{"id":"https://openalex.org/W3131320743","doi":"https://doi.org/10.1109/tnnls.2021.3054685","title":"Data-Based Optimal Consensus Control for Multiagent Systems With Policy Gradient Reinforcement Learning","display_name":"Data-Based Optimal Consensus Control for Multiagent Systems With Policy Gradient Reinforcement Learning","publication_year":2021,"publication_date":"2021-02-16","ids":{"openalex":"https://openalex.org/W3131320743","doi":"https://doi.org/10.1109/tnnls.2021.3054685","mag":"3131320743","pmid":"https://pubmed.ncbi.nlm.nih.gov/33587707"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3054685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3054685","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5073886757","display_name":"Xindi Yang","orcid":"https://orcid.org/0000-0003-2822-9002"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xindi Yang","raw_affiliation_strings":["Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China","Department of Control Science and Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396911","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-4527-9610"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China","Department of Control Science and Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040673729","display_name":"Zhuping Wang","orcid":"https://orcid.org/0000-0002-0334-4082"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuping Wang","raw_affiliation_strings":["Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China","Department of Control Science and Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073886757"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":5.6034,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.96352626,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"33","issue":"8","first_page":"3872","last_page":"3883"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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":1.0,"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":0.9912999868392944,"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":0.9908999800682068,"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":0.8255420923233032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7735817432403564},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7507498264312744},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.70872962474823},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6351516842842102},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5673608183860779},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5144729614257812},{"id":"https://openalex.org/keywords/consensus","display_name":"Consensus","score":0.48430219292640686},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.44180047512054443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34822964668273926},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3305153250694275},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21768927574157715},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14481914043426514}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8255420923233032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7735817432403564},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7507498264312744},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.70872962474823},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6351516842842102},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5673608183860779},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5144729614257812},{"id":"https://openalex.org/C107107730","wikidata":"https://www.wikidata.org/wiki/Q2994424","display_name":"Consensus","level":3,"score":0.48430219292640686},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.44180047512054443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34822964668273926},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3305153250694275},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21768927574157715},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14481914043426514},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3054685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3054685","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:33587707","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33587707","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G1375595937","display_name":null,"funder_award_id":"61922063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5565712806","display_name":null,"funder_award_id":"61733013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7116811465","display_name":null,"funder_award_id":"17ZR1445800","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"},{"id":"https://openalex.org/G8682232932","display_name":null,"funder_award_id":"19ZR1461400","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"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":39,"referenced_works":["https://openalex.org/W1606119439","https://openalex.org/W1863485266","https://openalex.org/W1991119064","https://openalex.org/W2013895638","https://openalex.org/W2020688906","https://openalex.org/W2048687352","https://openalex.org/W2086977346","https://openalex.org/W2087063454","https://openalex.org/W2092215165","https://openalex.org/W2107396783","https://openalex.org/W2107726111","https://openalex.org/W2108383324","https://openalex.org/W2125088529","https://openalex.org/W2141126179","https://openalex.org/W2146979682","https://openalex.org/W2148439597","https://openalex.org/W2153275646","https://openalex.org/W2162496869","https://openalex.org/W2320262435","https://openalex.org/W2339745223","https://openalex.org/W2477669843","https://openalex.org/W2491324263","https://openalex.org/W2508598219","https://openalex.org/W2512097721","https://openalex.org/W2548277951","https://openalex.org/W2550394442","https://openalex.org/W2789789879","https://openalex.org/W2797305442","https://openalex.org/W2809115421","https://openalex.org/W2907214660","https://openalex.org/W2913173906","https://openalex.org/W2963177211","https://openalex.org/W3015130121","https://openalex.org/W4206336194","https://openalex.org/W4214717370","https://openalex.org/W4307347247","https://openalex.org/W6684205842","https://openalex.org/W6692846177","https://openalex.org/W6921331664"],"related_works":["https://openalex.org/W2784200061","https://openalex.org/W2784026553","https://openalex.org/W2511063373","https://openalex.org/W3127518712","https://openalex.org/W3088852461","https://openalex.org/W2113824758","https://openalex.org/W3046085425","https://openalex.org/W2118264468","https://openalex.org/W2963943213","https://openalex.org/W2335243741"],"abstract_inverted_index":{"This":[0],"article":[1],"investigates":[2],"the":[3,47,71,76,82,105,121,158,168,173,178,185,197,200],"optimally":[4],"distributed":[5,31,55,90],"consensus":[6],"control":[7,56],"problem":[8,22],"for":[9,60],"discrete-time":[10],"multiagent":[11,61,119],"systems":[12,62],"with":[13,30],"completely":[14],"unknown":[15],"dynamics":[16],"and":[17,35,96,104,163,175],"computational":[18,115],"ability":[19,116],"differences.":[20],"The":[21,94],"can":[23],"be":[24],"viewed":[25],"as":[26],"solving":[27],"nonzero-sum":[28],"games":[29],"reinforcement":[32],"learning":[33,51,112],"(RL),":[34],"each":[36,138],"agent":[37,139],"is":[38,58,124,140,154],"a":[39,53,79],"player":[40],"in":[41,118,130,161],"these":[42],"games.":[43],"First,":[44],"to":[45,109,126,156,189,195],"guarantee":[46],"real-time":[48,80],"performance":[49,87],"of":[50,78,137,142,170,177,199],"algorithms,":[52],"data-based":[54],"algorithm":[57,84,123,160],"proposed":[59,83,122,159,201],"using":[63],"offline":[64],"system":[65,86],"interaction":[66],"data":[67,73],"sets.":[68],"By":[69],"utilizing":[70],"interactive":[72],"produced":[74],"during":[75],"run":[77],"system,":[81],"improves":[85],"based":[88,100],"on":[89,101,167],"policy":[91,133],"gradient":[92],"RL.":[93],"convergence":[95,174],"stability":[97],"are":[98,181,193],"guaranteed":[99,182],"functional":[102],"analysis":[103],"Lyapunov":[106],"method.":[107],"Second,":[108],"address":[110],"asynchronous":[111,128,164],"caused":[113],"by":[114,183],"differences":[117],"systems,":[120],"extended":[125],"an":[127,146],"version":[129],"which":[131,149],"executing":[132],"improvement":[134],"or":[135],"not":[136],"independent":[141],"its":[143],"neighbors.":[144],"Furthermore,":[145],"actor-critic":[147],"structure,":[148],"contains":[150],"two":[151],"neural":[152,179],"networks,":[153],"developed":[155],"implement":[157],"synchronous":[162],"cases.":[165],"Based":[166],"method":[169],"weighted":[171],"residuals,":[172],"optimality":[176],"networks":[180],"proving":[184],"approximation":[186],"errors":[187],"converge":[188],"zero.":[190],"Finally,":[191],"simulations":[192],"conducted":[194],"show":[196],"effectiveness":[198],"algorithm.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":6}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}