{"id":"https://openalex.org/W2765454702","doi":"https://doi.org/10.1109/tcyb.2017.2761878","title":"Optimal Robust Output Containment of Unknown Heterogeneous Multiagent System Using Off-Policy Reinforcement Learning","display_name":"Optimal Robust Output Containment of Unknown Heterogeneous Multiagent System Using Off-Policy Reinforcement Learning","publication_year":2017,"publication_date":"2017-10-30","ids":{"openalex":"https://openalex.org/W2765454702","doi":"https://doi.org/10.1109/tcyb.2017.2761878","mag":"2765454702","pmid":"https://pubmed.ncbi.nlm.nih.gov/29989978"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2017.2761878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2017.2761878","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","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/A5076377822","display_name":"Shan Zuo","orcid":"https://orcid.org/0000-0001-9830-9310"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan Zuo","raw_affiliation_strings":["UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA"],"raw_orcid":"https://orcid.org/0000-0001-9830-9310","affiliations":[{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035337020","display_name":"Yongduan Song","orcid":"https://orcid.org/0000-0002-2167-1861"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongduan Song","raw_affiliation_strings":["School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2167-1861","affiliations":[{"raw_affiliation_string":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-4074-1615","affiliations":[{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053089078","display_name":"Ali Davoudi","orcid":"https://orcid.org/0000-0003-2951-442X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Davoudi","raw_affiliation_strings":["UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-2951-442X","affiliations":[{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.187,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.97126151,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"48","issue":"11","first_page":"3197","last_page":"3207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9975000023841858,"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":0.9613999724388123,"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":0.8702752590179443},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.7150908708572388},{"id":"https://openalex.org/keywords/containment","display_name":"Containment (computer programming)","score":0.6882155537605286},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6868844628334045},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5837382674217224},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.542796790599823},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5027356147766113},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.468711793422699},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4594190716743469},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.41970717906951904},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3798030912876129},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22251299023628235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16377615928649902}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8702752590179443},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7150908708572388},{"id":"https://openalex.org/C2777019822","wikidata":"https://www.wikidata.org/wiki/Q390066","display_name":"Containment (computer programming)","level":2,"score":0.6882155537605286},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6868844628334045},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5837382674217224},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.542796790599823},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5027356147766113},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.468711793422699},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4594190716743469},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41970717906951904},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3798030912876129},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22251299023628235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16377615928649902},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2017.2761878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2017.2761878","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:29989978","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29989978","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 cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G7019557205","display_name":null,"funder_award_id":"ECCS-1405173","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7604827104","display_name":null,"funder_award_id":"N00014-17-1-2239","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W296003671","https://openalex.org/W575429305","https://openalex.org/W1614417283","https://openalex.org/W1912694276","https://openalex.org/W1968908471","https://openalex.org/W1970760998","https://openalex.org/W1970786657","https://openalex.org/W1972243698","https://openalex.org/W1972809999","https://openalex.org/W1993811387","https://openalex.org/W2001874077","https://openalex.org/W2003456468","https://openalex.org/W2011671151","https://openalex.org/W2012451615","https://openalex.org/W2024303516","https://openalex.org/W2032704188","https://openalex.org/W2035250412","https://openalex.org/W2038739174","https://openalex.org/W2070685556","https://openalex.org/W2071004621","https://openalex.org/W2072302088","https://openalex.org/W2102885431","https://openalex.org/W2107396783","https://openalex.org/W2115206688","https://openalex.org/W2121863487","https://openalex.org/W2129536919","https://openalex.org/W2140391590","https://openalex.org/W2140751720","https://openalex.org/W2141410403","https://openalex.org/W2146890818","https://openalex.org/W2148439597","https://openalex.org/W2167675457","https://openalex.org/W2229645943","https://openalex.org/W2292254734","https://openalex.org/W2320262435","https://openalex.org/W2331370928","https://openalex.org/W2344118647","https://openalex.org/W2345038028","https://openalex.org/W2415645061","https://openalex.org/W2430619152","https://openalex.org/W2462102501","https://openalex.org/W2478654971","https://openalex.org/W2484646121","https://openalex.org/W2529203006","https://openalex.org/W2550394442","https://openalex.org/W2569238770","https://openalex.org/W2767784613","https://openalex.org/W2963784270","https://openalex.org/W4213367573","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698","https://openalex.org/W1859185863","https://openalex.org/W4307691181","https://openalex.org/W4285537323","https://openalex.org/W1932159282","https://openalex.org/W2964126589","https://openalex.org/W3016225735"],"abstract_inverted_index":{"This":[0,44],"paper":[1],"investigates":[2],"optimal":[3,77,84,142],"robust":[4,78,143],"output":[5,79,144],"containment":[6,80,145],"problem":[7,81,87,94,146],"of":[8,52,147,157,169],"general":[9],"linear":[10],"heterogeneous":[11,148],"multiagent":[12],"systems":[13],"(MAS)":[14],"with":[15,88],"completely":[16],"unknown":[17],"dynamics.":[18,160],"A":[19],"model-based":[20],"algorithm":[21,47,136],"using":[22,118,126],"offline":[23,45],"policy":[24,110],"iteration":[25],"(PI)":[26],"is":[27,36,72,102,137],"first":[28,103],"developed,":[29],"where":[30],"the":[31,40,49,76,113,120,141,158,167,170],"-copy":[32],"internal":[33],"model":[34,51],"principle":[35],"utilized":[37],"to":[38,74,105,139,165],"address":[39,65],"system":[41,159],"parameter":[42],"variations.":[43],"PI":[46],"requires":[48],"nominal":[50],"each":[53],"agent,":[54],"which":[55],"may":[56],"not":[57],"be":[58],"available":[59],"in":[60,96,150],"most":[61],"real-world":[62],"applications.":[63],"To":[64,91],"this":[66,93,127],"issue,":[67],"a":[68,99,107,130],"discounted":[69],"performance":[70],"function":[71],"introduced":[73],"express":[75],"as":[82],"an":[83],"output-feedback":[85],"design":[86],"bounded":[89],"-gain.":[90],"solve":[92,140],"online":[95],"real":[97,151],"time,":[98,152],"Bellman":[100,128],"equation":[101],"developed":[104],"evaluate":[106],"certain":[108],"control":[109,115],"and":[111],"find":[112],"updated":[114],"policies,":[116],"simultaneously,":[117],"only":[119],"state/output":[121],"information":[122],"measured":[123],"online.":[124],"Then,":[125],"equation,":[129],"model-free":[131],"off-policy":[132],"integral":[133],"reinforcement":[134],"learning":[135],"proposed":[138,171],"MAS,":[149],"without":[153],"requiring":[154],"any":[155],"knowledge":[156],"Simulation":[161],"results":[162],"are":[163],"provided":[164],"verify":[166],"effectiveness":[168],"method.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":10}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}