{"id":"https://openalex.org/W3160714878","doi":"https://doi.org/10.1109/icpr48806.2021.9412176","title":"Self-Play or Group Practice: Learning to Play Alternating Markov Game in Multi-Agent System","display_name":"Self-Play or Group Practice: Learning to Play Alternating Markov Game in Multi-Agent System","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3160714878","doi":"https://doi.org/10.1109/icpr48806.2021.9412176","mag":"3160714878"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110838463","display_name":"Chin-Wing Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chin-Wing Leung","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052387391","display_name":"Shuyue Hu","orcid":"https://orcid.org/0000-0002-1908-1344"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shuyue Hu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022683388","display_name":"Ho-fung Leung","orcid":"https://orcid.org/0000-0003-4914-2934"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ho-Fung Leung","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9234","last_page":"9241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11031","display_name":"Game Theory and Applications","score":0.9889000058174133,"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":0.9839000105857849,"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":0.8778913021087646},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7550908327102661},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7118182182312012},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.6488175392150879},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6384091377258301},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6004272699356079},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5712553858757019},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5669616460800171},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5013704299926758},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.44580143690109253},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.44004014134407043},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41264063119888306},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3832172155380249},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3582228422164917},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.2998424470424652},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1254783570766449}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8778913021087646},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7550908327102661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7118182182312012},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.6488175392150879},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6384091377258301},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6004272699356079},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5712553858757019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5669616460800171},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5013704299926758},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.44580143690109253},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.44004014134407043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41264063119888306},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3832172155380249},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3582228422164917},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.2998424470424652},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1254783570766449},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W17749007","https://openalex.org/W32403112","https://openalex.org/W1481965470","https://openalex.org/W1506975691","https://openalex.org/W1542941925","https://openalex.org/W1548889916","https://openalex.org/W1564582110","https://openalex.org/W1626977535","https://openalex.org/W1965118359","https://openalex.org/W2016320057","https://openalex.org/W2074008662","https://openalex.org/W2089415692","https://openalex.org/W2099618002","https://openalex.org/W2102256448","https://openalex.org/W2103437045","https://openalex.org/W2120846115","https://openalex.org/W2131600418","https://openalex.org/W2135949932","https://openalex.org/W2142377488","https://openalex.org/W2145339207","https://openalex.org/W2147750403","https://openalex.org/W2175712524","https://openalex.org/W2574978968","https://openalex.org/W2604873668","https://openalex.org/W2617547828","https://openalex.org/W2618097077","https://openalex.org/W2620645529","https://openalex.org/W2766447205","https://openalex.org/W2770298516","https://openalex.org/W2787259794","https://openalex.org/W2808584951","https://openalex.org/W2810602713","https://openalex.org/W2895865957","https://openalex.org/W2898585845","https://openalex.org/W2902907165","https://openalex.org/W2951799422","https://openalex.org/W2951896791","https://openalex.org/W2963642149","https://openalex.org/W2964121744","https://openalex.org/W2967349019","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3005199613","https://openalex.org/W3035454135","https://openalex.org/W3091797874","https://openalex.org/W3207927678","https://openalex.org/W4233696721","https://openalex.org/W4299802797","https://openalex.org/W6636868823","https://openalex.org/W6678168664","https://openalex.org/W6736572398","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6738855998","https://openalex.org/W6755903938","https://openalex.org/W6773720453","https://openalex.org/W6802986734"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W3096874164","https://openalex.org/W4281812492","https://openalex.org/W3105579180","https://openalex.org/W2970347269","https://openalex.org/W2146763310","https://openalex.org/W3167472281","https://openalex.org/W4400868993"],"abstract_inverted_index":{"The":[0,140],"research":[1,58],"in":[2,9,52,71,136],"reinforcement":[3,22],"learning":[4,23,116,138,210],"has":[5],"achieved":[6],"great":[7],"success":[8],"strategic":[10],"game":[11,91,178,184],"playing.":[12],"These":[13],"successes":[14],"are":[15,43,112,152],"thanks":[16],"to":[17,31,68,86,143,165,220],"the":[18,32,36,137,144,149,155,169,177,183,192,200,209],"incorporation":[19],"of":[20,81,103,123,179,185,203],"deep":[21,170],"(DRL)":[24],"and":[25,131,148,168,182],"Monte":[26],"Carlo":[27],"Tree":[28],"Search":[29],"(MCTS)":[30],"agent":[33,126,135],"trained":[34,62],"under":[35,154],"self-play":[37,64],"(SP)":[38],"environment.":[39],"By":[40,107],"self-play,":[41],"agents":[42,61,82,111],"provided":[44],"with":[45,133,172],"an":[46,88,125],"incrementally":[47],"more":[48,193],"difficult":[49],"curriculum":[50],"which":[51],"turn":[53],"facilitates":[54],"learning.":[55],"However,":[56],"recent":[57],"suggests":[59],"that":[60,189,208],"via":[63],"may":[65],"easily":[66],"lead":[67],"getting":[69],"stuck":[70],"local":[72,218],"equilibria.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77],"consider":[78],"a":[79,95,101],"population":[80,102],"each":[83],"independently":[84],"learns":[85],"play":[87],"alternating":[89],"Markov":[90],"(AMG).":[92],"We":[93,187,205],"propose":[94],"new":[96],"training":[97,195],"framework-group":[98],"practice-":[99],"for":[100,120],"decentralized":[104],"RL":[105],"agents.":[106,221],"group":[108],"practice":[109],"(GP),":[110],"assigned":[113],"into":[114],"multiple":[115],"groups":[117],"during":[118],"training,":[119],"every":[121],"episode":[122],"games,":[124],"is":[127,160,191],"randomly":[128],"paired":[129],"up":[130],"practices":[132],"another":[134],"group.":[139],"convergence":[141],"result":[142],"optimal":[145],"value":[146],"function":[147],"Nash":[150],"equilibrium":[151],"proved":[153],"GP":[156,164,190],"framework.":[157],"Experimental":[158],"study":[159],"conducted":[161],"by":[162],"applying":[163,217],"Q-learning":[166,171],"algorithm":[167],"Monte-Carlo":[173],"tree":[174],"search":[175],"on":[176],"Connect":[180],"Four":[181],"Hex.":[186],"verify":[188],"efficient":[194],"scheme":[196],"than":[197],"SP":[198],"given":[199],"same":[201],"amount":[202],"training.":[204],"also":[206],"show":[207],"effectiveness":[211],"can":[212],"even":[213],"be":[214],"improved":[215],"when":[216],"grouping":[219]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}