{"id":"https://openalex.org/W3203485495","doi":"https://doi.org/10.1137/20m1382386","title":"Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon","display_name":"Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3203485495","doi":"https://doi.org/10.1137/20m1382386","mag":"3203485495"},"language":"en","primary_location":{"id":"doi:10.1137/20m1382386","is_oa":false,"landing_page_url":"https://doi.org/10.1137/20m1382386","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","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/A5065589370","display_name":"Ben Hambly","orcid":"https://orcid.org/0000-0003-0086-0695"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ben Hambly","raw_affiliation_strings":["\\dagger Mathematical Institute, University of Oxford, Oxford, OX2 6GG, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\\dagger Mathematical Institute, University of Oxford, Oxford, OX2 6GG, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068576165","display_name":"Renyuan Xu","orcid":"https://orcid.org/0000-0003-4293-3450"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Renyuan Xu","raw_affiliation_strings":["\\dagger Mathematical Institute, University of Oxford, Oxford, OX2 6GG, UK"],"raw_orcid":"https://orcid.org/0000-0003-4293-3450","affiliations":[{"raw_affiliation_string":"\\dagger Mathematical Institute, University of Oxford, Oxford, OX2 6GG, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048366794","display_name":"Huining Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Huining Yang","raw_affiliation_strings":["\\dagger Mathematical Institute, University of Oxford, Oxford, OX2 6GG, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\\dagger Mathematical Institute, University of Oxford, Oxford, OX2 6GG, UK","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048366794"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":5.1479,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.95947922,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"59","issue":"5","first_page":"3359","last_page":"3391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9950000047683716,"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":0.9950000047683716,"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":0.9918000102043152,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9801999926567078,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/regulator","display_name":"Regulator","score":0.6723854541778564},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.6631131172180176},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6392959356307983},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5829330086708069},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4877522587776184},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.48732098937034607},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4770335853099823},{"id":"https://openalex.org/keywords/linear-quadratic-gaussian-control","display_name":"Linear-quadratic-Gaussian control","score":0.45589378476142883},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.45292770862579346},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4247724413871765},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.4202638268470764},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3802562952041626},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3782668709754944},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.3749905228614807},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2610946297645569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17929157614707947},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.08605480194091797}],"concepts":[{"id":"https://openalex.org/C6929976","wikidata":"https://www.wikidata.org/wiki/Q3771881","display_name":"Regulator","level":3,"score":0.6723854541778564},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.6631131172180176},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6392959356307983},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5829330086708069},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4877522587776184},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.48732098937034607},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4770335853099823},{"id":"https://openalex.org/C204495892","wikidata":"https://www.wikidata.org/wiki/Q1798304","display_name":"Linear-quadratic-Gaussian control","level":3,"score":0.45589378476142883},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.45292770862579346},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4247724413871765},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.4202638268470764},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3802562952041626},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3782668709754944},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3749905228614807},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2610946297645569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17929157614707947},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.08605480194091797},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/20m1382386","is_oa":false,"landing_page_url":"https://doi.org/10.1137/20m1382386","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G667190850","display_name":"EPSRC Centre for Doctoral Training in Industrially Focused Mathematical Modelling","funder_award_id":"EP/L015803/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320296","display_name":"BP Global","ror":"https://ror.org/01zctcs90"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1903051497","https://openalex.org/W1988270113","https://openalex.org/W2040582618","https://openalex.org/W2075145522","https://openalex.org/W2082210980","https://openalex.org/W2166163936","https://openalex.org/W2604272474","https://openalex.org/W2822752092","https://openalex.org/W2966348706","https://openalex.org/W3012223895","https://openalex.org/W3033318690","https://openalex.org/W3089959184","https://openalex.org/W3104501706","https://openalex.org/W3121394145","https://openalex.org/W3122475569","https://openalex.org/W4212774754"],"related_works":["https://openalex.org/W3777868","https://openalex.org/W1990910969","https://openalex.org/W2051766198","https://openalex.org/W2915806395","https://openalex.org/W234468389","https://openalex.org/W2007152535","https://openalex.org/W3041379944","https://openalex.org/W2067197839","https://openalex.org/W2364244763","https://openalex.org/W2097411338"],"abstract_inverted_index":{"Related":[0],"DatabasesWeb":[1],"of":[2],"Science":[3],"You":[4],"must":[5],"be":[6],"logged":[7],"in":[8],"with":[9],"an":[10],"active":[11],"subscription":[12],"to":[13],"view":[14],"this.Article":[15],"DataHistorySubmitted:":[16],"24":[17],"November":[18],"2020Accepted:":[19],"15":[20],"June":[21],"2021Published":[22],"online:":[23],"28":[24],"September":[25],"2021Keywordslinear":[26],"quadratic":[27],"regulator,":[28],"reinforcement":[29],"learning,":[30],"policy":[31],"gradient":[32],"method,":[33],"stochastic":[34],"control,":[35],"optimal":[36,38],"liquidation,":[37],"executionAMS":[39],"Subject":[40],"Headings68Q25,":[41],"68R10,":[42],"68U05Publication":[43],"DataISSN":[44],"(print):":[45],"0363-0129ISSN":[46],"(online):":[47],"1095-7138Publisher:":[48],"Society":[49],"for":[50],"Industrial":[51],"and":[52],"Applied":[53],"MathematicsCODEN:":[54],"sjcodc":[55]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
