{"id":"https://openalex.org/W4315472194","doi":"https://doi.org/10.1109/cdc51059.2022.9993367","title":"Inverse Reinforcement Learning Control for Linear Multiplayer Games","display_name":"Inverse Reinforcement Learning Control for Linear Multiplayer Games","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315472194","doi":"https://doi.org/10.1109/cdc51059.2022.9993367"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9993367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9993367","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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/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":["University of Texas at Arlington,Arlington,TX,USA,76019"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington,Arlington,TX,USA,76019","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":["University of Texas at Arlington,Arlington,TX,USA,76019"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington,Arlington,TX,USA,76019","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":["University of Texas at Arlington,Arlington,TX,USA,76019"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington,Arlington,TX,USA,76019","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":["Northeastern University,The State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation,Shenyang,China,110819"],"affiliations":[{"raw_affiliation_string":"Northeastern University,The State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation,Shenyang,China,110819","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":["University of Texas at Arlington,Arlington,TX,USA,76019"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington,Arlington,TX,USA,76019","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":1.0361,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76072607,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2839","last_page":"2844"},"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":0.9952999949455261,"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":0.9562000036239624,"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":0.6976921558380127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6810858249664307},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6435259580612183},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5569846630096436},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5496791005134583},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5153617262840271},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5091561675071716},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5041378736495972},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4869571626186371},{"id":"https://openalex.org/keywords/differential-game","display_name":"Differential game","score":0.42212122678756714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3621768653392792},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3069608211517334},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22907641530036926},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.15313810110092163}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6976921558380127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6810858249664307},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6435259580612183},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5569846630096436},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5496791005134583},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5153617262840271},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5091561675071716},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5041378736495972},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4869571626186371},{"id":"https://openalex.org/C2779006483","wikidata":"https://www.wikidata.org/wiki/Q1973196","display_name":"Differential game","level":2,"score":0.42212122678756714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3621768653392792},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3069608211517334},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22907641530036926},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.15313810110092163},{"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/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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9993367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9993367","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1581842928","https://openalex.org/W1583837637","https://openalex.org/W1999874108","https://openalex.org/W2027161089","https://openalex.org/W2124394479","https://openalex.org/W2165726932","https://openalex.org/W2475651303","https://openalex.org/W2484646121","https://openalex.org/W2765116338","https://openalex.org/W2883057932","https://openalex.org/W2907275873","https://openalex.org/W2950438991","https://openalex.org/W2983464671","https://openalex.org/W3037298378","https://openalex.org/W3095316834","https://openalex.org/W3138984732","https://openalex.org/W3156476459","https://openalex.org/W3170519291","https://openalex.org/W3200276130","https://openalex.org/W3203504876","https://openalex.org/W4214717370","https://openalex.org/W4290991295","https://openalex.org/W4301018745","https://openalex.org/W4388319978","https://openalex.org/W6747901993","https://openalex.org/W6753207554","https://openalex.org/W6763248972"],"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/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"This":[0,49],"paper":[1,50],"proposes":[2],"model-based":[3,54,91],"and":[4,32,81,111],"model-free":[5],"inverse":[6,55,77,96],"reinforcement":[7],"learning":[8],"(RL)":[9],"control":[10,30,79,107],"algorithms":[11,23,116],"for":[12,65],"multiplayer":[13],"game":[14],"systems":[15],"described":[16],"by":[17,37],"linear":[18],"continuous-time":[19],"differential":[20],"equations.":[21],"Both":[22],"find":[24],"the":[25,27,35,39,46,90],"learner":[26],"same":[28],"optimal":[29,78,86],"policies":[31],"trajectories":[33],"as":[34],"expert,":[36],"inferring":[38],"unknown":[40],"expert":[41,106],"players\u2019":[42],"cost":[43,66],"functions":[44],"from":[45],"expert\u2019s":[47],"trajectories.":[48],"first":[51],"discusses":[52],"a":[53,69,120],"RL":[56,97],"policy":[57,63,83],"iteration":[58],"that":[59],"consists":[60],"of":[61,114],"1)":[62],"evaluation":[64],"matrices":[67],"using":[68,76,85],"Lyapunov":[70],"equation,":[71],"2)":[72],"state-reward":[73],"weight":[74],"improvement":[75,84],"(IOC),":[80],"3)":[82],"control.":[87],"Based":[88],"on":[89],"algorithm,":[92],"an":[93],"online":[94],"data-driven":[95],"algorithm":[98],"is":[99],"proposed":[100],"without":[101],"knowing":[102],"system":[103],"dynamics":[104],"or":[105],"gains.":[108],"Rigorous":[109],"convergence":[110],"stability":[112],"analysis":[113],"these":[115],"are":[117],"provided.":[118],"Finally,":[119],"simulation":[121],"example":[122],"verifies":[123],"our":[124],"approach.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}