{"id":"https://openalex.org/W3201527781","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533484","title":"Multi-Agent Cognition Difference Reinforcement Learning for Multi-Agent Cooperation","display_name":"Multi-Agent Cognition Difference Reinforcement Learning for Multi-Agent Cooperation","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3201527781","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533484","mag":"3201527781"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5075244395","display_name":"Huimu Wang","orcid":"https://orcid.org/0000-0001-7115-8831"},"institutions":[{"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/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":true,"raw_author_name":"Huimu Wang","raw_affiliation_strings":["School of Artificial Intelligence University of Chinese Academy of Sciences Institute of Automation Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence University of Chinese Academy of Sciences Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043281824","display_name":"Tenghai Qiu","orcid":"https://orcid.org/0000-0002-0312-5728"},"institutions":[{"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tenghai Qiu","raw_affiliation_strings":["Institute of Automation Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412085","display_name":"Zhen Liu","orcid":"https://orcid.org/0000-0003-1610-2338"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Liu","raw_affiliation_strings":["Institute of Automation Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"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/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/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":"Zhiqiang Pu","raw_affiliation_strings":["Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019541846","display_name":"Jianqiang Yi","orcid":"https://orcid.org/0000-0003-3268-9482"},"institutions":[{"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/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":"Jianqiang Yi","raw_affiliation_strings":["Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045244118","display_name":"Wanmai Yuan","orcid":"https://orcid.org/0000-0002-7140-1835"},"institutions":[{"id":"https://openalex.org/I4210130112","display_name":"China Academy of Information and Communications Technology","ror":"https://ror.org/038dte259","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210130112","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanmai Yuan","raw_affiliation_strings":["China Academy of Electronics and Information Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"China Academy of Electronics and Information Technology, Beijing, China","institution_ids":["https://openalex.org/I4210130112"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075244395"],"corresponding_institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63540988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.998199999332428,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9937000274658203,"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"}},{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.978600025177002,"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":0.817456066608429},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7468066215515137},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5968363881111145},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5402668714523315},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4994645118713379},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4781523644924164},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.45270344614982605},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4335816204547882},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3580257296562195},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3327176570892334},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08023932576179504},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07792022824287415}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.817456066608429},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7468066215515137},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5968363881111145},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5402668714523315},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4994645118713379},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4781523644924164},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.45270344614982605},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4335816204547882},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3580257296562195},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3327176570892334},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08023932576179504},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07792022824287415},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.5199999809265137,"display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G1594336315","display_name":null,"funder_award_id":"2018AAA0102404","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G85968781","display_name":null,"funder_award_id":"CXYJJ19-ZD-02,CXYJJ20-QN-05","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W297279189","https://openalex.org/W1542941925","https://openalex.org/W1959608418","https://openalex.org/W2121863487","https://openalex.org/W2123838014","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2225156818","https://openalex.org/W2547875792","https://openalex.org/W2575705757","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2756196406","https://openalex.org/W2776126823","https://openalex.org/W2785315072","https://openalex.org/W2803155336","https://openalex.org/W2808261958","https://openalex.org/W2894976951","https://openalex.org/W2920426271","https://openalex.org/W2948342290","https://openalex.org/W2949794851","https://openalex.org/W2953326790","https://openalex.org/W2962938168","https://openalex.org/W2962966033","https://openalex.org/W2963039558","https://openalex.org/W2963588154","https://openalex.org/W2963717208","https://openalex.org/W2963858333","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964338167","https://openalex.org/W2982316857","https://openalex.org/W2991479173","https://openalex.org/W2998367975","https://openalex.org/W3007999377","https://openalex.org/W3096726323","https://openalex.org/W3101380508","https://openalex.org/W3112965912","https://openalex.org/W4214717370","https://openalex.org/W4285723986","https://openalex.org/W4288336223","https://openalex.org/W4289363497","https://openalex.org/W4299802797","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6713411898","https://openalex.org/W6729448088","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6744537943","https://openalex.org/W6747941106","https://openalex.org/W6751139674","https://openalex.org/W6755069753","https://openalex.org/W6755542948","https://openalex.org/W6760783655","https://openalex.org/W6763173156"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370","https://openalex.org/W3038962357","https://openalex.org/W2189613824"],"abstract_inverted_index":{"Multi-agent":[0],"cooperation":[1,26],"is":[2,85,108,127],"one":[3],"of":[4,35,93,143,157],"the":[5,25,41,66,72,131,135,153,158],"most":[6],"attractive":[7],"research":[8],"fields":[9],"in":[10,20,29,87,96],"multi-agent":[11,79],"systems.":[12],"There":[13],"are":[14],"many":[15,55],"attempts":[16],"made":[17],"by":[18,54],"researchers":[19],"this":[21,88],"field":[22],"to":[23,61,110,114,129],"promote":[24],"behavior.":[27],"However,":[28],"partially-observable":[30],"environments,":[31],"a":[32,75,102],"large":[33],"number":[34],"agents":[36,42,56,136],"and":[37,101,148,155],"complex":[38,132],"interactions":[39,133],"among":[40,134],"cause":[43],"huge":[44],"difficulty":[45],"for":[46],"policy":[47,67],"learning.":[48],"Moreover,":[49],"redundant":[50],"communication":[51,104],"contents":[52],"caused":[53],"make":[57],"effective":[58],"features":[59],"hard":[60],"be":[62],"extracted,":[63],"which":[64],"prevents":[65],"from":[68],"converging.":[69],"To":[70],"address":[71],"limitations":[73],"above,":[74],"novel":[76],"method":[77],"called":[78],"cognition":[80,97,124],"difference":[81,98],"reinforcement":[82],"learning":[83],"(MACD-RL)":[84],"proposed":[86,159],"paper.":[89],"The":[90,141],"key":[91],"feature":[92],"MACD-RL":[94],"lies":[95],"network":[99,105],"(CDN)":[100],"soft":[103,138],"(SCN).":[106],"CDN":[107],"designed":[109,128],"allow":[111],"each":[112],"agent":[113],"choose":[115],"its":[116,122],"neighbors":[117],"(communication":[118],"targets)":[119],"adaptively":[120],"with":[121,137],"environment":[123],"difference.":[125],"SCN":[126],"handle":[130],"attention":[139],"mechanism.":[140],"results":[142],"simulations":[144],"including":[145],"mixed":[146],"cooperative":[147],"competitive":[149],"tasks":[150],"demonstrate":[151],"that":[152],"effectiveness":[154],"robustness":[156],"model.":[160]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}