{"id":"https://openalex.org/W4400078339","doi":"https://doi.org/10.1109/tcns.2024.3419823","title":"Nash-Minmax Strategy for Multiplayer Multiagent Graphical Games With Reinforcement Learning","display_name":"Nash-Minmax Strategy for Multiplayer Multiagent Graphical Games With Reinforcement Learning","publication_year":2024,"publication_date":"2024-06-27","ids":{"openalex":"https://openalex.org/W4400078339","doi":"https://doi.org/10.1109/tcns.2024.3419823"},"language":"en","primary_location":{"id":"doi:10.1109/tcns.2024.3419823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcns.2024.3419823","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/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":["Department of Electrical and Computer Engineering, Auburn University, Auburn, AL, USA","Department of Electrical and Computer Engineering, Auburn University, Auburn, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Auburn University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Auburn University, Auburn, USA","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":["Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, USA","Department of Electrical and Computer Engineering, University of Florida, Gainesville, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA","UTA Research Institute, University of Texas at Arlington, Fort Worth, USA"],"affiliations":[{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA","institution_ids":[]},{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Fort Worth, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053089078","display_name":"Ali Davoudi","orcid":"https://orcid.org/0000-0003-2951-442X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Davoudi","raw_affiliation_strings":["UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA","UTA Research Institute, University of Texas at Arlington, Fort Worth, USA"],"affiliations":[{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA","institution_ids":[]},{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Fort Worth, USA","institution_ids":[]}]}],"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":4.7811,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.9548773,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"12","issue":"1","first_page":"763","last_page":"775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8880000114440918,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8880000114440918,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.7687000036239624,"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":0.7265057563781738},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.6856405735015869},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6388700008392334},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5234931707382202},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.45020949840545654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44466838240623474},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.4372771382331848},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42435422539711},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33443957567214966},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2845742702484131},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15960511565208435},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1296548843383789},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.12360122799873352}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7265057563781738},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.6856405735015869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6388700008392334},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5234931707382202},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.45020949840545654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44466838240623474},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.4372771382331848},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42435422539711},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33443957567214966},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2845742702484131},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15960511565208435},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1296548843383789},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.12360122799873352},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcns.2024.3419823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcns.2024.3419823","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/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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1605963475","https://openalex.org/W1998380707","https://openalex.org/W2047417907","https://openalex.org/W2055300044","https://openalex.org/W2055891887","https://openalex.org/W2068949505","https://openalex.org/W2069038223","https://openalex.org/W2075093452","https://openalex.org/W2084580258","https://openalex.org/W2090677396","https://openalex.org/W2099175737","https://openalex.org/W2105850748","https://openalex.org/W2115206688","https://openalex.org/W2125256511","https://openalex.org/W2129951390","https://openalex.org/W2131363581","https://openalex.org/W2146890818","https://openalex.org/W2165744313","https://openalex.org/W2277723519","https://openalex.org/W2320262435","https://openalex.org/W2615040076","https://openalex.org/W2803623613","https://openalex.org/W2905422675","https://openalex.org/W2963177211","https://openalex.org/W2970419580","https://openalex.org/W3009014967","https://openalex.org/W3017761620","https://openalex.org/W3021399679","https://openalex.org/W3047879910","https://openalex.org/W4211097982","https://openalex.org/W4214717370","https://openalex.org/W4246447829","https://openalex.org/W4256175784","https://openalex.org/W4285306065","https://openalex.org/W4307776787","https://openalex.org/W4392476537"],"related_works":["https://openalex.org/W2016058626","https://openalex.org/W2474724840","https://openalex.org/W2963760573","https://openalex.org/W4312141693","https://openalex.org/W1536009559","https://openalex.org/W2103821767","https://openalex.org/W1969185016","https://openalex.org/W2037619003","https://openalex.org/W2111030377","https://openalex.org/W1965856819"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3],"address":[4],"the":[5,28,42,47,65,74,83,88,98,119,138,145],"synchronization":[6],"problem":[7],"in":[8,46,67,104,118],"multiplayer":[9],"multiagent":[10],"graphical":[11],"games,":[12],"where":[13,41],"each":[14,68,95],"agent":[15,23,49,69,96],"has":[16],"multiple":[17],"control":[18,30,90,100],"input":[19,31],"players.":[20],"Herein,":[21],"an":[22],"represents":[24,32],"a":[25,33,38],"system,":[26],"and":[27,81,97,113,124,148],"agent's":[29],"player's":[34],"outcome.":[35],"We":[36],"formulate":[37],"Nash-minmax":[39,114,139],"strategy,":[40],"interactions":[43,53],"of":[44,54],"players":[45,55,66,75,93,103],"same":[48],"are":[50,58,116,131],"nonzero-sum,":[51],"while":[52,73],"between":[56],"agents":[57,78],"antagonistic":[59],"(e.g.,":[60],"zero-sum":[61],"game).":[62],"That":[63],"is,":[64],"minimize":[70],"their":[71],"costs,":[72],"from":[76],"neighboring":[77,105],"go":[79],"against":[80],"maximize":[82],"costs.":[84],"This":[85],"approach":[86],"finds":[87],"Nash":[89],"solutions":[91,101,115],"for":[92,102],"within":[94],"worst":[99],"agents.":[106],"The":[107],"asymptotic":[108],"stability":[109],"under":[110],"mild":[111],"conditions":[112],"guaranteed":[117],"games.":[120],"Offline":[121],"policy":[122],"iteration":[123],"online":[125],"data-driven":[126],"off-policy":[127],"reinforcement":[128],"learning":[129],"algorithms":[130],"proposed,":[132],"with":[133],"proven":[134],"convergence,":[135],"to":[136],"compute":[137],"solutions.":[140],"A":[141],"simulation":[142],"example":[143],"validates":[144],"proposed":[146],"strategy":[147],"algorithms.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":14}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}