{"id":"https://openalex.org/W3184481401","doi":"https://doi.org/10.1109/tac.2022.3172250","title":"Reinforcement Learning for Adaptive Optimal Stationary Control of Linear Stochastic Systems","display_name":"Reinforcement Learning for Adaptive Optimal Stationary Control of Linear Stochastic Systems","publication_year":2022,"publication_date":"2022-05-03","ids":{"openalex":"https://openalex.org/W3184481401","doi":"https://doi.org/10.1109/tac.2022.3172250","mag":"3184481401"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2022.3172250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2022.3172250","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","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/A5058655480","display_name":"Bo Pang","orcid":"https://orcid.org/0000-0002-4359-2937"},"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":"Bo Pang","raw_affiliation_strings":["Control and Networks Lab, Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-4359-2937","affiliations":[{"raw_affiliation_string":"Control and Networks Lab, Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"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":["Control and Networks Lab, Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-4868-9359","affiliations":[{"raw_affiliation_string":"Control and Networks Lab, 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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":5.8475,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.9685905,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"68","issue":"4","first_page":"2383","last_page":"2390"},"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":0.9763000011444092,"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.963100016117096,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8436611890792847},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.674156665802002},{"id":"https://openalex.org/keywords/multiplicative-function","display_name":"Multiplicative function","score":0.6093875169754028},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.6070429682731628},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.5852541923522949},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5676642060279846},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.5336775183677673},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5030025839805603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4724942743778229},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4705776572227478},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4525827169418335},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.41323548555374146},{"id":"https://openalex.org/keywords/multiplicative-noise","display_name":"Multiplicative noise","score":0.4130653142929077},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3742496371269226},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.22095400094985962},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19143527746200562},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.18588033318519592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1313537359237671}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8436611890792847},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.674156665802002},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.6093875169754028},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.6070429682731628},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.5852541923522949},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5676642060279846},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.5336775183677673},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5030025839805603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4724942743778229},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4705776572227478},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4525827169418335},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41323548555374146},{"id":"https://openalex.org/C18015164","wikidata":"https://www.wikidata.org/wiki/Q6935000","display_name":"Multiplicative noise","level":5,"score":0.4130653142929077},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3742496371269226},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.22095400094985962},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19143527746200562},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.18588033318519592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1313537359237671},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C131021393","wikidata":"https://www.wikidata.org/wiki/Q7512759","display_name":"Signal transfer function","level":4,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","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/C13412647","wikidata":"https://www.wikidata.org/wiki/Q174948","display_name":"Analog signal","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2022.3172250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2022.3172250","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G6186092892","display_name":null,"funder_award_id":"EPCN-1903781","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G643496096","display_name":null,"funder_award_id":"ECCS-1501044","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W638400246","https://openalex.org/W1521738998","https://openalex.org/W1588340316","https://openalex.org/W1797739565","https://openalex.org/W1805871248","https://openalex.org/W1989220595","https://openalex.org/W1990005421","https://openalex.org/W2004585062","https://openalex.org/W2005902667","https://openalex.org/W2009803489","https://openalex.org/W2030918015","https://openalex.org/W2033951124","https://openalex.org/W2052334067","https://openalex.org/W2092024265","https://openalex.org/W2102316513","https://openalex.org/W2117741492","https://openalex.org/W2120225687","https://openalex.org/W2121832485","https://openalex.org/W2121863487","https://openalex.org/W2124477018","https://openalex.org/W2124783336","https://openalex.org/W2137566549","https://openalex.org/W2137850460","https://openalex.org/W2148439597","https://openalex.org/W2153461933","https://openalex.org/W2168407832","https://openalex.org/W2315214986","https://openalex.org/W2323824333","https://openalex.org/W2331243380","https://openalex.org/W2543834468","https://openalex.org/W2586680856","https://openalex.org/W2590144118","https://openalex.org/W2600386361","https://openalex.org/W2610857016","https://openalex.org/W2623785075","https://openalex.org/W2772589676","https://openalex.org/W2797638056","https://openalex.org/W2800330509","https://openalex.org/W2896663787","https://openalex.org/W2897661175","https://openalex.org/W2955341654","https://openalex.org/W2957695304","https://openalex.org/W2961703895","https://openalex.org/W2967651253","https://openalex.org/W2973215397","https://openalex.org/W2993197237","https://openalex.org/W2995552585","https://openalex.org/W2999204942","https://openalex.org/W3022566517","https://openalex.org/W3103545257","https://openalex.org/W3111531580","https://openalex.org/W3161401909","https://openalex.org/W3172934943","https://openalex.org/W3175769301","https://openalex.org/W3184481401","https://openalex.org/W3194881203","https://openalex.org/W4214717370","https://openalex.org/W4229706427","https://openalex.org/W4238209390","https://openalex.org/W4255718432","https://openalex.org/W4285719527","https://openalex.org/W4301886962","https://openalex.org/W6678518843","https://openalex.org/W6776438516","https://openalex.org/W6785331629"],"related_works":["https://openalex.org/W2329857478","https://openalex.org/W4308505035","https://openalex.org/W3181585847","https://openalex.org/W3110455746","https://openalex.org/W4320534395","https://openalex.org/W4220833355","https://openalex.org/W3195689441","https://openalex.org/W3065084342","https://openalex.org/W4303411701","https://openalex.org/W3184481401"],"abstract_inverted_index":{"This":[0],"article":[1],"studies":[2],"the":[3,49,76,91,103],"adaptive":[4,50],"optimal":[5,51,92],"stationary":[6,52],"control":[7,53,70],"of":[8,48,90,102],"continuous-time":[9],"linear":[10],"stochastic":[11],"systems":[12],"with":[13,94],"both":[14],"additive":[15],"and":[16,115],"multiplicative":[17],"noises,":[18],"using":[19],"reinforcement":[20,30],"learning":[21,31],"techniques.":[22],"Based":[23],"on":[24],"policy":[25,36,80],"iteration,":[26,37],"a":[27,87,107],"novel":[28],"off-policy":[29],"algorithm,":[32],"named":[33],"optimistic":[34,78],"least-squares-based":[35,79],"is":[38,41],"proposed,":[39],"which":[40],"able":[42],"to":[43,84,86,106],"find":[44],"iteratively":[45],"near-optimal":[46],"policies":[47],"problem":[54],"directly":[55],"from":[56,66],"input/state":[57],"data":[58],"without":[59],"explicitly":[60],"identifying":[61],"any":[62],"system":[63],"matrices,":[64],"starting":[65],"an":[67],"initial":[68],"admissible":[69],"policy.":[71],"The":[72,100],"solutions":[73],"given":[74],"by":[75],"proposed":[77,104],"iteration":[81],"are":[82],"proved":[83],"converge":[85],"small":[88],"neighborhood":[89],"solution":[93],"probability":[95],"one,":[96],"under":[97],"mild":[98],"conditions.":[99],"application":[101],"algorithm":[105],"triple":[108],"inverted":[109],"pendulum":[110],"example":[111],"validates":[112],"its":[113],"feasibility":[114],"effectiveness.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}