{"id":"https://openalex.org/W3207544809","doi":"https://doi.org/10.1109/tcyb.2022.3179775","title":"Empirical Policy Optimization for <i>n</i>-Player Markov Games","display_name":"Empirical Policy Optimization for <i>n</i>-Player Markov Games","publication_year":2022,"publication_date":"2022-06-24","ids":{"openalex":"https://openalex.org/W3207544809","doi":"https://doi.org/10.1109/tcyb.2022.3179775","mag":"3207544809","pmid":"https://pubmed.ncbi.nlm.nih.gov/35749334"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2022.3179775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2022.3179775","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"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/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 Management and Control for Complex 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 Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"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/A5006442353","display_name":"Weifan Li","orcid":"https://orcid.org/0000-0003-1871-8355"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"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/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":"Weifan Li","raw_affiliation_strings":["State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"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/A5103832112","display_name":"Mengchen Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengchen Zhao","raw_affiliation_strings":["Noah&#x2019;s Ark Laboratory, Huawei, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Noah&#x2019;s Ark Laboratory, Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["Noah&#x2019;s Ark Laboratory, Huawei, Beijing, China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Noah&#x2019;s Ark Laboratory, Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"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/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 Management and Control for Complex 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 Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"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":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4931,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90365246,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"53","issue":"10","first_page":"6443","last_page":"6455"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9803000092506409,"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":0.8263152241706848},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7574385404586792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7443156242370605},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6969754099845886},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6243735551834106},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5621731877326965},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.49139657616615295},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.47341710329055786},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4456847906112671},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.44489002227783203},{"id":"https://openalex.org/keywords/markov-perfect-equilibrium","display_name":"Markov perfect equilibrium","score":0.4418136477470398},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.4337821304798126},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4318443536758423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3110392689704895},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21146774291992188},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1398889124393463},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.13911288976669312}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8263152241706848},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7574385404586792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443156242370605},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6969754099845886},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6243735551834106},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5621731877326965},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.49139657616615295},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.47341710329055786},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4456847906112671},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.44489002227783203},{"id":"https://openalex.org/C67091656","wikidata":"https://www.wikidata.org/wiki/Q6771328","display_name":"Markov perfect equilibrium","level":3,"score":0.4418136477470398},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.4337821304798126},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4318443536758423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3110392689704895},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21146774291992188},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1398889124393463},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.13911288976669312},{"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2022.3179775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2022.3179775","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:35749334","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35749334","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2968709009","display_name":null,"funder_award_id":"2018AAA0101005","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6023506935","display_name":null,"funder_award_id":"XDA27030400","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