{"id":"https://openalex.org/W4385482683","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191654","title":"Causal Mean Field Multi-Agent Reinforcement Learning","display_name":"Causal Mean Field Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385482683","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191654"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191654","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.14200","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101108881","display_name":"Hao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I131434179","display_name":"Nanjing University of Chinese Medicine","ror":"https://ror.org/04523zj19","country_code":"CN","type":"education","lineage":["https://openalex.org/I131434179"]},{"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/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"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Ma","raw_affiliation_strings":["School of Nanjing, University of Chinese Academy of Sciences,Beijing,China","Chinese Academy of Sciences, Institute of Automation, Beijing, China","School of Nanjing, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Nanjing, University of Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210165038","https://openalex.org/I131434179"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Nanjing, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060319097","display_name":"Zhiqiang Pu","orcid":"https://orcid.org/0000-0002-4841-4048"},"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":"Zhiqiang Pu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China","Chinese Academy of Sciences, Institute of Automation, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"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":"Chinese Academy of Sciences, Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I4210112150","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/A5102234458","display_name":"Yi Pan","orcid":"https://orcid.org/0009-0009-5417-6013"},"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/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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Pan","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences,Beijing,China","Chinese Academy of Sciences, Institute of Automation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000412491","display_name":"Boyin Liu","orcid":null},"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":"Boyin Liu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China","Chinese Academy of Sciences, Institute of Automation, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"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":"Chinese Academy of Sciences, Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I4210112150","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/A5102508721","display_name":"Junlong Gao","orcid":"https://orcid.org/0009-0008-6579-5330"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlong Gao","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101634327","display_name":"Zhenyu Guo","orcid":"https://orcid.org/0000-0002-2869-429X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Guo","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101108881"],"corresponding_institution_ids":["https://openalex.org/I131434179","https://openalex.org/I19820366","https://openalex.org/I4210112150","https://openalex.org/I4210165038","https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.1744,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55279805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9821000099182129,"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/T10260","display_name":"Software Engineering Research","score":0.980400025844574,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8505274653434753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7259407043457031},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.7207618951797485},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6792200207710266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5589160323143005},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.49801135063171387},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48335498571395874},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45098504424095154},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3827723562717438},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13583338260650635}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8505274653434753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7259407043457031},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.7207618951797485},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6792200207710266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5589160323143005},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.49801135063171387},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48335498571395874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45098504424095154},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3827723562717438},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13583338260650635},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191654","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.14200","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.14200","pdf_url":"https://arxiv.org/pdf/2502.14200","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.14200","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.14200","pdf_url":"https://arxiv.org/pdf/2502.14200","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1501375624","https://openalex.org/W1972645710","https://openalex.org/W2057169303","https://openalex.org/W2098627973","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2785315072","https://openalex.org/W2885305518","https://openalex.org/W2894976951","https://openalex.org/W2903583264","https://openalex.org/W2904675649","https://openalex.org/W2917286209","https://openalex.org/W2963390684","https://openalex.org/W2963658727","https://openalex.org/W2963934958","https://openalex.org/W2982316857","https://openalex.org/W2991046523","https://openalex.org/W3012934742","https://openalex.org/W3100930738","https://openalex.org/W3156295478","https://openalex.org/W3188155443","https://openalex.org/W3198151161","https://openalex.org/W3211373382","https://openalex.org/W4220858968","https://openalex.org/W4251305326","https://openalex.org/W4283262646","https://openalex.org/W4285613100","https://openalex.org/W4286981685","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W6629985540","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6747941106","https://openalex.org/W6749304979","https://openalex.org/W6755069753","https://openalex.org/W6758588779","https://openalex.org/W6758732251","https://openalex.org/W6771904302","https://openalex.org/W6779753894","https://openalex.org/W6794679647","https://openalex.org/W6798214966"],"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/W2389214306","https://openalex.org/W2081494945","https://openalex.org/W2389053294","https://openalex.org/W2024136090","https://openalex.org/W4391331176"],"abstract_inverted_index":{"Scalability":[0],"remains":[1],"a":[2,34,38,114,162,167,186],"challenge":[3],"in":[4,161,180,183,193],"multi-agent":[5],"reinforcement":[6,18],"learning":[7,19],"and":[8,166,191],"is":[9,81,126],"currently":[10],"under":[11,51],"active":[12],"research.":[13],"A":[14],"framework":[15,43],"named":[16],"mean-field":[17,72],"(MFRL)":[20],"could":[21],"alleviate":[22],"the":[23,28,45,77,86,89,95,105,108,120,131,136,146],"scalability":[24,78,178],"problem":[25,36],"by":[26],"employing":[27],"Mean":[29],"Field":[30],"Theory":[31],"to":[32,47,75,154],"turn":[33],"many-agent":[35],"into":[37,113],"two-agent":[39],"problem.":[40,79],"However,":[41],"this":[42],"lacks":[44],"ability":[46],"identify":[48],"essential":[49,121],"interactions":[50],"nonstationary":[52],"environments.":[53],"Causality":[54],"contains":[55],"relatively":[56],"invariant":[57],"mechanisms":[58],"behind":[59,107],"interactions,":[60],"though":[61,93],"environments":[62,184,194],"are":[63],"nonstationary.":[64],"Therefore,":[65],"we":[66,103,134],"propose":[67],"an":[68],"algorithm":[69],"called":[70],"causal":[71,116,156],"Q-learning":[73],"(CMFQ)":[74],"address":[76],"CMFQ":[80,160],"ever":[82],"more":[83,197],"robust":[84],"toward":[85],"change":[87],"of":[88,91,98,111,123,143,149,189],"number":[90,188],"agents":[92,144,190],"inheriting":[94],"compressed":[96],"representation":[97,139],"MFRL's":[99],"action-state":[100],"space.":[101],"Firstly,":[102],"model":[104,117],"causality":[106],"decision-making":[109],"process":[110],"MFRL":[112],"structural":[115],"(SCM).":[118],"Then":[119],"degree":[122],"each":[124],"interaction":[125],"quantified":[127],"via":[128],"intervening":[129],"on":[130],"SCM.":[132],"Furthermore,":[133],"design":[135],"causality-aware":[137],"compact":[138],"for":[140],"behavioral":[141,151],"information":[142,152],"as":[145],"weighted":[147],"sum":[148],"all":[150],"according":[153],"their":[155],"effects.":[157],"We":[158],"test":[159],"mixed":[163],"cooperative-competitive":[164],"game":[165],"cooperative":[168],"game.":[169],"The":[170],"result":[171],"shows":[172],"that":[173],"our":[174],"method":[175],"has":[176],"excellent":[177],"performance":[179],"both":[181],"training":[182],"containing":[185,195],"large":[187],"testing":[192],"much":[196],"agents.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}