{"id":"https://openalex.org/W2320262435","doi":"https://doi.org/10.1109/tie.2016.2542134","title":"Data-Driven Optimal Consensus Control for Discrete-Time Multi-Agent Systems With Unknown Dynamics Using Reinforcement Learning Method","display_name":"Data-Driven Optimal Consensus Control for Discrete-Time Multi-Agent Systems With Unknown Dynamics Using Reinforcement Learning Method","publication_year":2016,"publication_date":"2016-03-15","ids":{"openalex":"https://openalex.org/W2320262435","doi":"https://doi.org/10.1109/tie.2016.2542134","mag":"2320262435"},"language":"en","primary_location":{"id":"doi:10.1109/tie.2016.2542134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tie.2016.2542134","pdf_url":null,"source":{"id":"https://openalex.org/S58031724","display_name":"IEEE Transactions on Industrial Electronics","issn_l":"0278-0046","issn":["0278-0046","1557-9948"],"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 Industrial Electronics","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/A5100625792","display_name":"Huaguang Zhang","orcid":"https://orcid.org/0000-0002-2375-9824"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huaguang Zhang","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101986741","display_name":"He Jiang","orcid":"https://orcid.org/0000-0001-9841-3580"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Jiang","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064721860","display_name":"Yanhong Luo","orcid":"https://orcid.org/0000-0001-6898-7903"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhong Luo","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044730926","display_name":"Geyang Xiao","orcid":"https://orcid.org/0000-0002-7597-1034"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Geyang Xiao","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100625792"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":34.455,"has_fulltext":false,"cited_by_count":404,"citation_normalized_percentile":{"value":0.99810875,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"64","issue":"5","first_page":"4091","last_page":"4100"},"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":0.9786999821662903,"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/T12047","display_name":"Viral Infections and Vectors","score":0.9764999747276306,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7758762240409851},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.7147696018218994},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6358005404472351},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.615381121635437},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5814634561538696},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5357363224029541},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5340584516525269},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5108463168144226},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.49365314841270447},{"id":"https://openalex.org/keywords/system-dynamics","display_name":"System dynamics","score":0.4690561592578888},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.4109896719455719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2626284956932068},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2362523376941681},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.182087242603302}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7758762240409851},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.7147696018218994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6358005404472351},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.615381121635437},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5814634561538696},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5357363224029541},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5340584516525269},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5108463168144226},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.49365314841270447},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.4690561592578888},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.4109896719455719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2626284956932068},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2362523376941681},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.182087242603302},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tie.2016.2542134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tie.2016.2542134","pdf_url":null,"source":{"id":"https://openalex.org/S58031724","display_name":"IEEE Transactions on Industrial Electronics","issn_l":"0278-0046","issn":["0278-0046","1557-9948"],"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 Industrial