{"id":"https://openalex.org/W4317987702","doi":"https://doi.org/10.1109/tsipn.2023.3239654","title":"Cooperative Learning of Multi-Agent Systems Via Reinforcement Learning","display_name":"Cooperative Learning of Multi-Agent Systems Via Reinforcement Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4317987702","doi":"https://doi.org/10.1109/tsipn.2023.3239654"},"language":"en","primary_location":{"id":"doi:10.1109/tsipn.2023.3239654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsipn.2023.3239654","pdf_url":null,"source":{"id":"https://openalex.org/S4306422866","display_name":"IEEE Transactions on Signal and Information Processing over Networks","issn_l":"2373-776X","issn":["2373-776X","2373-7778"],"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 Signal and Information Processing over Networks","raw_type":"journal-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/A5100328090","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0003-2070-960X"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronic and Information Engineering, Southwest University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0003-2070-960X","affiliations":[{"raw_affiliation_string":"Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronic and Information Engineering, Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080122414","display_name":"Chen Zhao","orcid":"https://orcid.org/0000-0001-8228-4139"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Zhao","raw_affiliation_strings":["Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronic and Information Engineering, Southwest University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronic and Information Engineering, Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074290686","display_name":"Tingwen Huang","orcid":"https://orcid.org/0000-0001-9610-846X"},"institutions":[{"id":"https://openalex.org/I58152225","display_name":"Texas A&M University at Qatar","ror":"https://ror.org/03vb4dm14","country_code":"QA","type":"education","lineage":["https://openalex.org/I58152225","https://openalex.org/I91045830"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Tingwen Huang","raw_affiliation_strings":["T & M University Qatar, Doha, Qatar"],"raw_orcid":"https://orcid.org/0000-0001-9610-846X","affiliations":[{"raw_affiliation_string":"T & M University Qatar, Doha, Qatar","institution_ids":["https://openalex.org/I58152225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089771051","display_name":"Pr\u0105sun Chakrabarti","orcid":"https://orcid.org/0000-0001-8062-4144"},"institutions":[{"id":"https://openalex.org/I110116418","display_name":"Maharaja Sayajirao University of Baroda","ror":"https://ror.org/01bx8ja67","country_code":"IN","type":"education","lineage":["https://openalex.org/I110116418"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prasun Chakrabarti","raw_affiliation_strings":["ITM SLS Baroda University, Vadodara, Gujarat, India"],"raw_orcid":"https://orcid.org/0000-0001-8062-4144","affiliations":[{"raw_affiliation_string":"ITM SLS Baroda University, Vadodara, Gujarat, India","institution_ids":["https://openalex.org/I110116418"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085207296","display_name":"J\u00fcrgen Kurths","orcid":"https://orcid.org/0000-0002-5926-4276"},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]},{"id":"https://openalex.org/I60200437","display_name":"Potsdam Institute for Climate Impact Research","ror":"https://ror.org/03e8s1d88","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I60200437"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Kurths","raw_affiliation_strings":["Potsdam Institute for Climate Impact Research, Potsdam, Germany","Institute of Physics, Humboldt University of Berlin, Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5926-4276","affiliations":[{"raw_affiliation_string":"Potsdam Institute for Climate Impact Research, Potsdam, Germany","institution_ids":["https://openalex.org/I60200437"]},{"raw_affiliation_string":"Institute of Physics, Humboldt University of Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.5998,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.97872041,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"9","issue":null,"first_page":"13","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9962999820709229,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7923929691314697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7654258012771606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5921791195869446},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5839331746101379},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5123122930526733},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.43206995725631714},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4011939764022827}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7923929691314697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7654258012771606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5921791195869446},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5839331746101379},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5123122930526733},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.43206995725631714},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4011939764022827},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tsipn.2023.3239654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsipn.2023.3239654","pdf_url":null,"source":{"id":"https://openalex.org/S4306422866","display_name":"IEEE