{"id":"https://openalex.org/W3155402581","doi":"https://doi.org/10.1109/tnnls.2021.3069728","title":"Reinforcement Learning-Based Cooperative Optimal Output Regulation via Distributed Adaptive Internal Model","display_name":"Reinforcement Learning-Based Cooperative Optimal Output Regulation via Distributed Adaptive Internal Model","publication_year":2021,"publication_date":"2021-04-14","ids":{"openalex":"https://openalex.org/W3155402581","doi":"https://doi.org/10.1109/tnnls.2021.3069728","mag":"3155402581","pmid":"https://pubmed.ncbi.nlm.nih.gov/33852393"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3069728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3069728","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/A5040120960","display_name":"Weinan Gao","orcid":"https://orcid.org/0000-0001-7921-018X"},"institutions":[{"id":"https://openalex.org/I106959904","display_name":"Florida Institute of Technology","ror":"https://ror.org/04atsbb87","country_code":"US","type":"education","lineage":["https://openalex.org/I106959904"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weinan Gao","raw_affiliation_strings":["Department of Mechanical and Civil Engineering, College of Engineering and Science, Florida Institute of Technology, Melbourne, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Civil Engineering, College of Engineering and Science, Florida Institute of Technology, Melbourne, FL, USA","institution_ids":["https://openalex.org/I106959904"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088956116","display_name":"Mohammed Mynuddin","orcid":"https://orcid.org/0000-0001-7898-5485"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed Mynuddin","raw_affiliation_strings":["Department of Civil, Environmental and Construction Engineering (Major in Transportation Engineering), University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Civil, Environmental and Construction Engineering (Major in Transportation Engineering), University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038037619","display_name":"Donald C. Wunsch","orcid":"https://orcid.org/0000-0002-9726-9051"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donald C. Wunsch","raw_affiliation_strings":["Department of Computer Engineering, Missouri University of Science and Technology (Missouri S&T), Rolla, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Missouri University of Science and Technology (Missouri S&T), Rolla, MO, USA","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067046312","display_name":"Zhong\u2010Ping Jiang","orcid":"https://orcid.org/0000-0002-4868-9359"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Ping Jiang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040120960"],"corresponding_institution_ids":["https://openalex.org/I106959904"],"apc_list":null,"apc_paid":null,"fwci":12.4202,"has_fulltext":false,"cited_by_count":125,"citation_normalized_percentile":{"value":0.9893506,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"33","issue":"10","first_page":"5229","last_page":"5240"},"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":0.991100013256073,"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/T12277","display_name":"Frequency Control in Power Systems","score":0.9368000030517578,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.810248613357544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7177813649177551},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.5321953296661377},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5277830958366394},{"id":"https://openalex.org/keywords/internal-model","display_name":"Internal model","score":0.522482693195343},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5116925239562988},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.4569772183895111},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4499618709087372},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42332789301872253},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4203249216079712},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4134940505027771},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3924137055873871},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33800140023231506},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3074697256088257},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2770993709564209},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12541863322257996},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09410929679870605}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.810248613357544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7177813649177551},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.5321953296661377},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5277830958366394},{"id":"https://openalex.org/C28427503","wikidata":"https://www.wikidata.org/wiki/Q13580300","display_name":"Internal