{"id":"https://openalex.org/W4380078504","doi":"https://doi.org/10.1109/twc.2023.3279268","title":"The Gradient Convergence Bound of Federated Multi-Agent Reinforcement Learning With Efficient Communication","display_name":"The Gradient Convergence Bound of Federated Multi-Agent Reinforcement Learning With Efficient Communication","publication_year":2023,"publication_date":"2023-06-09","ids":{"openalex":"https://openalex.org/W4380078504","doi":"https://doi.org/10.1109/twc.2023.3279268"},"language":"en","primary_location":{"id":"doi:10.1109/twc.2023.3279268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/twc.2023.3279268","pdf_url":null,"source":{"id":"https://openalex.org/S63459445","display_name":"IEEE Transactions on Wireless Communications","issn_l":"1536-1276","issn":["1536-1276","1558-2248"],"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 Wireless Communications","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/A5027890741","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0003-4564-470X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xing Xu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014842979","display_name":"Rongpeng Li","orcid":"https://orcid.org/0000-0003-4297-5060"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongpeng Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036831868","display_name":"Zhifeng Zhao","orcid":"https://orcid.org/0000-0002-5479-7890"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Zhao","raw_affiliation_strings":["Zhejiang Lab, Hangzhou, China","College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100626780","display_name":"Honggang Zhang","orcid":"https://orcid.org/0000-0003-1492-1364"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honggang Zhang","raw_affiliation_strings":["Zhejiang Lab, Hangzhou, China","College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027890741"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":2.9579,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.92690737,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"23","issue":"1","first_page":"507","last_page":"528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9986000061035156,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9986000061035156,"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":0.996399998664856,"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/T13553","display_name":"Age of Information Optimization","score":0.9937999844551086,"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":0.8858063220977783},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7977447509765625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7959169149398804},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7378196716308594},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6921496391296387},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.49560844898223877},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4661394953727722},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4646453559398651},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4432965815067291},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.43097156286239624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39045360684394836},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3688476085662842},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.25556695461273193},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11482846736907959},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07875123620033264}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8858063220977783},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7977447509765625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7959169149398804},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7378196716308594},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6921496391296387},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.49560844898223877},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4661394953727722},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4646453559398651},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4432965815067291},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.43097156286239624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39045360684394836},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3688476085662842},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25556695461273193},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11482846736907959},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07875123620033264},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/twc.2023.3279268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/twc.2023.3279268","pdf_url":null,"source":{"id":"https://openalex.org/S63459445","display_name":"IEEE Transactions on Wireless Communications","issn_l":"1536-1276","issn":["1536-1276","1558-2248"],"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 Wireless