{"id":"https://openalex.org/W3155344062","doi":"https://doi.org/10.1109/lsp.2021.3071962","title":"Decentralized TD(0) With Gradient Tracking","display_name":"Decentralized TD(0) With Gradient Tracking","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3155344062","doi":"https://doi.org/10.1109/lsp.2021.3071962","mag":"3155344062"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2021.3071962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3071962","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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/A5101999069","display_name":"Qifeng Lin","orcid":"https://orcid.org/0000-0003-0523-8811"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qifeng Lin","raw_affiliation_strings":["School of Computer Science, and Engineering, and Guangdong Province Key Laboratory of Computational Science, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0523-8811","affiliations":[{"raw_affiliation_string":"School of Computer Science, and Engineering, and Guangdong Province Key Laboratory of Computational Science, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029820392","display_name":"Qing Ling","orcid":"https://orcid.org/0000-0003-4222-5964"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Ling","raw_affiliation_strings":["School of Computer Science, and Engineering, and Guangdong Province Key Laboratory of Computational Science, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4222-5964","affiliations":[{"raw_affiliation_string":"School of Computer Science, and Engineering, and Guangdong Province Key Laboratory of Computational Science, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":1.0634,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.77621046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"28","issue":null,"first_page":"723","last_page":"727"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9998999834060669,"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":0.9959999918937683,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9948999881744385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6746308207511902},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.645561695098877},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6222811341285706},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6032623052597046},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5938809514045715},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5826621651649475},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.5203402042388916},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4553620219230652},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44597768783569336},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.43508094549179077},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.43201589584350586},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.41890373826026917},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2988235652446747},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.27435803413391113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20958197116851807},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.09233364462852478}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6746308207511902},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.645561695098877},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6222811341285706},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6032623052597046},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5938809514045715},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5826621651649475},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.5203402042388916},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4553620219230652},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44597768783569336},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.43508094549179077},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.43201589584350586},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.41890373826026917},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2988235652446747},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27435803413391113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20958197116851807},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.09233364462852478},{"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/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2021.3071962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3071962","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4442155276","display_name":null,"funder_award_id":"2020B1212060032","funder_id":"https://openalex.org/F4320330330","funder_display_name":"Guangdong Province Key Laboratory of Computational Science"},{"id":"https://openalex.org/G4787191783","display_name":null,"funder_award_id":"61973324","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320330330","display_name":"Guangdong Province Key Laboratory of Computational Science","ror":null},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1918371733","https://openalex.org/W2044212084","https://openalex.org/W2100677568","https://openalex.org/W2110395839","https://openalex.org/W2119112357","https://openalex.org/W2121863487","https://openalex.org/W2134042548","https://openalex.org/W2139418546","https://openalex.org/W2575705757","https://openalex.org/W2763533254","https://openalex.org/W2806236558","https://openalex.org/W2911283328","https://openalex.org/W2944956041","https://openalex.org/W2947958009","https://openalex.org/W2962856794","https://openalex.org/W2963023064","https://openalex.org/W2963228337","https://openalex.org/W2963616027","https://openalex.org/W2963649943","https://openalex.org/W2964123095","https://openalex.org/W3006380006","https://openalex.org/W3027121709","https://openalex.org/W3034741284","https://openalex.org/W3037229067","https://openalex.org/W3041202696","https://openalex.org/W3100513551","https://openalex.org/W3104888543","https://openalex.org/W3136903997","https://openalex.org/W4214717370","https://openalex.org/W4299802797","https://openalex.org/W6680307681","https://openalex.org/W6738796088","https://openalex.org/W6747035473","https://openalex.org/W6751658861","https://openalex.org/W6762191990","https://openalex.org/W6774804355","https://openalex.org/W6780179245"],"related_works":["https://openalex.org/W263682811","https://openalex.org/W2846499288","https://openalex.org/W2564172750","https://openalex.org/W3197592642","https://openalex.org/W3199158697","https://openalex.org/W2356977358","https://openalex.org/W2302465375","https://openalex.org/W2098528027","https://openalex.org/W2088605360","https://openalex.org/W2379811207"],"abstract_inverted_index":{"In":[0,43],"this":[1],"letter,":[2],"we":[3,109],"consider":[4],"the":[5,14,23,33,44,72,78,80,91,95,102,118,147,154],"policy":[6,29],"evaluation":[7],"problem":[8],"with":[9,25,113],"linear":[10],"function":[11],"approximation":[12],"in":[13,106],"context":[15],"of":[16,74,120],"decentralized":[17,40,107,114,156],"multi-agent":[18],"reinforcement":[19],"learning":[20],"(MARL),":[21],"where":[22],"agents":[24,92],"a":[26,39,62],"fixed":[27],"joint":[28],"cooperate":[30],"to":[31,71,116],"estimate":[32],"global":[34],"expected":[35],"accumulative":[36],"reward":[37,75],"through":[38],"communication":[41],"network.":[42],"existing":[45],"algorithms,":[46],"every":[47],"agent":[48],"updates":[49],"its":[50,55],"local":[51,57,63,81],"parameter":[52],"by":[53,101],"combining":[54],"neighboring":[56],"parameters":[58],"and":[59,97,140],"then":[60],"running":[61],"stochastic":[64,82],"temporal-difference(0)":[65],"(TD(0))":[66],"gradient":[67,103,111,132,138,141],"step.":[68],"However,":[69],"due":[70],"diversity":[73],"functions":[76],"across":[77],"agents,":[79],"TD(0)":[83,115,157],"gradients":[84],"can":[85],"be":[86],"very":[87],"different,":[88],"which":[89],"hinders":[90],"from":[93],"reaching":[94,121],"consensual":[96],"optimal":[98],"parameter.":[99],"Motivated":[100],"tracking":[104,112,139],"strategy":[105],"optimization,":[108],"combine":[110],"accelerate":[117],"process":[119],"consensus.":[122,142],"We":[123],"also":[124],"propose":[125],"two":[126],"other":[127],"acceleration":[128],"strategies,":[129],"one":[130],"is":[131],"consensus":[133],"while":[134],"another":[135],"jointly":[136],"uses":[137],"Numerical":[143],"experiments":[144],"demonstrate":[145],"that":[146],"proposed":[148],"algorithms":[149],"attain":[150],"faster":[151],"convergence":[152],"than":[153],"popular":[155],"method.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}