Electronics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4629068781","display_name":null,"funder_award_id":"61433004","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W173093232","https://openalex.org/W1513689897","https://openalex.org/W1602326725","https://openalex.org/W1614417283","https://openalex.org/W1968908471","https://openalex.org/W1969959431","https://openalex.org/W1971636608","https://openalex.org/W1977458621","https://openalex.org/W1983267717","https://openalex.org/W1983523797","https://openalex.org/W1987482599","https://openalex.org/W1997603681","https://openalex.org/W2002007892","https://openalex.org/W2005675298","https://openalex.org/W2010152647","https://openalex.org/W2012812921","https://openalex.org/W2019338681","https://openalex.org/W2020688906","https://openalex.org/W2033030672","https://openalex.org/W2035018355","https://openalex.org/W2035608030","https://openalex.org/W2039354440","https://openalex.org/W2045719273","https://openalex.org/W2048687352","https://openalex.org/W2049040026","https://openalex.org/W2052399669","https://openalex.org/W2060686658","https://openalex.org/W2067030256","https://openalex.org/W2068202815","https://openalex.org/W2085194340","https://openalex.org/W2086977346","https://openalex.org/W2097569048","https://openalex.org/W2098035803","https://openalex.org/W2107396783","https://openalex.org/W2108286682","https://openalex.org/W2108383324","https://openalex.org/W2111980775","https://openalex.org/W2116479681","https://openalex.org/W2120038868","https://openalex.org/W2131363581","https://openalex.org/W2136001135","https://openalex.org/W2137092694","https://openalex.org/W2141126179","https://openalex.org/W2146890818","https://openalex.org/W2147539438","https://openalex.org/W2165501837","https://openalex.org/W2165726932","https://openalex.org/W2312535066","https://openalex.org/W2963609304","https://openalex.org/W6682089242"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W2952594763","https://openalex.org/W4285537323","https://openalex.org/W1932159282","https://openalex.org/W2090698372","https://openalex.org/W4383890581","https://openalex.org/W2921905705","https://openalex.org/W4233178034","https://openalex.org/W2602009922"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,27,36,39,77,85,92,99,112,123,133,156,176,179],"optimal":[4,28,113],"consensus":[5,29,114],"control":[6,30,162],"problem":[7,115],"for":[8,31],"discrete-time":[9],"multi-agent":[10,32],"systems":[11,33,55],"with":[12],"completely":[13],"unknown":[14],"dynamics":[15],"by":[16],"utilizing":[17],"a":[18,68,106],"data-driven":[19],"reinforcement":[20],"learning":[21],"method.":[22,181],"It":[23],"is":[24,44,74],"known":[25],"that":[26],"relies":[34],"on":[35],"solution":[37],"of":[38,91,178],"coupled":[40],"Hamilton-Jacobi-Bellman":[41],"equation,":[42],"which":[43,96,127],"generally":[45],"impossible":[46],"to":[47,59,154,174],"be":[48],"solved":[49],"analytically.":[50],"Even":[51],"worse,":[52],"most":[53],"real-world":[54],"are":[56,152,172],"too":[57],"complicated":[58],"obtain":[60],"accurate":[61,86],"mathematical":[62],"models.":[63],"To":[64,131],"overcome":[65],"these":[66],"deficiencies,":[67],"data-based":[69],"adaptive":[70],"dynamic":[71,138],"programming":[72,139],"method":[73],"presented":[75],"using":[76],"current":[78],"and":[79,110,148,161],"past":[80],"system":[81,87],"data":[82],"rather":[83],"than":[84],"models":[88],"also":[89],"instead":[90],"traditional":[93],"identification":[94],"scheme":[95],"would":[97],"cause":[98],"approximation":[100],"residual":[101],"errors.":[102],"First,":[103],"we":[104,121],"establish":[105],"discounted":[107],"performance":[108,158],"index":[109,159],"formulate":[111],"via":[116],"Bellman":[117],"optimality":[118],"principle.":[119],"Then,":[120],"introduce":[122],"policy":[124],"iteration":[125],"algorithm":[126],"motivates":[128],"this":[129],"paper.":[130],"implement":[132],"proposed":[134,180],"online":[135],"action-dependent":[136],"heuristic":[137],"method,":[140],"two":[141,169],"neural":[142],"networks":[143],"(NNs),":[144],"1)":[145],"critic":[146],"NN":[147],"2)":[149],"actor":[150],"NN,":[151],"employed":[153],"approximate":[155],"iterative":[157],"functions":[160],"policies,":[163],"respectively,":[164],"in":[165],"real":[166],"time.":[167],"Finally,":[168],"simulation":[170],"examples":[171],"provided":[173],"demonstrate":[175],"effectiveness":[177]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":52},{"year":2024,"cited_by_count":52},{"year":2023,"cited_by_count":51},{"year":2022,"cited_by_count":48},{"year":2021,"cited_by_count":60},{"year":2020,"cited_by_count":40},{"year":2019,"cited_by_count":35},{"year":2018,"cited_by_count":35},{"year":2017,"cited_by_count":25}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}