{"id":"https://openalex.org/W4394744014","doi":"https://doi.org/10.1109/tetci.2024.3383454","title":"FM3Q: Factorized Multi-Agent MiniMax Q-Learning for Two-Team Zero-Sum Markov Game","display_name":"FM3Q: Factorized Multi-Agent MiniMax Q-Learning for Two-Team Zero-Sum Markov Game","publication_year":2024,"publication_date":"2024-04-12","ids":{"openalex":"https://openalex.org/W4394744014","doi":"https://doi.org/10.1109/tetci.2024.3383454"},"language":"en","primary_location":{"id":"doi:10.1109/tetci.2024.3383454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2024.3383454","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational Intelligence","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/A5014614157","display_name":"Guangzheng Hu","orcid":"https://orcid.org/0000-0001-8035-7410"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangzheng Hu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8035-7410","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080193690","display_name":"Yuanheng Zhu","orcid":"https://orcid.org/0000-0001-5384-423X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5384-423X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327745","display_name":"Haoran Li","orcid":"https://orcid.org/0000-0003-2559-9585"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Li","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2559-9585","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8218-9633","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.704,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85503178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"8","issue":"6","first_page":"4033","last_page":"4045"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.8805999755859375,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.8805999755859375,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.8338000178337097,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.8252000212669373,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/zero-sum-game","display_name":"Zero-sum game","score":0.8214049339294434},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.7291330695152283},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.7109774351119995},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.67690509557724},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.45160046219825745},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.44326668977737427},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.43971729278564453},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39309921860694885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3883219063282013},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.3691927194595337},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3628042936325073},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.32776308059692383},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2833261489868164},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15977174043655396}],"concepts":[{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.8214049339294434},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.7291330695152283},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.7109774351119995},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.67690509557724},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.45160046219825745},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.44326668977737427},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.43971729278564453},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39309921860694885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3883219063282013},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3691927194595337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3628042936325073},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.32776308059692383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2833261489868164},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15977174043655396},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetci.2024.3383454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2024.3383454","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5782916338","display_name":null,"funder_award_id":"4232056","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G800914696","display_name":null,"funder_award_id":"62136008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8179479325","display_name":null,"funder_award_id":"62293541","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W2145339207","https://openalex.org/W2902907165","https://openalex.org/W2963890729","https://openalex.org/W2982316857","https://openalex.org/W2996896271","https://openalex.org/W2997338169","https://openalex.org/W3084241738","https://openalex.org/W3093785081","https://openalex.org/W3110979110","https://openalex.org/W3113301408","https://openalex.org/W3165472686","https://openalex.org/W3196869853","https://openalex.org/W3207544809","https://openalex.org/W3210169707","https://openalex.org/W4281553483","https://openalex.org/W4293255096","https://openalex.org/W4312576764","https://openalex.org/W4383533414","https://openalex.org/W4385488528","https://openalex.org/W6606719070","https://openalex.org/W6631168379","https://openalex.org/W6678168664","https://openalex.org/W6679100793","https://openalex.org/W6682074005","https://openalex.org/W6743367460","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6758729514","https://openalex.org/W6768536907","https://openalex.org/W6772005887","https://openalex.org/W6772619952","https://openalex.org/W6780812528","https://openalex.org/W6783838878","https://openalex.org/W6784152626","https://openalex.org/W6790900645","https://openalex.org/W6800877681","https://openalex.org/W6802325372","https://openalex.org/W6803644465","https://openalex.org/W6804321159","https://openalex.org/W6840380725","https://openalex.org/W6845758549","https://openalex.org/W6850742479","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W1970303738","https://openalex.org/W3141427172","https://openalex.org/W3152424015","https://openalex.org/W187740018","https://openalex.org/W2804582172","https://openalex.org/W2162286586","https://openalex.org/W2057383904","https://openalex.org/W4255368532","https://openalex.org/W1565282301","https://openalex.org/W2276575217"],"abstract_inverted_index":{"Many":[0],"real-world":[1],"applications":[2],"involve":[3],"some":[4],"agents":[5],"that":[6,13],"fall":[7],"into":[8,115],"two":[9],"teams,":[10],"with":[11,38,134],"payoffs":[12],"are":[14,47],"equal":[15],"within":[16],"the":[17,25,69,75,82,110,122,144,160,171],"same":[18],"team":[19],"but":[20],"of":[21,52,55,162,177],"opposite":[22],"sign":[23],"across":[24],"opponent":[26],"team.":[27],"The":[28],"so-called":[29],"two-team":[30,78,151],"zero-sum":[31],"Markov":[32],"games":[33],"(2t0sMGs)":[34],"can":[35,108],"be":[36],"resolved":[37],"reinforcement":[39,99],"learning":[40,100,132,172],"in":[41,50,89],"recent":[42],"years.":[43],"However,":[44],"existing":[45],"methods":[46],"thus":[48],"inefficient":[49],"light":[51],"insufficient":[53],"consideration":[54],"intra-team":[56],"credit":[57],"assignment,":[58],"data":[59],"utilization,":[60],"and":[61,81,118,142,146,174,179],"computational":[62],"intractability.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,94,165],"propose":[68],"individual-global-minimax":[70],"(IGMM)":[71],"principle":[72],"to":[73,139,158,169],"ensure":[74],"coherence":[76],"between":[77],"minimax":[79,112,124,148],"behaviors":[80,85],"individual":[83,116],"greedy":[84],"through":[86],"Q":[87,113,125],"functions":[88,126],"2t0sMGs.":[90,128,184],"Based":[91],"on":[92,183],"it,":[93],"present":[95],"a":[96],"novel":[97],"multi-agent":[98],"framework,":[101],"Factorized":[102],"Multi-Agent":[103],"MiniMax":[104],"Q-Learning":[105],"(FM3Q),":[106],"which":[107],"factorize":[109],"joint":[111],"function":[114],"ones":[117],"iteratively":[119],"solve":[120],"for":[121,127,150],"IGMM-satisfied":[123],"Moreover,":[129],"an":[130],"online":[131],"algorithm":[133],"neural":[135],"networks":[136],"is":[137,156],"proposed":[138],"implement":[140],"FM3Q":[141,178],"obtain":[143],"deterministic":[145],"decentralized":[147],"policies":[149],"players.":[152],"A":[153],"theoretical":[154],"analysis":[155],"provided":[157],"prove":[159],"convergence":[161],"FM3Q.":[163],"Empirically,":[164],"use":[166],"three":[167],"environments":[168],"evaluate":[170],"efficiency":[173],"final":[175],"performance":[176],"show":[180],"its":[181],"superiority":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}