{"id":"https://openalex.org/W2912832158","doi":"https://doi.org/10.1109/tcyb.2018.2890046","title":"Optimal Output Regulation of Linear Discrete-Time Systems With Unknown Dynamics Using Reinforcement Learning","display_name":"Optimal Output Regulation of Linear Discrete-Time Systems With Unknown Dynamics Using Reinforcement Learning","publication_year":2019,"publication_date":"2019-01-25","ids":{"openalex":"https://openalex.org/W2912832158","doi":"https://doi.org/10.1109/tcyb.2018.2890046","mag":"2912832158","pmid":"https://pubmed.ncbi.nlm.nih.gov/30703054"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2018.2890046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2018.2890046","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/A5100396295","display_name":"Yi Jiang","orcid":"https://orcid.org/0000-0001-8927-0119"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"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":["CA","CN"],"is_corresponding":true,"raw_author_name":"Yi Jiang","raw_affiliation_strings":["International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","University of Alberta, Edmonton, Canada"],"affiliations":[{"raw_affiliation_string":"International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089224471","display_name":"Bahare Kiumarsi","orcid":"https://orcid.org/0000-0002-9701-8375"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bahare Kiumarsi","raw_affiliation_strings":["Michigan State University, East Lansing, USA"],"affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033960992","display_name":"Jialu Fan","orcid":"https://orcid.org/0000-0001-7585-1166"},"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":"Jialu Fan","raw_affiliation_strings":["International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042520521","display_name":"Tianyou Chai","orcid":"https://orcid.org/0000-0002-4623-1483"},"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":"Tianyou Chai","raw_affiliation_strings":["International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070599005","display_name":"Jinna Li","orcid":"https://orcid.org/0000-0001-9985-6308"},"institutions":[{"id":"https://openalex.org/I166846921","display_name":"Liaoning Shihua University","ror":"https://ror.org/00k6c4h29","country_code":"CN","type":"education","lineage":["https://openalex.org/I166846921"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinna Li","raw_affiliation_strings":["School of Information and Control Engineering, Liaoning Shihua University, Fushun, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Liaoning Shihua University, Fushun, China","institution_ids":["https://openalex.org/I166846921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","UTA Research Institute, University of Texas at Arlington, Arlington, USA"],"affiliations":[{"raw_affiliation_string":"International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Arlington, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100396295"],"corresponding_institution_ids":["https://openalex.org/I154425047","https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":11.578,"has_fulltext":false,"cited_by_count":130,"citation_normalized_percentile":{"value":0.98847369,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"50","issue":"7","first_page":"3147","last_page":"3156"},"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9771000146865845,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7202829718589783},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.6962135434150696},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6021047830581665},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5889230370521545},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5458259582519531},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5403059124946594},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.5193256139755249},{"id":"https://openalex.org/keywords/discrete-optimization","display_name":"Discrete optimization","score":0.5161953568458557},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.50356525182724},{"id":"https://openalex.org/keywords/system-dynamics","display_name":"System dynamics","score":0.4433184564113617},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4279310405254364},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32551029324531555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08077377080917358}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7202829718589783},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.6962135434150696},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6021047830581665},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5889230370521545},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5458259582519531},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5403059124946594},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.5193256139755249},{"id":"https://openalex.org/C145671259","wikidata":"https://www.wikidata.org/wiki/Q1493786","display_name":"Discrete optimization","level":3,"score":0.5161953568458557},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.50356525182724},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.4433184564113617},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4279310405254364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32551029324531555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08077377080917358},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2018.2890046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2018.2890046","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:30703054","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30703054","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":[],"awards":[{"id":"https://openalex.org/G1460833335","display_name":null,"funder_award_id":"61533015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3951694549","display_name":null,"funder_award_id":"N160804001","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5409562055","display_name":null,"funder_award_id":"B08015","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"},{"id":"https://openalex.org/G74425646","display_name":null,"funder_award_id":"61673280","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7583496911","display_name":null,"funder_award_id":"61333012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G772161998","display_name":null,"funder_award_id":"61304028","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"},{"id":"https://openalex.org/F4320322429","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null},{"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":41,"referenced_works":["https://openalex.org/W92805021","https://openalex.org/W296003671","https://openalex.org/W1605411138","https://openalex.org/W1614417283","https://openalex.org/W1907796993","https://openalex.org/W1912694276","https://openalex.org/W1969959431","https://openalex.org/W1976956127","https://openalex.org/W1991119064","https://openalex.org/W2005437559","https://openalex.org/W2012451615","https://openalex.org/W2013895638","https://openalex.org/W2016833569","https://openalex.org/W2072454019","https://openalex.org/W2093831009","https://openalex.org/W2103422919","https://openalex.org/W2118589723","https://openalex.org/W2139416664","https://openalex.org/W2148439597","https://openalex.org/W2149087996","https://openalex.org/W2162991547","https://openalex.org/W2321029100","https://openalex.org/W2333120204","https://openalex.org/W2484646121","https://openalex.org/W2498677259","https://openalex.org/W2580629550","https://openalex.org/W2606378794","https://openalex.org/W2762709466","https://openalex.org/W2767307332","https://openalex.org/W2771641782","https://openalex.org/W2775523681","https://openalex.org/W2790958326","https://openalex.org/W2884730950","https://openalex.org/W2887344203","https://openalex.org/W2891732111","https://openalex.org/W2911032305","https://openalex.org/W3213472335","https://openalex.org/W4213367573","https://openalex.org/W4285719527","https://openalex.org/W6603762378","https://openalex.org/W6804409665"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W2066714521","https://openalex.org/W4285080375","https://openalex.org/W2543590894","https://openalex.org/W2598260969"],"abstract_inverted_index":{"This":[0,22],"paper":[1],"presents":[2],"a":[3,33,56,84,113],"model-free":[4,85,114],"optimal":[5,65],"approach":[6,115],"based":[7,104],"on":[8,105],"reinforcement":[9],"learning":[10],"for":[11,17,118,141],"solving":[12],"the":[13,42,45,50,64,74,77,92,95,106,109,119,127,133,138,143,154,157],"output":[14,46],"regulation":[15],"problem":[16,23,37,59,98],"discrete-time":[18],"systems":[19],"under":[20],"disturbances.":[21],"is":[24,38,60,88,116,124,130],"first":[25],"broken":[26],"down":[27],"into":[28],"two":[29],"optimization":[30,36,58,71,97,111,121],"problems:":[31],"1)":[32],"constrained":[34],"static":[35,120],"established":[39,61],"to":[40,44,62,90,94,108,132,137,152],"find":[41,63,91],"solution":[43,93,107],"regulator":[47],"equations":[48],"(i.e.,":[49],"feedforward":[51],"control":[52,67,139],"input)":[53],"and":[54],"2)":[55],"dynamic":[57,96,110],"feedback":[66],"input.":[68],"Solving":[69],"these":[70],"problems":[72],"requires":[73],"knowledge":[75],"of":[76,145,156],"system":[78],"dynamics.":[79],"To":[80],"obviate":[81],"this":[82],"requirement,":[83],"off-policy":[86],"algorithm":[87,129],"presented":[89],"using":[99],"only":[100],"measured":[101],"data.":[102],"Then,":[103],"problem,":[112],"provided":[117,151],"problem.":[122],"It":[123],"shown":[125],"that":[126],"proposed":[128,158],"insensitive":[131],"probing":[134],"noise":[135],"added":[136],"input":[140],"satisfying":[142],"persistence":[144],"excitation":[146],"condition.":[147],"Simulation":[148],"results":[149],"are":[150],"verify":[153],"effectiveness":[155],"approach.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":4}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}