{"id":"https://openalex.org/W3187450731","doi":"https://doi.org/10.24963/ijcai.2021/70","title":"MFVFD: A Multi-Agent Q-Learning Approach to Cooperative and Non-Cooperative Tasks","display_name":"MFVFD: A Multi-Agent Q-Learning Approach to Cooperative and Non-Cooperative Tasks","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3187450731","doi":"https://doi.org/10.24963/ijcai.2021/70","mag":"3187450731"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/70","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/70","pdf_url":"https://www.ijcai.org/proceedings/2021/0070.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0070.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100669565","display_name":"Tianhao Zhang","orcid":"https://orcid.org/0000-0002-5939-3932"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianhao Zhang","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089028438","display_name":"Qiwei Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiwei Ye","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101544241","display_name":"Jiang Bian","orcid":"https://orcid.org/0000-0002-9472-600X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang Bian","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044920558","display_name":"Guangming Xie","orcid":"https://orcid.org/0000-0001-6504-0087"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Xie","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101884287","display_name":"Tie\u2010Yan Liu","orcid":"https://orcid.org/0000-0002-0476-8020"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tie-Yan Liu","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100669565"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.3597,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84512794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"500","last_page":"506"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958999752998352,"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":0.9958999752998352,"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/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9742000102996826,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7575732469558716},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7257742881774902},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5907098054885864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5135693550109863},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49982404708862305},{"id":"https://openalex.org/keywords/cooperative-game-theory","display_name":"Cooperative game theory","score":0.48879072070121765},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4600169360637665},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.41109681129455566},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38760635256767273},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3301212191581726},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.21888861060142517},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15473228693008423},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.11006975173950195}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7575732469558716},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7257742881774902},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5907098054885864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5135693550109863},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49982404708862305},{"id":"https://openalex.org/C2781416736","wikidata":"https://www.wikidata.org/wiki/Q105354050","display_name":"Cooperative game theory","level":3,"score":0.48879072070121765},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4600169360637665},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.41109681129455566},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38760635256767273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3301212191581726},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.21888861060142517},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15473228693008423},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.11006975173950195},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/70","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/70","pdf_url":"https://www.ijcai.org/proceedings/2021/0070.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/70","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/70","pdf_url":"https://www.ijcai.org/proceedings/2021/0070.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3187450731.pdf","grobid_xml":"https://content.openalex.org/works/W3187450731.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W1540380506","https://openalex.org/W1542941925","https://openalex.org/W1588316674","https://openalex.org/W1964257800","https://openalex.org/W1972645710","https://openalex.org/W2011000015","https://openalex.org/W2053518311","https://openalex.org/W2057169303","https://openalex.org/W2120327309","https://openalex.org/W2120846115","https://openalex.org/W2134779831","https://openalex.org/W2565610523","https://openalex.org/W2602275733","https://openalex.org/W2746553466","https://openalex.org/W2766413382","https://openalex.org/W2785315072","https://openalex.org/W2807741983","https://openalex.org/W2893175095","https://openalex.org/W2899076365","https://openalex.org/W2949561945","https://openalex.org/W2949963774","https://openalex.org/W2963403868","https://openalex.org/W2963934958","https://openalex.org/W3008684691","https://openalex.org/W3037725723","https://openalex.org/W3046288222","https://openalex.org/W3093287223","https://openalex.org/W3107615218","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W4301501993","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Value":[0],"function":[1,31,42],"decomposition":[2,32],"(VFD)":[3],"methods":[4,25],"under":[5],"the":[6,39,65,79],"popular":[7],"paradigm":[8],"of":[9,86],"centralized":[10],"training":[11],"and":[12,55,67],"decentralized":[13],"execution":[14],"(CTDE)":[15],"have":[16],"promoted":[17],"multi-agent":[18,49],"reinforcement":[19],"learning":[20],"progress.":[21],"However,":[22],"existing":[23,94],"VFD":[24],"proceed":[26],"from":[27],"a":[28,47],"group's":[29],"value":[30,41],"to":[33],"only":[34],"solve":[35],"cooperative":[36,54],"tasks.":[37],"With":[38],"individual":[40],"decomposition,":[43],"we":[44],"propose":[45],"MFVFD,":[46],"novel":[48],"Q-learning":[50],"approach":[51],"for":[52],"solving":[53],"non-cooperative":[56],"tasks":[57,83],"based":[58],"on":[59,64,78],"mean-field":[60],"theory.":[61],"Our":[62],"analysis":[63],"Hawk-Dove":[66],"Nonmonotonic":[68],"Cooperation":[69],"matrix":[70],"games":[71],"evaluate":[72],"MFVFD's":[73],"convergent":[74],"solution.":[75],"Empirical":[76],"studies":[77],"challenging":[80],"mixed":[81],"cooperative-competitive":[82],"where":[84],"hundreds":[85],"agents":[87],"coexist":[88],"demonstrate":[89],"that":[90],"MFVFD":[91],"significantly":[92],"outperforms":[93],"baselines.":[95]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}