{"id":"https://openalex.org/W4210910856","doi":"https://doi.org/10.1109/tsmc.2022.3145693","title":"Q-Learning for Continuous-Time Linear Systems: A Data-Driven Implementation of the Kleinman Algorithm","display_name":"Q-Learning for Continuous-Time Linear Systems: A Data-Driven Implementation of the Kleinman Algorithm","publication_year":2022,"publication_date":"2022-02-07","ids":{"openalex":"https://openalex.org/W4210910856","doi":"https://doi.org/10.1109/tsmc.2022.3145693"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2022.3145693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2022.3145693","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","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/A5072322964","display_name":"Corrado Possieri","orcid":"https://orcid.org/0000-0003-2528-3935"},"institutions":[{"id":"https://openalex.org/I4210162062","display_name":"Istituto di Analisi dei Sistemi ed Informatica Antonio Ruberti","ror":"https://ror.org/054ye0e45","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210155236","https://openalex.org/I4210162062"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Corrado Possieri","raw_affiliation_strings":["Istituto di Analisi dei Sistemi ed Informatica &#x201C;A. Ruberti,&#x201D; Consiglio Nazionale delle Ricerche, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0003-2528-3935","affiliations":[{"raw_affiliation_string":"Istituto di Analisi dei Sistemi ed Informatica &#x201C;A. Ruberti,&#x201D; Consiglio Nazionale delle Ricerche, Rome, Italy","institution_ids":["https://openalex.org/I4210162062"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018597173","display_name":"Mario Sassano","orcid":"https://orcid.org/0000-0003-4525-4656"},"institutions":[{"id":"https://openalex.org/I116067653","display_name":"University of Rome Tor Vergata","ror":"https://ror.org/02p77k626","country_code":"IT","type":"education","lineage":["https://openalex.org/I116067653"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mario Sassano","raw_affiliation_strings":["Dipartimento di Ingegneria Civile e Ingegneria Informatica, Universit&#x00E0; di Roma Tor Vergata, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4525-4656","affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria Civile e Ingegneria Informatica, Universit&#x00E0; di Roma Tor Vergata, Rome, Italy","institution_ids":["https://openalex.org/I116067653"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.651,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93781476,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"52","issue":"10","first_page":"6487","last_page":"6497"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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":0.9997000098228455,"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/T11236","display_name":"Control Systems and Identification","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/monotone-polygon","display_name":"Monotone polygon","score":0.6060996055603027},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5613989233970642},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5499944686889648},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5279349684715271},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.525066077709198},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4588956832885742},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45706525444984436},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4529423415660858},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4499899744987488},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42879486083984375},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42717432975769043},{"id":"https://openalex.org/keywords/algebraic-number","display_name":"Algebraic number","score":0.42035025358200073},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3446519374847412}],"concepts":[{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.6060996055603027},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5613989233970642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5499944686889648},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5279349684715271},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.525066077709198},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4588956832885742},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45706525444984436},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4529423415660858},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4499899744987488},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42879486083984375},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42717432975769043},{"id":"https://openalex.org/C9376300","wikidata":"https://www.wikidata.org/wiki/Q168817","display_name":"Algebraic