{"id":"https://openalex.org/W4415969707","doi":"https://doi.org/10.1109/iecon58223.2025.11221592","title":"A New Approach for Consensus Control with Multi-Agent Reinforcement Learning","display_name":"A New Approach for Consensus Control with Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W4415969707","doi":"https://doi.org/10.1109/iecon58223.2025.11221592"},"language":null,"primary_location":{"id":"doi:10.1109/iecon58223.2025.11221592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon58223.2025.11221592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2025 \u2013 51st Annual Conference of the IEEE Industrial Electronics Society","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100369313","display_name":"Yue Yang","orcid":"https://orcid.org/0009-0003-5641-2899"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yue","raw_affiliation_strings":["Hangzhou Dianzi University,School of Automation,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University,School of Automation,Hangzhou,China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058644929","display_name":"Qiang L\u00fc","orcid":"https://orcid.org/0000-0001-8217-2305"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Lu","raw_affiliation_strings":["Hangzhou Dianzi University,School of Automation,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University,School of Automation,Hangzhou,China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018457813","display_name":"Fengmin Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengmin Yu","raw_affiliation_strings":["Hangzhou Dianzi University,School of Automation,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University,School of Automation,Hangzhou,China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102023865","display_name":"Fan Yang","orcid":"https://orcid.org/0009-0001-0601-3334"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Hangzhou Dianzi University,School of Automation,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University,School of Automation,Hangzhou,China","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.39910000562667847,"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":0.39910000562667847,"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":0.27869999408721924,"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":0.2678000032901764,"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":0.8276000022888184},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5841000080108643},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.550599992275238},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5435000061988831},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5081999897956848},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.45019999146461487},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3010999858379364}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8276000022888184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6894000172615051},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5841000080108643},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.550599992275238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5468000173568726},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5435000061988831},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5081999897956848},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37929999828338623},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.29409998655319214},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C155386361","wikidata":"https://www.wikidata.org/wiki/Q1649571","display_name":"Process control","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.2597000002861023}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iecon58223.2025.11221592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon58223.2025.11221592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2025 \u2013 51st Annual Conference of the IEEE Industrial Electronics Society","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1998109019","https://openalex.org/W2012812921","https://openalex.org/W2099175737","https://openalex.org/W2107396783","https://openalex.org/W2125668987","https://openalex.org/W2165744313","https://openalex.org/W2342938949","https://openalex.org/W2343497731","https://openalex.org/W2560814118","https://openalex.org/W2611346233","https://openalex.org/W2737628516","https://openalex.org/W2763354547","https://openalex.org/W2768779900","https://openalex.org/W2889856497","https://openalex.org/W2948942255","https://openalex.org/W3128164051","https://openalex.org/W3128397403","https://openalex.org/W4388286312"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5],"multi-agent":[6,19],"reinforcement":[7,28],"learning":[8,29],"approach":[9,44,69],"to":[10],"address":[11],"the":[12,33,42,52,60,65,83],"design":[13],"problem":[14],"of":[15,36,67,75,80],"control":[16,22],"strategy":[17],"for":[18],"consensus.":[20],"Distributed":[21],"policy":[23],"is":[24],"learned":[25],"automatically":[26],"through":[27],"algorithm,":[30],"thereby":[31],"circumventing":[32],"intricate":[34],"process":[35],"controller":[37],"design.":[38],"To":[39],"be":[40],"specific,":[41],"proposed":[43],"exhibits":[45],"notable":[46],"consistency":[47],"performance":[48],"in":[49,59,82],"scenarios":[50],"wherein":[51],"agents\u2019":[53],"initial":[54,73],"positions":[55,74,81],"differs":[56],"from":[57],"that":[58],"training":[61],"environment.":[62],"We":[63],"confirm":[64],"effectiveness":[66],"our":[68],"by":[70],"using":[71],"several":[72],"agents":[76],"and":[77],"different":[78],"dimensionality":[79],"simulations.":[84]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-06T00:00:00"}