{"id":"https://openalex.org/W2922217511","doi":"https://doi.org/10.1109/cdc40024.2019.9029975","title":"On Applications of Bootstrap in Continuous Space Reinforcement Learning","display_name":"On Applications of Bootstrap in Continuous Space Reinforcement Learning","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2922217511","doi":"https://doi.org/10.1109/cdc40024.2019.9029975","mag":"2922217511"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9029975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.05803","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074828603","display_name":"Mohamad Kazem Shirani Faradonbeh","orcid":"https://orcid.org/0009-0000-1111-8440"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohamad Kazem Shirani Faradonbeh","raw_affiliation_strings":["Department of Statistics and the Informatics Institute, University of Florida, Gainesville, FL, USA","University of Florida,Department of Statistics and the Informatics Institute,Gainesville,FL,USA,32611-5585"],"affiliations":[{"raw_affiliation_string":"Department of Statistics and the Informatics Institute, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"University of Florida,Department of Statistics and the Informatics Institute,Gainesville,FL,USA,32611-5585","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051918150","display_name":"Ambuj Tewari","orcid":"https://orcid.org/0000-0001-6969-7844"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ambuj Tewari","raw_affiliation_strings":["Department of Statistics and the Department of Electrical Engineering and Computer Science (by courtesy), University of Michigan, Ann Arbor, MI, USA","University of Michigan,Department of Statistics and the Department of Electrical Engineering and Computer Science (by courtesy),Ann Arbor,MI,USA,48109-1107"],"affiliations":[{"raw_affiliation_string":"Department of Statistics and the Department of Electrical Engineering and Computer Science (by courtesy), University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan,Department of Statistics and the Department of Electrical Engineering and Computer Science (by courtesy),Ann Arbor,MI,USA,48109-1107","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017220650","display_name":"George Michailidis","orcid":"https://orcid.org/0000-0002-3676-1739"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Michailidis","raw_affiliation_strings":["Department of Statistics and the Informatics Institute, University of Florida, Gainesville, FL, USA","University of Florida,Department of Statistics and the Informatics Institute,Gainesville,FL,USA,32611-5585"],"affiliations":[{"raw_affiliation_string":"Department of Statistics and the Informatics Institute, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"University of Florida,Department of Statistics and the Informatics Institute,Gainesville,FL,USA,32611-5585","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074828603"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":0.209597,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55121966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"31","issue":null,"first_page":"1977","last_page":"1984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9997000098228455,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9879000186920166,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8184300661087036},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.6639688014984131},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.6314120888710022},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6106128692626953},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5161322355270386},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4692012667655945},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.445137083530426},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.44434672594070435},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4236072897911072},{"id":"https://openalex.org/keywords/square-root","display_name":"Square root","score":0.41930633783340454},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37322506308555603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34296321868896484},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3249968886375427},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28756165504455566},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.23666471242904663},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1318398416042328}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8184300661087036},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6639688014984131},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.6314120888710022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6106128692626953},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5161322355270386},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4692012667655945},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.445137083530426},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.44434672594070435},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4236072897911072},{"id":"https://openalex.org/C11577676","wikidata":"https://www.wikidata.org/wiki/Q134237","display_name":"Square