number","level":2,"score":0.42035025358200073},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3446519374847412},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tsmc.2022.3145693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2022.3145693","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"},{"id":"pmh:oai:art.torvergata.it:2108/294506","is_oa":false,"landing_page_url":"https://hdl.handle.net/2108/294506","pdf_url":null,"source":{"id":"https://openalex.org/S4306400993","display_name":"Cineca Institutional Research Information System (Tor Vergata University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I116067653","host_organization_name":"University of Rome Tor Vergata","host_organization_lineage":["https://openalex.org/I116067653"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W177930832","https://openalex.org/W234738007","https://openalex.org/W1521930086","https://openalex.org/W1587799944","https://openalex.org/W1937324737","https://openalex.org/W1941445455","https://openalex.org/W1983523797","https://openalex.org/W1993174141","https://openalex.org/W1999072436","https://openalex.org/W2005545232","https://openalex.org/W2024303516","https://openalex.org/W2037025184","https://openalex.org/W2061328016","https://openalex.org/W2063358594","https://openalex.org/W2068949505","https://openalex.org/W2087063454","https://openalex.org/W2095590702","https://openalex.org/W2096512797","https://openalex.org/W2104843094","https://openalex.org/W2145830976","https://openalex.org/W2148439597","https://openalex.org/W2152161277","https://openalex.org/W2160561608","https://openalex.org/W2188644438","https://openalex.org/W2312229020","https://openalex.org/W2344560087","https://openalex.org/W2402675186","https://openalex.org/W2467518411","https://openalex.org/W2536620281","https://openalex.org/W2564717627","https://openalex.org/W2605628695","https://openalex.org/W2774852867","https://openalex.org/W2786459301","https://openalex.org/W2884633276","https://openalex.org/W2912426569","https://openalex.org/W2920417161","https://openalex.org/W2941503513","https://openalex.org/W2967813116","https://openalex.org/W3011120880","https://openalex.org/W3036186095","https://openalex.org/W3135791089","https://openalex.org/W3210839039","https://openalex.org/W4250772482","https://openalex.org/W4252055930","https://openalex.org/W4312258136","https://openalex.org/W4388319978","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W1859185863","https://openalex.org/W2964126589","https://openalex.org/W4285537323","https://openalex.org/W1932159282","https://openalex.org/W4307691181","https://openalex.org/W3016225735","https://openalex.org/W2017412075","https://openalex.org/W1518875602","https://openalex.org/W2116748936","https://openalex.org/W2767258356"],"abstract_inverted_index":{"A":[0],"data-driven":[1,122],"strategy":[2,117],"to":[3,109,143],"estimate":[4],"the":[5,9,29,32,39,44,48,53,72,77,85,88,107,110,115,125,131,136,144,153],"optimal":[6,17,33,145],"feedback":[7,63],"and":[8,55],"value":[10],"function":[11],"in":[12],"an":[13,21,60],"infinite-horizon,":[14],"continuous-time,":[15],"linear-quadratic":[16],"control":[18],"problem":[19],"for":[20,52],"unknown":[22],"system":[23],"is":[24,65,149],"proposed.":[25],"The":[26,147],"method":[27],"permits":[28],"construction":[30],"of":[31,38,47,80,97,124,135,155],"policy":[34,64],"without":[35,41,56],"any":[36],"knowledge":[37],"model,":[40],"requiring":[42],"that":[43,59],"time":[45],"derivatives":[46],"state":[49],"are":[50,70,103],"available":[51],"design,":[54],"even":[57],"assuming":[58],"initial":[61],"stabilizing":[62],"available.":[66],"Two":[67],"alternative":[68],"architectures":[69],"discussed:":[71],"first":[73],"scheme":[74],"revolves":[75],"around":[76],"periodic":[78],"computation":[79],"some":[81,98],"matrix":[82],"inversions":[83],"involving":[84],"Q-function,":[86],"whereas":[87],"second":[89],"approach":[90],"relies":[91],"on":[92],"a":[93,120],"purely":[94],"continuous-time":[95],"implementation":[96,123],"dynamic":[99],"systems":[100],"whose":[101],"trajectories":[102],"uniformly":[104],"attracted":[105],"by":[106,152],"solutions":[108],"above":[111],"algebraic":[112],"equations.":[113],"Interestingly,":[114],"proposed":[116],"essentially":[118],"constitutes":[119],"(direct)":[121],"celebrated":[126],"Kleinman":[127],"algorithm,":[128],"hence":[129],"subsuming":[130],"particularly":[132],"appealing":[133],"features":[134],"latter,":[137],"such":[138],"as":[139],"quadratic":[140],"monotone":[141],"convergence":[142],"solution.":[146],"theory":[148],"then":[150],"validated":[151],"means":[154],"practically":[156],"motivated":[157],"applications.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
