{"id":"https://openalex.org/W4381162568","doi":"https://doi.org/10.1109/tcns.2022.3210856","title":"Multiagent Graphical Games With Inverse Reinforcement Learning","display_name":"Multiagent Graphical Games With Inverse Reinforcement Learning","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4381162568","doi":"https://doi.org/10.1109/tcns.2022.3210856"},"language":"en","primary_location":{"id":"doi:10.1109/tcns.2022.3210856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcns.2022.3210856","pdf_url":null,"source":{"id":"https://openalex.org/S2502544478","display_name":"IEEE Transactions on Control of Network Systems","issn_l":"2325-5870","issn":["2325-5870","2372-2533"],"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 Control of Network Systems","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/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, The University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-0606-2803","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"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":["Department of Electrical Engineering, The University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-3275-9551","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The 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, The University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-4074-1615","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"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, The University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-2951-442X","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":4.6055,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.9590592,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"10","issue":"2","first_page":"841","last_page":"852"},"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":0.9994000196456909,"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":0.9545999765396118,"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/inverse","display_name":"Inverse","score":0.7576786279678345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6364393830299377},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6216243505477905},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5222921371459961},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.46808868646621704},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44522824883461},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.43593552708625793},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4260020852088928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4009683430194855},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34211379289627075},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24810197949409485}],"concepts":[{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.7576786279678345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6364393830299377},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6216243505477905},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5222921371459961},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.46808868646621704},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44522824883461},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.43593552708625793},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4260020852088928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4009683430194855},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34211379289627075},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24810197949409485},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcns.2022.3210856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcns.2022.3210856","pdf_url":null,"source":{"id":"https://openalex.org/S2502544478","display_name":"IEEE Transactions on Control of Network Systems","issn_l":"2325-5870","issn":["2325-5870","2372-2533"],"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 Control of Network Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1506806321","https://openalex.org/W1559990548","https://openalex.org/W1582264157","https://openalex.org/W1591675293","https://openalex.org/W1603698551","https://openalex.org/W1614417283","https://openalex.org/W1616818660","https://openalex.org/W1999874108","https://openalex.org/W2024303516","https://openalex.org/W2027161089","https://openalex.org/W2053910308","https://openalex.org/W2058857176","https://openalex.org/W2086602679","https://openalex.org/W2092215165","https://openalex.org/W2093300195","https://openalex.org/W2098432798","https://openalex.org/W2113023245","https://openalex.org/W2124394479","https://openalex.org/W2134491302","https://openalex.org/W2148439597","https://openalex.org/W2347074400","https://openalex.org/W2410842990","https://openalex.org/W2487144912","https://openalex.org/W2500893136","https://openalex.org/W2803623613","https://openalex.org/W2883057932","https://openalex.org/W2943094749","https://openalex.org/W2963277051","https://openalex.org/W2982172847","https://openalex.org/W2997938989","https://openalex.org/W3156476459","https://openalex.org/W3170519291","https://openalex.org/W3186624155","https://openalex.org/W4211008118","https://openalex.org/W4214717370","https://openalex.org/W6632235069","https://openalex.org/W6633543754","https://openalex.org/W6635261211","https://openalex.org/W6676728370","https://openalex.org/W6718092244","https://openalex.org/W6753207554"],"related_works":["https://openalex.org/W24774503","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2331917905","https://openalex.org/W3155039083","https://openalex.org/W1543136835","https://openalex.org/W1970914699"],"abstract_inverted_index":{"This":[0],"work":[1],"investigates":[2],"inverse":[3,43,59,69,98,126],"reinforcement":[4],"learning":[5],"(RL)":[6],"for":[7],"multiagent":[8],"systems":[9],"(MAS)":[10],"defined":[11],"by":[12,20,39],"Graphical":[13],"Apprentice":[14],"Games.":[15],"These":[16],"games":[17],"are":[18,91,109],"solved":[19,92],"a":[21,41,67],"learner":[22,80,106],"MAS":[23,32,81,107],"finding":[24],"the":[25,77,105,121,124],"unknown":[26],"cost":[27],"functions":[28,103],"of":[29,76,123],"an":[30,50,57],"expert":[31,78],"from":[33],"its":[34],"demonstrated":[35],"behavior.":[36],"We":[37,64],"begin":[38],"developing":[40],"model-based":[42],"RL":[44,70,99,127],"algorithm":[45,71],"including":[46],"two":[47],"update":[48,54],"loops:1)":[49],"inner-loop":[51],"optimal":[52,60,87],"control":[53,61,88],"and":[55,79,89,115],"2)":[56],"outer-loop":[58],"(IOC)":[62],"update.":[63],"then":[65],"introduce":[66],"model-free":[68],"that":[72,104],"uses":[73],"online":[74],"behaviors":[75],"without":[82],"knowing":[83],"their":[84],"dynamics.":[85],"The":[86,101],"IOC":[90],"as":[93],"subproblems":[94],"in":[95],"both":[96,113],"proposed":[97,125],"algorithms.":[100,128],"reward":[102],"finds":[108],"proven":[110],"to":[111],"be":[112],"stabilizing":[114],"nonunique.":[116],"Simulated":[117],"case":[118],"studies":[119],"validate":[120],"effectiveness":[122]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}