Transactions on Signal and Information Processing over Networks","issn_l":"2373-776X","issn":["2373-776X","2373-7778"],"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 Signal and Information Processing over Networks","raw_type":"journal-article"},{"id":"pmh:oai:publications.pik-potsdam.de:item_28321","is_oa":false,"landing_page_url":"https://publications.pik-potsdam.de/pubman/item/item_28321","pdf_url":null,"source":{"id":"https://openalex.org/S4306400891","display_name":"Publication Database PIK (Potsdam Institute for Climate Impact Research (PIK))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60200437","host_organization_name":"Potsdam Institute for Climate Impact Research","host_organization_lineage":["https://openalex.org/I60200437"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Signal and Information Processing over Networks","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G4963745024","display_name":null,"funder_award_id":"62276214","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1974426910","https://openalex.org/W1991284037","https://openalex.org/W2048687352","https://openalex.org/W2089684487","https://openalex.org/W2428098056","https://openalex.org/W2529357854","https://openalex.org/W2556875844","https://openalex.org/W2634239194","https://openalex.org/W2775595149","https://openalex.org/W2797818671","https://openalex.org/W2802164917","https://openalex.org/W2803208334","https://openalex.org/W2897975793","https://openalex.org/W2949235991","https://openalex.org/W2963609304","https://openalex.org/W2969925811","https://openalex.org/W2995511751","https://openalex.org/W2996590754","https://openalex.org/W3000735016","https://openalex.org/W3003040443","https://openalex.org/W3003499901","https://openalex.org/W3011033481","https://openalex.org/W3011445504","https://openalex.org/W3021399679","https://openalex.org/W3039138740","https://openalex.org/W3042939536","https://openalex.org/W3043661245","https://openalex.org/W3104140780","https://openalex.org/W3125811536","https://openalex.org/W3174955147","https://openalex.org/W3181267977","https://openalex.org/W3198269772","https://openalex.org/W3209777177","https://openalex.org/W3210830506","https://openalex.org/W4200008856","https://openalex.org/W4210710597","https://openalex.org/W4210727699","https://openalex.org/W4286664751"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"In":[0],"many":[1],"specific":[2],"scenarios,":[3],"accurateand":[4],"practical":[5,171],"cooperative":[6,22,46,88,137],"learning":[7,23,36,42,47,56,138],"is":[8],"a":[9,54,121,163],"commonly":[10],"encountered":[11],"challenge":[12],"in":[13,67,158],"multi-agent":[14,26,155],"systems.":[15],"Thus,":[16],"the":[17,40,44,61,64,68,73,79,101,105,109,113,131,147,150,154,159],"current":[18],"investigation":[19],"focuses":[20],"on":[21,72,149],"algorithms":[24],"for":[25],"systems":[27],"and":[28,81,90,108,126,145,173],"underpins":[29],"an":[30],"alternate":[31],"data-based":[32,41,115],"neural":[33,75],"network":[34],"reinforcement":[35],"framework.":[37],"To":[38],"achieve":[39],"optimization,":[43],"proposed":[45],"framework,":[48],"which":[49],"comprises":[50],"two":[51],"layers,":[52],"introduces":[53],"virtual":[55,65,106],"objective.":[57],"The":[58],"followers":[59],"learn":[60],"behaviors":[62,89],"of":[63,153],"objects":[66,107],"first":[69],"layer":[70,99],"based":[71],"adaptive":[74],"networks":[76],"(NNs).":[77],"Specifically,":[78],"actor":[80],"critic":[82],"NNs":[83],"are":[84],"applied":[85],"to":[86],"acquire":[87],"assess":[91],"this":[92,168],"layer's":[93],"long-term":[94],"utility":[95],"function.":[96],"Then":[97],"another":[98],"realizes":[100],"tracking":[102],"performance":[103,116],"between":[104],"leader":[110],"by":[111],"introducing":[112],"local":[114],"index.":[117],"Then,":[118],"we":[119],"formulate":[120],"resulting":[122],"deterministic":[123],"optimization":[124],"problem":[125],"resolve":[127],"it":[128],"effectively":[129],"with":[130],"policy":[132],"iteration":[133],"algorithm.":[134],"This":[135],"intuitive":[136],"algorithm":[139],"also":[140],"preserves":[141],"good":[142],"robustness":[143],"properties":[144],"eliminates":[146],"dependence":[148],"prior":[151],"knowledge":[152],"system":[156,166],"model":[157],"solution":[160],"process.":[161],"Finally,":[162],"multi-robot":[164],"formation":[165],"demonstrates":[167],"promising":[169],"development's":[170],"appeal":[172],"highly":[174],"effective":[175],"outcome.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}