{"id":"https://openalex.org/W4377710635","doi":"https://doi.org/10.1109/tcsii.2023.3279309","title":"Learning Optimal Control Policy for Unknown Discrete-Time Systems","display_name":"Learning Optimal Control Policy for Unknown Discrete-Time Systems","publication_year":2023,"publication_date":"2023-05-23","ids":{"openalex":"https://openalex.org/W4377710635","doi":"https://doi.org/10.1109/tcsii.2023.3279309"},"language":"en","primary_location":{"id":"doi:10.1109/tcsii.2023.3279309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsii.2023.3279309","pdf_url":null,"source":{"id":"https://openalex.org/S93916849","display_name":"IEEE Transactions on Circuits & Systems II Express Briefs","issn_l":"1549-7747","issn":["1549-7747","1558-3791"],"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 Circuits and Systems II: Express Briefs","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/A5032771161","display_name":"Jing Lai","orcid":"https://orcid.org/0000-0002-9920-0066"},"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":"Jing Lai","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9920-0066","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/A5021953090","display_name":"Junlin Xiong","orcid":"https://orcid.org/0000-0002-0128-4960"},"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":"Junlin Xiong","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-0128-4960","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":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3726,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62479185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"70","issue":"11","first_page":"4191","last_page":"4195"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9879000186920166,"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":0.9819999933242798,"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/kronecker-product","display_name":"Kronecker product","score":0.6747959852218628},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.6332060098648071},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5737217664718628},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5731890201568604},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5398440361022949},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48779991269111633},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4803658425807953},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.40099674463272095},{"id":"https://openalex.org/keywords/kronecker-delta","display_name":"Kronecker delta","score":0.37586307525634766},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32567131519317627},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3004691004753113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16120943427085876}],"concepts":[{"id":"https://openalex.org/C46030957","wikidata":"https://www.wikidata.org/wiki/Q1238125","display_name":"Kronecker product","level":3,"score":0.6747959852218628},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.6332060098648071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5737217664718628},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5731890201568604},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5398440361022949},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48779991269111633},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4803658425807953},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.40099674463272095},{"id":"https://openalex.org/C39482219","wikidata":"https://www.wikidata.org/wiki/Q192826","display_name":"Kronecker delta","level":2,"score":0.37586307525634766},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32567131519317627},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3004691004753113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16120943427085876},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsii.2023.3279309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsii.2023.3279309","pdf_url":null,"source":{"id":"https://openalex.org/S93916849","display_name":"IEEE Transactions on Circuits & Systems II Express Briefs","issn_l":"1549-7747","issn":["1549-7747","1558-3791"],"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 Circuits and Systems II: Express Briefs","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8020654489","display_name":null,"funder_award_id":"62273320","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":22,"referenced_works":["https://openalex.org/W1680219837","https://openalex.org/W1983523797","https://openalex.org/W2013895638","https://openalex.org/W2022018324","https://openalex.org/W2188644438","https://openalex.org/W2484646121","https://openalex.org/W2772589676","https://openalex.org/W2790759697","https://openalex.org/W2903410452","https://openalex.org/W2927564896","https://openalex.org/W2974120149","https://openalex.org/W3046082844","https://openalex.org/W3119327948","https://openalex.org/W4210732025","https://openalex.org/W4214717370","https://openalex.org/W4223502737","https://openalex.org/W4226119189","https://openalex.org/W4280490104","https://openalex.org/W4281253024","https://openalex.org/W4283727098","https://openalex.org/W4308902993","https://openalex.org/W6810392763"],"related_works":["https://openalex.org/W123417539","https://openalex.org/W4233239985","https://openalex.org/W2079407403","https://openalex.org/W2060299328","https://openalex.org/W2117336295","https://openalex.org/W2073634779","https://openalex.org/W3102722572","https://openalex.org/W2090103374","https://openalex.org/W1564288589","https://openalex.org/W577870507"],"abstract_inverted_index":{"This":[0],"brief":[1],"studies":[2],"the":[3,21,25,30,33,41,49,54,61,69,81],"optimal":[4,50],"control":[5,37,66],"policy":[6,67],"learning":[7],"problem":[8],"for":[9],"discrete-time":[10],"linear":[11],"systems.":[12],"A":[13],"data-driven":[14],"model-free":[15,58],"algorithm":[16,43,59,83],"is":[17],"proposed":[18,42,82],"by":[19,40],"using":[20],"data":[22],"matrices":[23],"of":[24,32,71],"augmented":[26],"system":[27],"state":[28],"and":[29,68,84],"increasing":[31],"discount":[34],"factor.":[35],"The":[36],"gains":[38],"generated":[39],"are":[44,77],"proven":[45],"to":[46,48,79],"converge":[47],"one.":[51],"Compared":[52],"with":[53],"existing":[55],"work,":[56],"our":[57],"avoids":[60],"dependence":[62],"on":[63],"initial":[64],"stabilizing":[65],"use":[70],"Kronecker":[72],"product.":[73],"Some":[74],"numerical":[75],"examples":[76],"provided":[78],"illustrate":[80],"analysis":[85],"results.":[86]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
