{"id":"https://openalex.org/W3116531410","doi":"https://doi.org/10.1109/tnnls.2020.3042508","title":"Model-Free Reinforcement Learning for Fully Cooperative Consensus Problem of Nonlinear Multiagent Systems","display_name":"Model-Free Reinforcement Learning for Fully Cooperative Consensus Problem of Nonlinear Multiagent Systems","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3116531410","doi":"https://doi.org/10.1109/tnnls.2020.3042508","mag":"3116531410","pmid":"https://pubmed.ncbi.nlm.nih.gov/33338022"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2020.3042508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3042508","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/A5101438534","display_name":"Hong Wang","orcid":"https://orcid.org/0000-0003-2724-8156"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hong Wang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404496","display_name":"Man Li","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Man Li","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101438534"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":3.9018,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.94824663,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"33","issue":"4","first_page":"1482","last_page":"1491"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hamilton\u2013jacobi\u2013bellman-equation","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","score":0.9084479212760925},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8584163188934326},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.7329033613204956},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6147820949554443},{"id":"https://openalex.org/keywords/jacobian-matrix-and-determinant","display_name":"Jacobian matrix and determinant","score":0.6069278120994568},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5707883834838867},{"id":"https://openalex.org/keywords/consensus","display_name":"Consensus","score":0.546660840511322},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5429049134254456},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.47969934344291687},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.451643705368042},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4270781874656677},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31586888432502747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22865921258926392},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.17978084087371826}],"concepts":[{"id":"https://openalex.org/C196978813","wikidata":"https://www.wikidata.org/wiki/Q3302775","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","level":3,"score":0.9084479212760925},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8584163188934326},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7329033613204956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6147820949554443},{"id":"https://openalex.org/C200331156","wikidata":"https://www.wikidata.org/wiki/Q506041","display_name":"Jacobian matrix and determinant","level":2,"score":0.6069278120994568},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5707883834838867},{"id":"https://openalex.org/C107107730","wikidata":"https://www.wikidata.org/wiki/Q2994424","display_name":"Consensus","level":3,"score":0.546660840511322},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5429049134254456},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.47969934344291687},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.451643705368042},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4270781874656677},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31586888432502747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22865921258926392},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.17978084087371826},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2020.3042508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3042508","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:33338022","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33338022","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":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W593135937","https://openalex.org/W1162378864","https://openalex.org/W1998361253","https://openalex.org/W1998922549","https://openalex.org/W1999678919","https://openalex.org/W2011694027","https://openalex.org/W2017819785","https://openalex.org/W2049500052","https://openalex.org/W2101382291","https://openalex.org/W2108383324","https://openalex.org/W2110852918","https://openalex.org/W2128928412","https://openalex.org/W2137642864","https://openalex.org/W2139416664","https://openalex.org/W2145143778","https://openalex.org/W2148011644","https://openalex.org/W2156629001","https://openalex.org/W2164141517","https://openalex.org/W2164634106","https://openalex.org/W2299109138","https://openalex.org/W2320262435","https://openalex.org/W2514447902","https://openalex.org/W2530077971","https://openalex.org/W2581606339","https://openalex.org/W2586495351","https://openalex.org/W2606378794","https://openalex.org/W2611945474","https://openalex.org/W2740962288","https://openalex.org/W2762911482","https://openalex.org/W2795872744","https://openalex.org/W2803623613","https://openalex.org/W2805542056","https://openalex.org/W2866066083","https://openalex.org/W2897822515","https://openalex.org/W2926422816","https://openalex.org/W2951650773","https://openalex.org/W3142915818","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W4320342078","https://openalex.org/W2766998270","https://openalex.org/W207287952","https://openalex.org/W4239477580","https://openalex.org/W1986314707","https://openalex.org/W3116531410","https://openalex.org/W1863485266","https://openalex.org/W3120223241","https://openalex.org/W2889834506","https://openalex.org/W2949081101"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"an":[3,130],"off-policy":[4,131],"model-free":[5,68,71,115,132],"algorithm":[6,163],"based":[7,91],"on":[8,92],"reinforcement":[9],"learning":[10],"(RL)":[11],"to":[12,53,56,76,118,141],"optimize":[13,142],"the":[14,27,36,58,78,83,93,96,114,120,124,143,148,167],"fully":[15],"cooperative":[16],"(FC)":[17],"consensus":[18,30,145],"problem":[19,31,146],"of":[20,147,160],"nonlinear":[21],"continuous-time":[22],"multiagent":[23],"systems":[24],"(MASs).":[25],"First,":[26],"optimal":[28,79,84],"FC":[29,144],"is":[32,50,74,104,164],"transformed":[33],"into":[34,113],"solving":[35],"coupled":[37,59],"Hamilton-Jacobian-Bellman":[38],"(HJB)":[39],"equation.":[40,61],"Then,":[41,90],"we":[42,128],"propose":[43,129],"a":[44,67,70],"policy":[45,86],"iteration":[46],"(PI)-based":[47],"algorithm,":[48,136],"which":[49,137],"further":[51],"proved":[52],"be":[54,139],"effective":[55],"solve":[57],"HJB":[60],"To":[62],"implement":[63],"this":[64,161],"scheme":[65],"in":[66,151],"way,":[69],"Bellman":[72,116],"equation":[73,117],"derived":[75,105],"find":[77],"value":[80,125],"function":[81],"and":[82,101,109,123],"control":[85],"for":[87,99],"each":[88],"agent.":[89],"least-squares":[94],"approach,":[95],"tuning":[97],"law":[98],"actor":[100,108],"critic":[102,110],"weights":[103],"by":[106,154,166],"employing":[107],"neural":[111],"networks":[112],"approximate":[119],"target":[121],"policies":[122],"function.":[126],"Finally,":[127],"integral":[133],"RL":[134],"(IRL)":[135],"can":[138],"used":[140],"whole":[149],"system":[150],"real":[152],"time":[153],"using":[155],"measured":[156],"data.":[157],"The":[158],"effectiveness":[159],"proposed":[162],"verified":[165],"simulation":[168],"results.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":4}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2025-10-10T00:00:00"}