{"id":"https://openalex.org/W4402264735","doi":"https://doi.org/10.23919/acc60939.2024.10644167","title":"Oracle Complexity Reduction for Model-Free LQR: A Stochastic Variance-Reduced Policy Gradient Approach","display_name":"Oracle Complexity Reduction for Model-Free LQR: A Stochastic Variance-Reduced Policy Gradient Approach","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4402264735","doi":"https://doi.org/10.23919/acc60939.2024.10644167"},"language":"en","primary_location":{"id":"doi:10.23919/acc60939.2024.10644167","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc60939.2024.10644167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","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/A5070513733","display_name":"Leonardo F. Toso","orcid":"https://orcid.org/0000-0001-8679-868X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonardo F. Toso","raw_affiliation_strings":["Columbia University in the City of New York,Department of Electrical Engineering,New York,NY,USA,10027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University in the City of New York,Department of Electrical Engineering,New York,NY,USA,10027","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452641","display_name":"Han Wang","orcid":"https://orcid.org/0000-0001-5448-9903"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Wang","raw_affiliation_strings":["Columbia University in the City of New York,Department of Electrical Engineering,New York,NY,USA,10027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University in the City of New York,Department of Electrical Engineering,New York,NY,USA,10027","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101563166","display_name":"James Anderson","orcid":"https://orcid.org/0000-0001-8210-6527"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Anderson","raw_affiliation_strings":["Columbia University in the City of New York,Department of Electrical Engineering,New York,NY,USA,10027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University in the City of New York,Department of Electrical Engineering,New York,NY,USA,10027","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":0.7112,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70001849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4032","last_page":"4037"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9994999766349792,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/variance-reduction","display_name":"Variance reduction","score":0.7902418375015259},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.7629269361495972},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.7378644943237305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6104001998901367},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5853562355041504},{"id":"https://openalex.org/keywords/random-oracle","display_name":"Random oracle","score":0.4834898114204407},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37380439043045044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19442260265350342},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.06458646059036255},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.06400960683822632}],"concepts":[{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.7902418375015259},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7629269361495972},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.7378644943237305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6104001998901367},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5853562355041504},{"id":"https://openalex.org/C94284585","wikidata":"https://www.wikidata.org/wiki/Q228184","display_name":"Random oracle","level":4,"score":0.4834898114204407},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37380439043045044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19442260265350342},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.06458646059036255},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.06400960683822632},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C203062551","wikidata":"https://www.wikidata.org/wiki/Q201339","display_name":"Public-key cryptography","level":3,"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/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc60939.2024.10644167","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc60939.2024.10644167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6988599536","display_name":null,"funder_award_id":"2144634,2231350","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":36,"referenced_works":["https://openalex.org/W203276351","https://openalex.org/W2011866373","https://openalex.org/W2022638422","https://openalex.org/W2105875671","https://openalex.org/W2107411554","https://openalex.org/W2107438106","https://openalex.org/W2125612430","https://openalex.org/W2803300317","https://openalex.org/W2810882972","https://openalex.org/W3011908139","https://openalex.org/W3045745164","https://openalex.org/W3046992251","https://openalex.org/W3098412154","https://openalex.org/W3103047293","https://openalex.org/W3166923021","https://openalex.org/W3174844138","https://openalex.org/W3206321238","https://openalex.org/W4310238750","https://openalex.org/W4315472036","https://openalex.org/W4367841446","https://openalex.org/W4386147959","https://openalex.org/W4402264735","https://openalex.org/W6675761068","https://openalex.org/W6676105031","https://openalex.org/W6751777967","https://openalex.org/W6751972096","https://openalex.org/W6753122105","https://openalex.org/W6754297394","https://openalex.org/W6756870468","https://openalex.org/W6762577472","https://openalex.org/W6762819967","https://openalex.org/W6785116810","https://openalex.org/W6786084949","https://openalex.org/W6797770812","https://openalex.org/W6802758289","https://openalex.org/W6856078685"],"related_works":["https://openalex.org/W2073713056","https://openalex.org/W3110702597","https://openalex.org/W2169816622","https://openalex.org/W2298254442","https://openalex.org/W1997242758","https://openalex.org/W2169367269","https://openalex.org/W2951368390","https://openalex.org/W2291558465","https://openalex.org/W1981992409","https://openalex.org/W2067529449"],"abstract_inverted_index":{"We":[0],"investigate":[1],"the":[2,9,34,38,42],"problem":[3,15],"of":[4,37],"learning":[5],"an$\\epsilon$-approximate":[6],"solution":[7,36,98],"for":[8,45],"discrete-time":[10],"Linear":[11],"Quadratic":[12],"Regulator":[13],"(LQR)":[14],"via":[16],"a":[17,89],"Stochastic":[18],"Variance-Reduced":[19],"Policy":[20],"Gradient":[21],"(SVRPG)":[22],"approach.":[23,79],"Whilst":[24],"policy":[25],"gradient":[26,50],"methods":[27],"have":[28],"proven":[29],"to":[30,33],"converge":[31],"linearly":[32],"optimal":[35,97],"model-free":[39],"LQR":[40],"problem,":[41],"substantial":[43],"requirement":[44],"two-point":[46,86],"cost":[47,60,101],"queries":[48],"in":[49,56,88],"estimations":[51,87],"may":[52],"be":[53],"intractable,":[54],"particularly":[55],"applications":[57],"where":[58],"obtaining":[59],"function":[61],"evaluations":[62],"at":[63],"two":[64],"distinct":[65],"control":[66],"input":[67],"configurations":[68],"is":[69],"exceptionally":[70],"costly.":[71],"To":[72],"this":[73],"end,":[74],"we":[75],"propose":[76],"an":[77,95],"oracle-efficient":[78],"Our":[80],"method":[81],"combines":[82],"both":[83],"one-point":[84],"and":[85],"dual-loop":[90],"variance-reduced":[91],"algorithm.":[92],"It":[93],"achieves":[94],"approximate":[96],"with":[99],"only$\\mathcal{O}\\left(\\log(1/\\epsilon)^{\\beta}\\right)$two-point":[100],"information":[102],"for$\\beta\\in(0,1)$.":[103]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}