{"id":"https://openalex.org/W4391020303","doi":"https://doi.org/10.1109/cdc49753.2023.10383803","title":"Adaptive Optimal Output Regulation of Discrete-Time Linear Systems: A Reinforcement Learning Approach","display_name":"Adaptive Optimal Output Regulation of Discrete-Time Linear Systems: A Reinforcement Learning Approach","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391020303","doi":"https://doi.org/10.1109/cdc49753.2023.10383803"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100600959","display_name":"Sayan Chakraborty","orcid":"https://orcid.org/0000-0003-4646-6415"},"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":"Sayan Chakraborty","raw_affiliation_strings":["New York University,CAN Lab,Brooklyn,NY,USA,11201"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,CAN Lab,Brooklyn,NY,USA,11201","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040120960","display_name":"Weinan Gao","orcid":"https://orcid.org/0000-0001-7921-018X"},"institutions":[{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]},{"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":"Weinan Gao","raw_affiliation_strings":["Northeastern University,State Key Laboratory of Synthetical Automation for Process Industries,Shenyang,China,110819"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,State Key Laboratory of Synthetical Automation for Process Industries,Shenyang,China,110819","institution_ids":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040301558","display_name":"Kyriakos G. Vamvoudakis","orcid":"https://orcid.org/0000-0003-1978-4848"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyriakos G. Vamvoudakis","raw_affiliation_strings":["The Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology,GA,USA,30332-0150"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology,GA,USA,30332-0150","institution_ids":["https://openalex.org/I130701444"]}]},{"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":["New York University,CAN Lab,Brooklyn,NY,USA,11201"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,CAN Lab,Brooklyn,NY,USA,11201","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7950","last_page":"7955"},"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":0.9843000173568726,"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":0.9366000294685364,"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":0.7272882461547852},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.6703014373779297},{"id":"https://openalex.org/keywords/uniqueness","display_name":"Uniqueness","score":0.6682593822479248},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6510862708091736},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6132501363754272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6005430221557617},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5114988088607788},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4994211196899414},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.4609355032444},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28797781467437744},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.22894814610481262},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20558932423591614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1522800326347351},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.1483880579471588}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7272882461547852},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.6703014373779297},{"id":"https://openalex.org/C2777021972","wikidata":"https://www.wikidata.org/wiki/Q22976830","display_name":"Uniqueness","level":2,"score":0.6682593822479248},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6510862708091736},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6132501363754272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6005430221557617},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5114988088607788},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4994211196899414},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.4609355032444},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28797781467437744},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.22894814610481262},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20558932423591614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1522800326347351},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.1483880579471588},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6492591857","display_name":null,"funder_award_id":"EPCN-2210320,CPS-2227185,S&AS-1849198,CPS-1851588,CPS-2227153","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W165924882","https://openalex.org/W1573503290","https://openalex.org/W1930027090","https://openalex.org/W1972809999","https://openalex.org/W1994075432","https://openalex.org/W2011866373","https://openalex.org/W2024303516","https://openalex.org/W2098432798","https://openalex.org/W2103422919","https://openalex.org/W2118589723","https://openalex.org/W2120225687","https://openalex.org/W2148439597","https://openalex.org/W2152161277","https://openalex.org/W2165726932","https://openalex.org/W2173085035","https://openalex.org/W2333120204","https://openalex.org/W2511897101","https://openalex.org/W2767307332","https://openalex.org/W2772589676","https://openalex.org/W2808312533","https://openalex.org/W2889961793","https://openalex.org/W2912832158","https://openalex.org/W2987667606","https://openalex.org/W3103939126","https://openalex.org/W3114263192","https://openalex.org/W3121634745","https://openalex.org/W3187048847","https://openalex.org/W4213251304","https://openalex.org/W4213367573","https://openalex.org/W4214717370","https://openalex.org/W4237591687","https://openalex.org/W4244299687","https://openalex.org/W4283385486","https://openalex.org/W4308081001"],"related_works":["https://openalex.org/W571281153","https://openalex.org/W2949403936","https://openalex.org/W4301247218","https://openalex.org/W3023806604","https://openalex.org/W2952139525","https://openalex.org/W2129818458","https://openalex.org/W4289551052","https://openalex.org/W2602009922","https://openalex.org/W2166339378","https://openalex.org/W3104183741"],"abstract_inverted_index":{"In":[0],"this":[1,76],"paper,":[2],"we":[3],"solve":[4],"the":[5,17,46,55,61,92,99],"optimal":[6],"output":[7,51],"regulation":[8,52],"problem":[9],"for":[10,49,66],"discrete-time":[11,50],"systems":[12],"without":[13],"precise":[14],"knowledge":[15],"of":[16,60,91,98],"system":[18],"model.":[19],"Drawing":[20],"inspiration":[21],"from":[22,54],"reinforcement":[23],"learning":[24],"and":[25,38,72,89],"adaptive":[26],"dynamic":[27],"programming,":[28],"a":[29,78,109],"data-driven":[30,93],"solution":[31],"is":[32,43,83,102],"developed":[33],"that":[34,45],"enables":[35],"asymptotic":[36],"tracking":[37],"disturbance":[39],"rejection.":[40],"Notably,":[41],"it":[42],"discovered":[44],"proposed":[47,100],"approach":[48,57],"differs":[53],"continuous-time":[56],"in":[58],"terms":[59],"persistent":[62,80],"excitation":[63,81],"condition":[64,82],"required":[65],"policy":[67,94],"iteration":[68],"to":[69,85],"be":[70],"unique":[71],"convergent.":[73],"To":[74],"address":[75],"issue,":[77],"new":[79],"introduced":[84],"ensure":[86],"both":[87],"uniqueness":[88],"convergence":[90],"iteration.":[95],"The":[96],"efficacy":[97],"methodology":[101],"validated":[103],"by":[104],"an":[105],"inverted":[106],"pendulum":[107],"on":[108],"cart":[110],"example.":[111]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}