Communications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G5459816226","display_name":null,"funder_award_id":"62071425","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6722698454","display_name":null,"funder_award_id":"LR23F010005","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1641379095","https://openalex.org/W1828849564","https://openalex.org/W2099618002","https://openalex.org/W2107726111","https://openalex.org/W2113059852","https://openalex.org/W2131600418","https://openalex.org/W2145339207","https://openalex.org/W2160643434","https://openalex.org/W2245795247","https://openalex.org/W2535838896","https://openalex.org/W2556660792","https://openalex.org/W2724382637","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2783596173","https://openalex.org/W2793948820","https://openalex.org/W2795242006","https://openalex.org/W2900182564","https://openalex.org/W2904246096","https://openalex.org/W2913044204","https://openalex.org/W2913845934","https://openalex.org/W2962788286","https://openalex.org/W2962863496","https://openalex.org/W2963433607","https://openalex.org/W2964043796","https://openalex.org/W2970020383","https://openalex.org/W2995022099","https://openalex.org/W3013198946","https://openalex.org/W3016207298","https://openalex.org/W3025869479","https://openalex.org/W3028270327","https://openalex.org/W3047079385","https://openalex.org/W3047304572","https://openalex.org/W3047357290","https://openalex.org/W3087172506","https://openalex.org/W3094368349","https://openalex.org/W3100789280","https://openalex.org/W3113079445","https://openalex.org/W3131448887","https://openalex.org/W3134277527","https://openalex.org/W3212066104","https://openalex.org/W4206054900","https://openalex.org/W4214717370","https://openalex.org/W4285260612","https://openalex.org/W4297687186","https://openalex.org/W4313043980","https://openalex.org/W4319303175","https://openalex.org/W4377562264","https://openalex.org/W6622473587","https://openalex.org/W6634413486","https://openalex.org/W6638018090","https://openalex.org/W6684205842","https://openalex.org/W6692846177","https://openalex.org/W6720643467","https://openalex.org/W6730236268","https://openalex.org/W6736572398","https://openalex.org/W6739994853","https://openalex.org/W6741002519","https://openalex.org/W6745458143","https://openalex.org/W6749652452","https://openalex.org/W6751646691","https://openalex.org/W6752012617","https://openalex.org/W6754143808","https://openalex.org/W6755921573","https://openalex.org/W6757592117","https://openalex.org/W6758491413","https://openalex.org/W6766831760","https://openalex.org/W6769116889","https://openalex.org/W6775160012","https://openalex.org/W6782559215","https://openalex.org/W6791518594"],"related_works":["https://openalex.org/W4206903459","https://openalex.org/W4283028824","https://openalex.org/W2754816816","https://openalex.org/W3046901963","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4362706668","https://openalex.org/W4231621013","https://openalex.org/W3171021120","https://openalex.org/W3008318776"],"abstract_inverted_index":{"The":[0],"paper":[1,94,156],"considers":[2],"independent":[3,48],"reinforcement":[4,84],"learning":[5,16,49,85],"(IRL)":[6],"for":[7,162],"multi-agent":[8],"collaborative":[9],"decision-making":[10],"in":[11,173],"the":[12,45,63,67,74,81,112,120,130,139,175],"paradigm":[13],"of":[14,38,47,73,114,122,141],"federated":[15],"(FL).":[17],"However,":[18],"FL":[19],"generates":[20],"excessive":[21],"communication":[22],"overheads":[23],"between":[24],"agents":[25,39,52,131,149],"and":[26,66,80,126,166,171,182],"a":[27,35,115,133,135,143],"remote":[28],"central":[29],"server,":[30],"especially":[31],"when":[32],"it":[33],"involves":[34],"large":[36],"number":[37],"or":[40],"iterations.":[41],"Besides,":[42],"due":[43],"to":[44,101],"heterogeneity":[46],"environments,":[50],"multiple":[51],"may":[53],"undergo":[54],"asynchronous":[55],"Markov":[56],"decision":[57],"processes":[58],"(MDPs),":[59],"which":[60],"will":[61],"affect":[62],"training":[64],"samples":[65],"model\u2019s":[68,116,144],"convergence":[69,160],"performance.":[70],"On":[71],"top":[72],"variation-aware":[75],"periodic":[76],"averaging":[77],"(VPA)":[78],"method":[79],"policy-based":[82],"deep":[83],"(DRL)":[86],"algorithm":[87],"(i.e.,":[88],"proximal":[89],"policy":[90],"optimization":[91,98],"(PPO)),":[92],"this":[93],"proposes":[95],"two":[96],"advanced":[97],"schemes":[99],"orienting":[100],"stochastic":[102],"gradient":[103],"descent":[104],"(SGD):":[105],"1)":[106],"A":[107],"decay-based":[108],"scheme":[109,137],"gradually":[110],"decays":[111],"weights":[113],"local":[117,124,145],"gradients":[118,146],"with":[119],"progress":[121],"successive":[123],"updates,":[125],"2)":[127],"By":[128],"representing":[129],"as":[132],"graph,":[134],"consensus-based":[136],"studies":[138],"impact":[140],"exchanging":[142],"among":[147],"nearby":[148],"from":[150],"an":[151],"algebraic":[152],"connectivity":[153],"perspective.":[154],"This":[155],"also":[157],"provides":[158],"novel":[159],"guarantees":[161],"both":[163],"developed":[164],"schemes,":[165],"demonstrates":[167],"their":[168],"superior":[169],"effectiveness":[170],"efficiency":[172],"improving":[174],"system\u2019s":[176],"utility":[177],"value":[178],"through":[179],"theoretical":[180],"analyses":[181],"simulation":[183],"results.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}