{"id":"https://openalex.org/W3030585287","doi":"https://doi.org/10.1109/access.2020.2997899","title":"Adaptive Learning: A New Decentralized Reinforcement Learning Approach for Cooperative Multiagent Systems","display_name":"Adaptive Learning: A New Decentralized Reinforcement Learning Approach for Cooperative Multiagent Systems","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3030585287","doi":"https://doi.org/10.1109/access.2020.2997899","mag":"3030585287"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2997899","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2997899","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09102277.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09102277.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051107809","display_name":"Menglin Li","orcid":"https://orcid.org/0000-0003-3307-5490"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Meng-Lin Li","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defence Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defence Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081802331","display_name":"Shaofei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofei Chen","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defence Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defence Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100394982","display_name":"Jing Chen","orcid":"https://orcid.org/0000-0003-3409-8651"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Chen","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defence Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defence Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051107809"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.0388,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89467164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"8","issue":null,"first_page":"99404","last_page":"99421"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.991100013256073,"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":0.8488976359367371},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8209570646286011},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5975739359855652},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5737775564193726},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.504778265953064},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.45895370841026306},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.448900431394577},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3388381600379944}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8488976359367371},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8209570646286011},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5975739359855652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5737775564193726},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.504778265953064},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.45895370841026306},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.448900431394577},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3388381600379944},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.2997899","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2997899","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09102277.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bc6f2a1503774c0ea923a2e815582f49","is_oa":true,"landing_page_url":"https://doaj.org/article/bc6f2a1503774c0ea923a2e815582f49","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 99404-99421 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.2997899","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2997899","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09102277.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2263791643","display_name":null,"funder_award_id":"61702528","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2702356746","display_name":null,"funder_award_id":"61702","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3030585287.pdf","grobid_xml":"https://content.openalex.org/works/W3030585287.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W56117469","https://openalex.org/W584625781","https://openalex.org/W1191599655","https://openalex.org/W1555689267","https://openalex.org/W1560074431","https://openalex.org/W1641379095","https://openalex.org/W1989858079","https://openalex.org/W1991119064","https://openalex.org/W2104602264","https://openalex.org/W2108892923","https://openalex.org/W2121092017","https://openalex.org/W2129936995","https://openalex.org/W2138076440","https://openalex.org/W2145339207","https://openalex.org/W2147492008","https://openalex.org/W2155968351","https://openalex.org/W2172933221","https://openalex.org/W2364538387","https://openalex.org/W2371549047","https://openalex.org/W2395575420","https://openalex.org/W2466211196","https://openalex.org/W2555255624","https://openalex.org/W2588283865","https://openalex.org/W2592798481","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2730807149","https://openalex.org/W2743009361","https://openalex.org/W2746553466","https://openalex.org/W2749807327","https://openalex.org/W2756