{"id":"https://openalex.org/W3027376757","doi":"https://doi.org/10.1109/lcsys.2020.2995547","title":"Model-Free Reinforcement Learning of Minimal-Cost Variance Control","display_name":"Model-Free Reinforcement Learning of Minimal-Cost Variance Control","publication_year":2020,"publication_date":"2020-05-19","ids":{"openalex":"https://openalex.org/W3027376757","doi":"https://doi.org/10.1109/lcsys.2020.2995547","mag":"3027376757"},"language":"en","primary_location":{"id":"doi:10.1109/lcsys.2020.2995547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2020.2995547","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","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/A5073846906","display_name":"Gangshan Jing","orcid":"https://orcid.org/0000-0003-0066-204X"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gangshan Jing","raw_affiliation_strings":["Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040513070","display_name":"He Bai","orcid":"https://orcid.org/0000-0002-4247-0698"},"institutions":[{"id":"https://openalex.org/I115475287","display_name":"Oklahoma State University","ror":"https://ror.org/01g9vbr38","country_code":"US","type":"education","lineage":["https://openalex.org/I115475287"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He Bai","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054187846","display_name":"Jemin George","orcid":"https://orcid.org/0000-0001-8417-5411"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jemin George","raw_affiliation_strings":["Computational and Information Sciences Directorate (CISD), CCDC Army Research Laboratory, Adelphi, USA"],"affiliations":[{"raw_affiliation_string":"Computational and Information Sciences Directorate (CISD), CCDC Army Research Laboratory, Adelphi, USA","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055360778","display_name":"Aranya Chakrabortty","orcid":"https://orcid.org/0000-0002-3474-8215"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aranya Chakrabortty","raw_affiliation_strings":["Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073846906"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":1.2981,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84640337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"4","issue":"4","first_page":"916","last_page":"921"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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":1.0,"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":0.9902999997138977,"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":0.9605000019073486,"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/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.858051061630249},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7862725257873535},{"id":"https://openalex.org/keywords/algebraic-riccati-equation","display_name":"Algebraic Riccati equation","score":0.664114773273468},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.556931734085083},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5142828822135925},{"id":"https://openalex.org/keywords/riccati-equation","display_name":"Riccati equation","score":0.5127866864204407},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.48226338624954224},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.46379122138023376},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4430292248725891},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.42797306180000305},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3833989202976227},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3705138564109802},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.24486416578292847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15310335159301758}],"concepts":[{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.858051061630249},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7862725257873535},{"id":"https://openalex.org/C13847129","wikidata":"https://www.wikidata.org/wiki/Q4723989","display_name":"Algebraic Riccati equation","level":4,"score":0.664114773273468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.556931734085083},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5142828822135925},{"id":"https://openalex.org/C45473103","wikidata":"https://www.wikidata.org/wiki/Q851503","display_name":"Riccati equation","level":3,"score":0.5127866864204407},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.48226338624954224},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.46379122138023376},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4430292248725891},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.42797306180000305},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3833989202976227},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3705138564109802},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.24486416578292847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15310335159301758},{"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/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcsys.2020.2995547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2020.2995547","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1479830474","display_name":null,"funder_award_id":"CNS 1931932","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"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1983097489","https://openalex.org/W2017525961","https://openalex.org/W2024303516","https://openalex.org/W2037025184","https://openalex.org/W2096473846","https://openalex.org/W2103202975","https://openalex.org/W2121863487","https://openalex.org/W2133778318","https://openalex.org/W2148439597","https://openalex.org/W2331243380","https://openalex.org/W2501730499","https://openalex.org/W2585299106","https://openalex.org/W2590570612","https://openalex.org/W2735471763","https://openalex.org/W2799664482","https://openalex.org/W2884955570","https://openalex.org/W2908974431","https://openalex.org/W2913981879","https://openalex.org/W2918660012","https://openalex.org/W2919774326","https://openalex.org/W3045695591","https://openalex.org/W3145128584","https://openalex.org/W4214717370","https://openalex.org/W4246219036","https://openalex.org/W6679964708","https://openalex.org/W6734269517","https://openalex.org/W6781435397"],"related_works":["https://openalex.org/W2005019312","https://openalex.org/W2018296362","https://openalex.org/W2107449083","https://openalex.org/W2547959172","https://openalex.org/W2002357820","https://openalex.org/W1737855854","https://openalex.org/W197349956","https://openalex.org/W2997206142","https://openalex.org/W2804494800","https://openalex.org/W2027962246"],"abstract_inverted_index":{"This":[0],"letter":[1],"proposes":[2],"two":[3,70,160],"reinforcement":[4],"learning":[5,101],"(RL)":[6],"algorithms":[7,72],"for":[8,18,33,123,143],"solving":[9],"a":[10,34,47,59,109],"class":[11],"of":[12,46,92,99,108,146,158],"coupled":[13],"algebraic":[14],"Riccati":[15],"equations":[16],"(CARE)":[17],"linear":[19,64],"stochastic":[20,125],"dynamic":[21],"systems":[22],"with":[23],"unknown":[24],"state":[25],"and":[26,126],"input":[27,75],"matrices.":[28],"The":[29,113],"CARE":[30],"are":[31,152],"formulated":[32],"minimal-cost":[35],"variance":[36,45],"(MCV)":[37],"control":[38],"problem":[39],"that":[40],"aims":[41],"to":[42,118,139,154],"minimize":[43],"the":[44,74,81,96,100,130,134,156,159],"cost":[48],"function":[49],"while":[50],"keeping":[51],"its":[52],"mean":[53],"at":[54,80],"an":[55],"acceptable":[56],"range":[57],"using":[58],"noisy":[60],"infinite-horizon":[61],"full-state":[62],"feedback":[63],"quadratic":[65],"regulator":[66],"(LQR).":[67],"We":[68],"propose":[69],"RL":[71,122,148],"where":[73],"matrix":[76,106],"can":[77],"be":[78,119],"estimated":[79],"very":[82],"first":[83],"iteration.":[84],"This,":[85],"in":[86,95],"turn,":[87],"frees":[88],"up":[89],"significant":[90],"amount":[91],"computational":[93],"complexity":[94,115],"intermediate":[97],"steps":[98],"phase":[102],"by":[103],"avoiding":[104],"repeated":[105],"inversion":[107],"high-dimensional":[110],"data":[111],"matrix.":[112],"overall":[114],"is":[116,136],"shown":[117],"less":[120],"than":[121],"both":[124],"deterministic":[127],"LQR.":[128],"Additionally,":[129],"disturbance":[131],"noise":[132],"entering":[133],"model":[135],"not":[137],"required":[138],"satisfy":[140],"any":[141],"condition":[142],"ensuring":[144],"efficiency":[145],"either":[147],"algorithms.":[149],"Simulation":[150],"examples":[151],"presented":[153],"illustrate":[155],"effectiveness":[157],"designs.":[161]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4}],"updated_date":"2026-03-08T08:50:53.379069","created_date":"2025-10-10T00:00:00"}