model","level":3,"score":0.522482693195343},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5116925239562988},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.4569772183895111},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4499618709087372},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42332789301872253},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4203249216079712},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4134940505027771},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3924137055873871},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33800140023231506},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3074697256088257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2770993709564209},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12541863322257996},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09410929679870605},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3069728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3069728","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:33852393","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33852393","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":[],"awards":[{"id":"https://openalex.org/G2219731665","display_name":null,"funder_award_id":"69A3551747124","funder_id":"https://openalex.org/F4320306108","funder_display_name":"U.S. Department of Transportation"},{"id":"https://openalex.org/G3185130980","display_name":null,"funder_award_id":"19\u201312","funder_id":"https://openalex.org/F4320309979","funder_display_name":"Georgia Department of Transportation"},{"id":"https://openalex.org/G7241937758","display_name":null,"funder_award_id":"EPCN-1903781","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306108","display_name":"U.S. Department of Transportation","ror":"https://ror.org/02xfw2e90"},{"id":"https://openalex.org/F4320309979","display_name":"Georgia Department of Transportation","ror":"https://ror.org/00ktzqz45"},{"id":"https://openalex.org/F4320312855","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W114979488","https://openalex.org/W1531362183","https://openalex.org/W1991360560","https://openalex.org/W1994829382","https://openalex.org/W1999416503","https://openalex.org/W2014706340","https://openalex.org/W2028922668","https://openalex.org/W2037025184","https://openalex.org/W2093831009","https://openalex.org/W2097243307","https://openalex.org/W2115856428","https://openalex.org/W2124234993","https://openalex.org/W2125950605","https://openalex.org/W2139780556","https://openalex.org/W2148439597","https://openalex.org/W2152161277","https://openalex.org/W2160932744","https://openalex.org/W2228328747","https://openalex.org/W2280043427","https://openalex.org/W2320262435","https://openalex.org/W2333120204","https://openalex.org/W2339167885","https://openalex.org/W2430619152","https://openalex.org/W2467518411","https://openalex.org/W2481799503","https://openalex.org/W2497568066","https://openalex.org/W2498677259","https://openalex.org/W2552003518","https://openalex.org/W2609750639","https://openalex.org/W2734351487","https://openalex.org/W2742883526","https://openalex.org/W2767307332","https://openalex.org/W2767758861","https://openalex.org/W2767784613","https://openalex.org/W2789789879","https://openalex.org/W2790958326","https://openalex.org/W2793914020","https://openalex.org/W2803623613","https://openalex.org/W2896799653","https://openalex.org/W2912778211","https://openalex.org/W2913173906","https://openalex.org/W2921889099","https://openalex.org/W2927564896","https://openalex.org/W2954033048","https://openalex.org/W2983464671","https://openalex.org/W2995552585","https://openalex.org/W3003040443","https://openalex.org/W4213367573","https://openalex.org/W4214717370","https://openalex.org/W4249919931","https://openalex.org/W4301886962"],"related_works":["https://openalex.org/W1932159282","https://openalex.org/W4285537323","https://openalex.org/W2379312070","https://openalex.org/W2136173754","https://openalex.org/W2110050003","https://openalex.org/W2953025626","https://openalex.org/W2499081552","https://openalex.org/W2366053282","https://openalex.org/W1653644965","https://openalex.org/W2128788708"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"a":[3,30,40,45,98],"data-driven":[4],"distributed":[5,31,41,46],"control":[6,103],"method":[7],"is":[8,35],"proposed":[9,63],"to":[10,48,73],"solve":[11],"the":[12,50,56,75,88,115],"cooperative":[13,27],"optimal":[14,76],"output":[15,28],"regulation":[16],"problem":[17],"of":[18,58,87],"leader-follower":[19],"multiagent":[20,59],"systems.":[21],"Different":[22],"from":[23,118],"traditional":[24],"studies":[25],"on":[26,55],"regulation,":[29],"adaptive":[32,106],"internal":[33,42],"model":[34,43],"originally":[36],"developed,":[37],"which":[38,119],"includes":[39],"and":[44,70,81,84],"observer":[47],"estimate":[49],"leader's":[51,89],"dynamics.":[52],"Without":[53],"relying":[54],"dynamics":[57],"systems,":[60],"we":[61,95],"have":[62,96],"two":[64],"reinforcement":[65],"learning":[66],"algorithms,":[67],"policy":[68],"iteration":[69],"value":[71],"iteration,":[72],"learn":[74],"controller":[77],"through":[78],"online":[79],"input":[80],"state":[82],"data,":[83],"estimated":[85],"values":[86],"state.":[90],"By":[91],"combining":[92],"these":[93,113],"methods,":[94],"established":[97],"basis":[99],"for":[100],"connecting":[101],"data-distributed":[102],"methods":[104],"with":[105],"dynamic":[107],"programming":[108],"approaches":[109],"in":[110],"general":[111],"since":[112],"are":[114,121],"theoretical":[116],"foundation":[117],"they":[120],"built.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":38},{"year":2024,"cited_by_count":37},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}