{"id":"https://openalex.org/W4413393844","doi":"https://doi.org/10.23919/acc63710.2025.11107753","title":"Distributed Nash Control of Multiplayer Multiagent Differential Games with Reinforcement Learning","display_name":"Distributed Nash Control of Multiplayer Multiagent Differential Games with Reinforcement Learning","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413393844","doi":"https://doi.org/10.23919/acc63710.2025.11107753"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11107753","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","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/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bosen Lian","raw_affiliation_strings":["Auburn University,Department of Electrical and Computer Engineering,Auburn,AL,USA,36849"],"affiliations":[{"raw_affiliation_string":"Auburn University,Department of Electrical and Computer Engineering,Auburn,AL,USA,36849","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101743497","display_name":"Yizhong Zhang","orcid":"https://orcid.org/0000-0002-4312-0040"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yizhong Zhang","raw_affiliation_strings":["Auburn University,Department of Electrical and Computer Engineering,Auburn,AL,USA,36849"],"affiliations":[{"raw_affiliation_string":"Auburn University,Department of Electrical and Computer Engineering,Auburn,AL,USA,36849","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102973745","display_name":"Wenqian Xue","orcid":"https://orcid.org/0000-0002-3670-3854"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenqian Xue","raw_affiliation_strings":["University of Florida,Department of Mechanical and Aerospace Engineering,Gainesville,FL,USA,32608"],"affiliations":[{"raw_affiliation_string":"University of Florida,Department of Mechanical and Aerospace Engineering,Gainesville,FL,USA,32608","institution_ids":["https://openalex.org/I33213144"]}]},{"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"]},{"id":"https://openalex.org/I1310985481","display_name":"Botanical Research Institute of Texas","ror":"https://ror.org/02wxwab08","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1310985481"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["University of Texas at Arlington,UTA Research Institute,Fort Worth,TX,USA,76118"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington,UTA Research Institute,Fort Worth,TX,USA,76118","institution_ids":["https://openalex.org/I1310985481","https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001862814"],"corresponding_institution_ids":["https://openalex.org/I82497590"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29010329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"791","last_page":"796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.710099995136261,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.710099995136261,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6797999739646912,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7604233026504517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7185064554214478},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6413462162017822},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.4772883951663971},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4602929353713989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24701958894729614},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.15110692381858826},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10756120085716248},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09407761693000793}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7604233026504517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7185064554214478},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6413462162017822},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.4772883951663971},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4602929353713989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24701958894729614},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.15110692381858826},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10756120085716248},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09407761693000793},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc63710.2025.11107753","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2011671151","https://openalex.org/W2068949505","https://openalex.org/W2072302088","https://openalex.org/W2075093452","https://openalex.org/W2108383324","https://openalex.org/W2123876595","https://openalex.org/W2160643434","https://openalex.org/W2475651303","https://openalex.org/W2531648764","https://openalex.org/W2983464671","https://openalex.org/W3047879910","https://openalex.org/W3137906938","https://openalex.org/W3209777177","https://openalex.org/W4246447829","https://openalex.org/W4285306065","https://openalex.org/W4385194856","https://openalex.org/W4387083432","https://openalex.org/W4392476537","https://openalex.org/W4400078339"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"This":[0],"paper":[1],"formulates":[2],"multiplayer":[3,14],"multiagent":[4,15],"differential":[5],"games":[6,29,47,93],"to":[7,38,68],"design":[8],"the":[9,28,46,49,53,70,88,91],"optimal":[10,40],"containment":[11],"control":[12,23,41,73],"of":[13,45,52,90],"systems.":[16],"Distributed":[17],"Nash":[18,72],"equilibrium":[19],"(simplified":[20],"as":[21],"Nash)":[22],"policies":[24],"are":[25,57],"designed":[26,92],"within":[27],"using":[30],"only":[31],"local":[32,54],"agents\u2019":[33],"trajectories,":[34],"enabling":[35],"all":[36],"players":[37],"implement":[39],"simultaneously.":[42],"The":[43],"solvability":[44],"and":[48,94],"asymptotic":[50],"stability":[51],"error":[55],"system":[56,77,82],"ensured.":[58],"A":[59],"data-driven":[60],"integral":[61],"reinforcement":[62],"learning":[63],"(RL)":[64],"algorithm":[65],"is":[66],"devised":[67],"compute":[69],"distributed":[71],"online":[74],"by":[75],"leveraging":[76],"trajectories":[78],"without":[79],"knowing":[80],"explicit":[81],"dynamics.":[83],"Finally,":[84],"simulation":[85],"results":[86],"verify":[87],"effectiveness":[89],"algorithms.":[95]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}