"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"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W180051558","https://openalex.org/W1191599655","https://openalex.org/W1491706803","https://openalex.org/W1542941925","https://openalex.org/W1575592356","https://openalex.org/W1717133655","https://openalex.org/W1771410628","https://openalex.org/W1788877992","https://openalex.org/W1849094143","https://openalex.org/W1964757264","https://openalex.org/W1967250398","https://openalex.org/W1973474784","https://openalex.org/W2002373723","https://openalex.org/W2085963752","https://openalex.org/W2114134981","https://openalex.org/W2116718598","https://openalex.org/W2121863487","https://openalex.org/W2129454099","https://openalex.org/W2144274908","https://openalex.org/W2145339207","https://openalex.org/W2167732364","https://openalex.org/W2291986326","https://openalex.org/W2405379562","https://openalex.org/W2568214755","https://openalex.org/W2575731723","https://openalex.org/W2593044849","https://openalex.org/W2736601468","https://openalex.org/W2752024324","https://openalex.org/W2766447205","https://openalex.org/W2781726626","https://openalex.org/W2783096200","https://openalex.org/W2803973384","https://openalex.org/W2885541157","https://openalex.org/W2907669392","https://openalex.org/W2913409451","https://openalex.org/W2922444559","https://openalex.org/W2925418831","https://openalex.org/W2949608212","https://openalex.org/W2951301202","https://openalex.org/W2951713757","https://openalex.org/W2963184621","https://openalex.org/W2963890729","https://openalex.org/W2964164283","https://openalex.org/W2964381205","https://openalex.org/W2967474307","https://openalex.org/W2970537473","https://openalex.org/W2974589008","https://openalex.org/W2982316857","https://openalex.org/W2989838630","https://openalex.org/W2990022244","https://openalex.org/W2995938461","https://openalex.org/W2996634922","https://openalex.org/W2998555768","https://openalex.org/W3004418671","https://openalex.org/W3035780950","https://openalex.org/W3036687207","https://openalex.org/W3042871037","https://openalex.org/W3093785081","https://openalex.org/W3100292177","https://openalex.org/W3106491339","https://openalex.org/W3110979110","https://openalex.org/W3174422131","https://openalex.org/W3174819736","https://openalex.org/W3175240969","https://openalex.org/W3196869853","https://openalex.org/W4200008856","https://openalex.org/W4232630730","https://openalex.org/W4254547512","https://openalex.org/W4287391791","https://openalex.org/W4294789298","https://openalex.org/W4295598622","https://openalex.org/W4297789683","https://openalex.org/W6607392825","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6638036514","https://openalex.org/W6677095636","https://openalex.org/W6681187623","https://openalex.org/W6696772115","https://openalex.org/W6741002519","https://openalex.org/W6743367460","https://openalex.org/W6749304979","https://openalex.org/W6754803952","https://openalex.org/W6758729514","https://openalex.org/W6768536907","https://openalex.org/W6779806417","https://openalex.org/W6785161469","https://openalex.org/W6801058317","https://openalex.org/W6804360855","https://openalex.org/W7073685127"],"related_works":["https://openalex.org/W4214835929","https://openalex.org/W4226086326","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4281478226","https://openalex.org/W4255368532","https://openalex.org/W2126257849","https://openalex.org/W3144388779","https://openalex.org/W3119014777","https://openalex.org/W1570906179"],"abstract_inverted_index":{"In":[0,18,52],"single-agent":[1],"Markov":[2,20],"decision":[3],"processes,":[4],"an":[5,91,119,130],"agent":[6,37],"can":[7],"optimize":[8],"its":[9,86,94,152],"policy":[10,81,132,153],"based":[11,154],"on":[12,155,168,179],"the":[13,16,24,30,36,57,165,177],"interaction":[14,25],"with":[15,125,148],"environment.":[17],"multiplayer":[19],"games":[21],"(MGs),":[22],"however,":[23],"is":[26,77,118,136],"nonstationary":[27],"due":[28],"to":[29,78,83,114,121,163,175],"behaviors":[31],"of":[32,59,93,104],"other":[33],"players,":[34],"so":[35],"has":[38],"no":[39],"fixed":[40],"optimization":[41,133],"objective.":[42],"The":[43,75],"challenge":[44],"becomes":[45],"finding":[46],"equilibrium":[47],"policies":[48,61],"for":[49,72,101],"all":[50],"players.":[51],"this":[53],"research,":[54],"we":[55,128],"treat":[56],"evolution":[58],"player":[60,150],"as":[62],"a":[63,68,102,115,139,145,172],"dynamical":[64],"process":[65],"and":[66,142,171],"propose":[67],"novel":[69],"learning":[70,109],"scheme":[71,110],"Nash":[73,122],"equilibrium.":[74,123],"core":[76],"evolve":[79],"one's":[80],"according":[82],"not":[84],"just":[85],"current":[87],"in-game":[88],"performance,":[89],"but":[90],"aggregation":[92],"performance":[95],"over":[96],"history.":[97],"We":[98,158],"show":[99,176],"that":[100,117],"variety":[103],"MGs,":[105,170],"players":[106],"in":[107,138,144],"our":[108],"will":[111],"provably":[112],"converge":[113],"point":[116],"approximation":[120],"Combined":[124],"neural":[126],"networks,":[127],"develop":[129],"empirical":[131],"algorithm,":[134],"which":[135],"implemented":[137],"reinforcement-learning":[140],"framework":[141],"runs":[143],"distributed":[146],"way,":[147],"each":[149],"optimizing":[151],"own":[156],"observations.":[157],"use":[159],"two":[160],"numerical":[161],"examples":[162],"validate":[164],"convergence":[166],"property":[167],"small-scale":[169],"pong":[173],"example":[174],"potential":[178],"large":[180],"games.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2021-10-25T00:00:00"}