{"id":"https://openalex.org/W4380032322","doi":"https://doi.org/10.1109/jiot.2023.3284510","title":"Distributed Neural Learning Algorithms for Multiagent Reinforcement Learning","display_name":"Distributed Neural Learning Algorithms for Multiagent Reinforcement Learning","publication_year":2023,"publication_date":"2023-06-09","ids":{"openalex":"https://openalex.org/W4380032322","doi":"https://doi.org/10.1109/jiot.2023.3284510"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2023.3284510","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/jiot.2023.3284510","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","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/A5100705693","display_name":"Pengcheng Dai","orcid":"https://orcid.org/0000-0003-1455-7216"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Dai","raw_affiliation_strings":["Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1455-7216","affiliations":[{"raw_affiliation_string":"Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069640828","display_name":"Hongzhe Liu","orcid":"https://orcid.org/0000-0002-6887-368X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhe Liu","raw_affiliation_strings":["Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6887-368X","affiliations":[{"raw_affiliation_string":"Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenwu Yu","orcid":"https://orcid.org/0000-0001-6406-2399"},"institutions":[{"id":"https://openalex.org/I4210155350","display_name":"Purple Mountain Laboratories","ror":"https://ror.org/04zcbk583","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210155350"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Yu","raw_affiliation_strings":["Frontiers Science Center for Mobile Information Communication and Security, School of Mathematics, Southeast University, Nanjing, China","Purple Mountain Laboratories, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-6406-2399","affiliations":[{"raw_affiliation_string":"Frontiers Science Center for Mobile Information Communication and Security, School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"Purple Mountain Laboratories, Nanjing, China","institution_ids":["https://openalex.org/I4210155350"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351665","display_name":"He Wang","orcid":"https://orcid.org/0000-0002-3065-393X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Wang","raw_affiliation_strings":["Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1727,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50198727,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"10","issue":"23","first_page":"21039","last_page":"21060"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9987000226974487,"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":0.9987000226974487,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.7591913938522339},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7132463455200195},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6906511783599854},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.6284528374671936},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6123983860015869},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6042041778564453},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.5800849199295044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48055222630500793},{"id":"https://openalex.org/keywords/distributed-algorithm","display_name":"Distributed algorithm","score":0.4624035954475403},{"id":"https://openalex.org/keywords/types-of-artificial-neural-networks","display_name":"Types of artificial neural networks","score":0.4121185839176178},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39794209599494934},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.25093162059783936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591913938522339},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7132463455200195},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6906511783599854},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.6284528374671936},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6123983860015869},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6042041778564453},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.5800849199295044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48055222630500793},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.4624035954475403},{"id":"https://openalex.org/C177973122","wikidata":"https://www.wikidata.org/wiki/Q7860946","display_name":"Types of artificial neural networks","level":4,"score":0.4121185839176178},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39794209599494934},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.25093162059783936},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2023.3284510","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/jiot.2023.3284510","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.6700000166893005}],"awards":[{"id":"https://openalex.org/G2227361669","display_name":null,"funder_award_id":"BM2017002","funder_id":"https://openalex.org/F4320330188","funder_display_name":"Jiangsu Provincial Key Laboratory of Networked Collective Intelligence, Southeast University"},{"id":"https://openalex.org/G4949000581","display_name":null,"funder_award_id":"62073076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7139063063","display_name":null,"funder_award_id":"BK20210216","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G7846504898","display_name":null,"funder_award_id":"62233004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G883240379","display_name":null,"funder_award_id":"2022ZD0120002","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330188","display_name":"Jiangsu Provincial Key Laboratory of Networked Collective Intelligence, Southeast University","ror":null},{"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":32,"referenced_works":["https://openalex.org/W1918371733","https://openalex.org/W2114791779","https://openalex.org/W2139418546","https://openalex.org/W2145339207","https://openalex.org/W2581108373","https://openalex.org/W2809148419","https://openalex.org/W2915117209","https://openalex.org/W2924131335","https://openalex.org/W2958746411","https://openalex.org/W2963616027","https://openalex.org/W2966633400","https://openalex.org/W2967474307","https://openalex.org/W2968782695","https://openalex.org/W2969195240","https://openalex.org/W3016207298","https://openalex.org/W3081103181","https://openalex.org/W3109546547","https://openalex.org/W3174056649","https://openalex.org/W4205501012","https://openalex.org/W4214717370","https://openalex.org/W4226059675","https://openalex.org/W4285114354","https://openalex.org/W6683195989","https://openalex.org/W6749032143","https://openalex.org/W6751972096","https://openalex.org/W6760724441","https://openalex.org/W6762191990","https://openalex.org/W6762786500","https://openalex.org/W6762819967","https://openalex.org/W6765601489","https://openalex.org/W6767941141","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W3021988786","https://openalex.org/W2979432606","https://openalex.org/W3099311996","https://openalex.org/W3119329039","https://openalex.org/W4306703873","https://openalex.org/W2964123095","https://openalex.org/W1553308207","https://openalex.org/W2772472730","https://openalex.org/W3119645134","https://openalex.org/W1501293601"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"the":[3,23,36,60,76,87,97,113,117,120,128,133,141,144,152,155],"fully":[4],"distributed":[5,38,61,98,156],"neural":[6,10,62,71,99,157],"learning":[7,17,63,100,158],"algorithms":[8,39,64,101,122,142],"by":[9,42,67,86,126],"network":[11,72],"approximation":[12,73],"for":[13,90],"networked":[14],"multiagent":[15],"reinforcement":[16],"(NMARL)":[18],"are":[19,40,65,108,123],"studied.":[20],"To":[21,56],"tackle":[22],"convergence":[24,118],"analysis":[25],"of":[26,35,53,80,119,137,154],"methods":[27],"in":[28],"NMARL":[29,82,114],"with":[30,102],"tremendous":[31],"state-action":[32],"space,":[33],"most":[34],"existing":[37],"designed":[41],"linear":[43],"function":[44],"approximation,":[45],"which":[46],"however":[47],"would":[48],"fall":[49],"into":[50],"a":[51,69],"situation":[52],"poor":[54],"expression.":[55],"conquer":[57],"such":[58],"limitation,":[59],"developed":[66],"using":[68],"novel":[70],"that":[74],"bridges":[75],"theory":[77],"and":[78,105],"practice":[79],"deep":[81],"(DMARL).":[83],"Specifically,":[84],"inspired":[85],"overparametrization":[88,129],"method":[89,130],"minimizing":[91],"mean-squared":[92],"projected":[93],"bellman":[94],"error":[95],"(MSPBE),":[96],"population":[103],"semigradients":[104,107],"stochastic":[106],"respectively,":[109],"proposed":[110,121],"to":[111,131,139],"solve":[112],"problem.":[115],"Furthermore,":[116],"strictly":[124],"given":[125],"employing":[127],"establish":[132],"approximate":[134],"stationary":[135],"point":[136],"MSPBE":[138],"characterize":[140],"toward":[143],"global":[145],"optimum.":[146],"Finally,":[147],"some":[148],"numerical":[149],"simulations":[150],"demonstrate":[151],"effectiveness":[153],"algorithms.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}