564332485199},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2022.3186229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3186229","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:35786561","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35786561","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/G1742339193","display_name":null,"funder_award_id":"W911NF-20-1-0132","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G4155764213","display_name":null,"funder_award_id":"N00014-18-1-2221","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W132264163","https://openalex.org/W1540245649","https://openalex.org/W1581842928","https://openalex.org/W1614417283","https://openalex.org/W1903683453","https://openalex.org/W1999874108","https://openalex.org/W2024303516","https://openalex.org/W2027161089","https://openalex.org/W2069195348","https://openalex.org/W2124394479","https://openalex.org/W2165726932","https://openalex.org/W2171302338","https://openalex.org/W2475651303","https://openalex.org/W2484646121","https://openalex.org/W2765116338","https://openalex.org/W2782637183","https://openalex.org/W2883057932","https://openalex.org/W2886235386","https://openalex.org/W2946954414","https://openalex.org/W2950438991","https://openalex.org/W2951650773","https://openalex.org/W2983464671","https://openalex.org/W2990694606","https://openalex.org/W3009702296","https://openalex.org/W3013559981","https://openalex.org/W3037298378","https://openalex.org/W3093985518","https://openalex.org/W3095316834","https://openalex.org/W3096135216","https://openalex.org/W3103939126","https://openalex.org/W3120441334","https://openalex.org/W3121683757","https://openalex.org/W3138984732","https://openalex.org/W3156476459","https://openalex.org/W3157204454","https://openalex.org/W3161844359","https://openalex.org/W3165962983","https://openalex.org/W3170519291","https://openalex.org/W3191504080","https://openalex.org/W3197880264","https://openalex.org/W3200276130","https://openalex.org/W3203504876","https://openalex.org/W4287692910","https://openalex.org/W4301018745","https://openalex.org/W4388319978","https://openalex.org/W6747901993","https://openalex.org/W6753207554","https://openalex.org/W6763248972","https://openalex.org/W6781315541","https://openalex.org/W6799835771"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W4391331176"],"abstract_inverted_index":{"This":[0,73],"article":[1,74,123],"proposes":[2,76],"a":[3,31,77],"data-driven":[4,128],"inverse":[5,22,79,103,130,159],"reinforcement":[6],"learning":[7],"(RL)":[8],"control":[9,46,55,105,142],"algorithm":[10,132,161],"for":[11,90],"nonzero-sum":[12],"multiplayer":[13],"games":[14,27],"in":[15,25],"linear":[16],"continuous-time":[17],"differential":[18],"dynamical":[19],"systems.":[20],"The":[21,49],"RL":[23,80,131,160],"problem":[24],"the":[26,34,53,61,117,150,157,172,184,187],"is":[28],"solved":[29],"by":[30],"learner":[32],"reconstructing":[33,91],"unknown":[35],"expert":[36,141],"players'":[37],"cost":[38,92],"functions":[39],"from":[40],"demonstrated":[41],"expert's":[42],"optimal":[43,104,113],"state":[44],"and":[45,58,107,146],"input":[47],"trajectories.":[48],"learner,":[50],"thus,":[51],"obtains":[52],"same":[54],"feedback":[56],"gains":[57],"trajectories":[59,68],"as":[60],"expert,":[62],"only":[63],"using":[64,94,102,112],"data":[65],"along":[66],"system":[67,71,138],"without":[69,133],"knowing":[70,134],"dynamics.":[72],"first":[75],"model-based":[78,118],"policy":[81,87,109,119],"iteration":[82,120],"framework":[83],"that":[84,156],"has:":[85],"1)":[86],"evaluation":[88],"step":[89,101,111],"matrices":[93],"Lyapunov":[95],"functions;":[96],"2)":[97],"state-reward":[98],"weight":[99],"improvement":[100,110],"(IOC);":[106],"3)":[108],"control.":[114],"Based":[115],"on":[116],"algorithm,":[121],"this":[122],"further":[124],"develops":[125],"an":[126],"online":[127],"off-policy":[129,158],"any":[135],"knowledge":[136],"of":[137,149,174,186],"dynamics":[139],"or":[140],"gains.":[143],"Rigorous":[144],"convergence":[145],"stability":[147],"analysis":[148],"algorithms":[151],"are":[152,168],"provided.":[153],"It":[154],"shows":[155],"guarantees":[162],"unbiased":[163],"solutions":[164],"while":[165],"probing":[166],"noises":[167],"added":[169],"to":[170],"satisfy":[171],"persistence":[173],"excitation":[175],"(PE)":[176],"condition.":[177],"Finally,":[178],"two":[179],"different":[180],"simulation":[181],"examples":[182],"validate":[183],"effectiveness":[185],"proposed":[188],"algorithms.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}