196406","https://openalex.org/W2902982219","https://openalex.org/W2949963774","https://openalex.org/W2963658727","https://openalex.org/W2963934958","https://openalex.org/W2964043796","https://openalex.org/W2964338167","https://openalex.org/W3004640943","https://openalex.org/W3004732081","https://openalex.org/W4288594419","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W4306179383","https://openalex.org/W6602332174","https://openalex.org/W6617197716","https://openalex.org/W6627932998","https://openalex.org/W6633472260","https://openalex.org/W6675811377","https://openalex.org/W6677067356","https://openalex.org/W6677939520","https://openalex.org/W6679458411","https://openalex.org/W6680502337","https://openalex.org/W6692846177","https://openalex.org/W6712181171","https://openalex.org/W6713411898","https://openalex.org/W6719729129","https://openalex.org/W6730065366","https://openalex.org/W6734678876","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6740914062","https://openalex.org/W6743756900","https://openalex.org/W6744537943","https://openalex.org/W6746513637","https://openalex.org/W6749304979","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6773620346","https://openalex.org/W6773690109","https://openalex.org/W6780559895","https://openalex.org/W6846392434"],"related_works":["https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2120009678","https://openalex.org/W2037601570","https://openalex.org/W2912947802","https://openalex.org/W2123856982"],"abstract_inverted_index":{"Multiagent":[0],"systems":[1],"(MASs)":[2],"have":[3,49,113],"received":[4],"extensive":[5],"attention":[6],"in":[7,28,58,60,66,79,107,219,285,312],"a":[8,67,75,80,132,161,190,227,260,286,300,323],"variety":[9],"of":[10,72,91,103,168,184,239,259,265,274,283,315,320],"domains,":[11],"such":[12,136],"as":[13],"robotics":[14],"and":[15,122,187,223,333],"distributed":[16],"control.":[17],"This":[18],"paper":[19,152],"focuses":[20,154],"on":[21,33,155,199],"how":[22],"independent":[23],"learners":[24],"(ILs,":[25],"structures":[26],"used":[27],"decentralized":[29,68,188],"reinforcement":[30,192,309],"learning)":[31],"decide":[32],"their":[34],"individual":[35],"behaviors":[36],"to":[37,53,89,99,131,176,291,303],"achieve":[38],"coherent":[39],"joint":[40,56,92],"behavior.":[41],"To":[42],"date,":[43],"Reinforcement":[44],"learning(RL)":[45],"approaches":[46],"for":[47,74,195,308],"ILs":[48],"not":[50,84,139],"guaranteed":[51],"convergence":[52],"the":[54,70,101,119,156,166,171,177,182,210,216,220,232,240,250,256,263,266,275,281,305,313],"optimal":[55],"policy":[57],"scenarios":[59],"which":[61,86],"communication":[62,120],"is":[63,83,96,174,202,269],"difficult.":[64],"Especially":[65],"algorithm,":[69,327],"proportion":[71],"credit":[73],"single":[76],"agent\u2019s":[77],"action":[78],"multiagent":[81,228],"system":[82],"distinguished,":[85],"can":[87,207,243,253,288],"lead":[88],"miscoordination":[90,284,306],"actions.":[93],"Therefore,":[94,150],"it":[95,225],"highly":[97],"significant":[98],"study":[100],"mechanisms":[102,112],"coordination":[104,111,197,238,257],"between":[105,236],"agents":[106],"MASs.":[108],"Most":[109],"previous":[110],"been":[114],"carried":[115],"out":[116],"by":[117,213],"modeling":[118],"mechanism":[121],"other":[123],"agent":[124],"policies.":[125],"These":[126],"methods":[127],"are":[128,145],"applicable":[129],"only":[130],"particular":[133],"system,":[134],"so":[135],"algorithms":[137,311],"do":[138],"offer":[140],"generalizability,":[141],"especially":[142],"when":[143],"there":[144],"dozens":[146,316],"or":[147,317],"more":[148,159,270,318],"agents.":[149,163,321],"this":[151],"mainly":[153],"MAS":[157,287],"contains":[158],"than":[160,272],"dozen":[162],"By":[164,180,230],"combining":[165,224],"method":[167],"parallel":[169],"computation,":[170],"experimental":[172],"environment":[173],"closer":[175],"application":[178],"scene.":[179],"studying":[181],"paradigm":[183],"centralized":[185],"training":[186,267],"execution(CTDE),":[189],"multi-agent":[191],"learning":[193,211,234,310],"algorithm":[194,206,252],"implicit":[196],"based":[198],"TD":[200],"error":[201],"proposed.":[203],"The":[204],"new":[205,301,324],"dynamically":[208],"adjust":[209],"rate":[212,235],"deeply":[214],"analyzing":[215],"dissonance":[217],"problem":[218,282,307],"matrix":[221],"game":[222],"with":[226],"environment.":[229],"adjusting":[231],"dynamic":[233],"agents,":[237],"agents\u2019":[241],"strategies":[242],"be":[244,289,331],"achieved.":[245],"Experimental":[246],"results":[247,268,329],"show":[248],"that":[249,273],"proposed":[251],"effectively":[254],"improve":[255],"ability":[258],"MAS.":[261],"Moreover,":[262],"variance":[264],"stable":[271],"hysteretic":[276],"Q":[277],"learning(HQL)":[278],"algorithm.":[279],"Hence,":[280],"avoided":[290],"some":[292],"extent":[293],"without":[294],"additional":[295],"communication.":[296],"Our":[297],"work":[298],"provides":[299],"way":[302],"solve":[304],"scale":[314],"number":[319],"As":[322],"IL":[325],"structure":[326],"our":[328],"should":[330],"extended":[332],"further":[334],"studied.":[335]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}