root","level":2,"score":0.41930633783340454},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37322506308555603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34296321868896484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3249968886375427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28756165504455566},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.23666471242904663},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1318398416042328},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cdc40024.2019.9029975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.05803","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.05803","pdf_url":"https://arxiv.org/pdf/1903.05803","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2922217511","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1903.05803","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1903.05803","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.05803","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.05803","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.05803","pdf_url":"https://arxiv.org/pdf/1903.05803","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2922217511.pdf","grobid_xml":"https://content.openalex.org/works/W2922217511.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W50486269","https://openalex.org/W53582479","https://openalex.org/W61273216","https://openalex.org/W195033972","https://openalex.org/W1521930086","https://openalex.org/W1535136082","https://openalex.org/W1579979603","https://openalex.org/W1687382548","https://openalex.org/W1851714595","https://openalex.org/W1963488305","https://openalex.org/W1973240854","https://openalex.org/W2000352206","https://openalex.org/W2009551863","https://openalex.org/W2019972886","https://openalex.org/W2043265117","https://openalex.org/W2043962331","https://openalex.org/W2048287263","https://openalex.org/W2063986268","https://openalex.org/W2064997337","https://openalex.org/W2069057356","https://openalex.org/W2094826322","https://openalex.org/W2098432798","https://openalex.org/W2098918617","https://openalex.org/W2117897510","https://openalex.org/W2119738618","https://openalex.org/W2137435813","https://openalex.org/W2167856595","https://openalex.org/W2174477337","https://openalex.org/W2343609400","https://openalex.org/W2548328397","https://openalex.org/W2732381065","https://openalex.org/W2761923184","https://openalex.org/W2762498633","https://openalex.org/W2768425162","https://openalex.org/W2789525339","https://openalex.org/W2804569092","https://openalex.org/W2804585439","https://openalex.org/W2811188376","https://openalex.org/W2883971433","https://openalex.org/W2890141553","https://openalex.org/W2900221856","https://openalex.org/W2914594564","https://openalex.org/W2951143099","https://openalex.org/W2951990408","https://openalex.org/W2962740831","https://openalex.org/W2963695785","https://openalex.org/W2963938771","https://openalex.org/W2973076431","https://openalex.org/W3012506381","https://openalex.org/W3012692135","https://openalex.org/W3122810100","https://openalex.org/W3124265655","https://openalex.org/W4236323066","https://openalex.org/W4248696375","https://openalex.org/W6602031475","https://openalex.org/W6607786297","https://openalex.org/W6634861202","https://openalex.org/W6637387425","https://openalex.org/W6695011786","https://openalex.org/W6745072325","https://openalex.org/W6751494857","https://openalex.org/W6751799726","https://openalex.org/W6752539433","https://openalex.org/W6754447547","https://openalex.org/W6756164497","https://openalex.org/W6756955122","https://openalex.org/W6765369835","https://openalex.org/W6779152747"],"related_works":["https://openalex.org/W3177107840","https://openalex.org/W3047267560","https://openalex.org/W2141064830","https://openalex.org/W3039767125","https://openalex.org/W3039984786","https://openalex.org/W1511164163","https://openalex.org/W3028474848","https://openalex.org/W3191836031","https://openalex.org/W269667127","https://openalex.org/W333087574","https://openalex.org/W2914375891","https://openalex.org/W2247346057","https://openalex.org/W3027624373","https://openalex.org/W3203981230","https://openalex.org/W2990320418","https://openalex.org/W1498557354","https://openalex.org/W3190360147","https://openalex.org/W3001641429","https://openalex.org/W2791126661","https://openalex.org/W1548789276"],"abstract_inverted_index":{"In":[0,67],"decision":[1],"making":[2],"problems":[3],"for":[4,18],"continuous":[5],"state":[6],"and":[7,52,65],"action":[8],"spaces,":[9],"linear":[10,20],"dynamical":[11],"models":[12],"are":[13],"widely":[14],"employed.":[15],"Specifically,":[16],"policies":[17,38,59,74],"stochastic":[19],"systems":[21],"subject":[22],"to":[23,84],"quadratic":[24],"cost":[25],"functions":[26],"capture":[27],"a":[28,76],"large":[29],"number":[30],"of":[31,80,93],"applications":[32],"in":[33,42],"reinforcement":[34],"learning.":[35],"Selected":[36],"randomized":[37],"have":[39],"been":[40],"studied":[41],"the":[43,48,91,95,103],"literature":[44],"recently":[45],"that":[46,72,101],"address":[47],"trade-off":[49],"between":[50],"identification":[51],"control.":[53],"However,":[54],"little":[55],"is":[56,106],"known":[57],"about":[58],"based":[60],"on":[61,90],"bootstrapping":[62],"observed":[63],"states":[64],"actions.":[66],"this":[68],"work,":[69],"we":[70],"show":[71],"bootstrap-based":[73],"achieve":[75],"square":[77],"root":[78],"scaling":[79],"regret":[81],"with":[82],"respect":[83],"time.":[85],"We":[86],"also":[87,107],"obtain":[88],"results":[89,105],"accuracy":[92],"learning":[94],"model's":[96],"dynamics.":[97],"Corroborative":[98],"numerical":[99],"analysis":[100],"illustrates":[102],"technical":[104],"provided.":[108]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}