{"id":"https://openalex.org/W4391021411","doi":"https://doi.org/10.1109/cdc49753.2023.10383470","title":"Data-Enabled Policy Optimization for the Linear Quadratic Regulator","display_name":"Data-Enabled Policy Optimization for the Linear Quadratic Regulator","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391021411","doi":"https://doi.org/10.1109/cdc49753.2023.10383470"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","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/A5026081309","display_name":"Feiran Zhao","orcid":"https://orcid.org/0000-0003-3142-2903"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiran Zhao","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Automation,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091434894","display_name":"Florian D\u00f6rfler","orcid":"https://orcid.org/0000-0002-9649-5305"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Florian D\u00f6rfler","raw_affiliation_strings":["ETH Zurich,Department of Information Technology and Electrical Engineering,Zurich,Switzerland,8092"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Department of Information Technology and Electrical Engineering,Zurich,Switzerland,8092","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088962631","display_name":"Keyou You","orcid":"https://orcid.org/0000-0003-4355-5340"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyou You","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Automation,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6160","last_page":"6165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.9986000061035156,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9976999759674072,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.7196546196937561},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5926923751831055},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.5817955732345581},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5663312673568726},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5537921190261841},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5327831506729126},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5232240557670593},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.47926756739616394},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.4725857973098755},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4368094801902771},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.43632227182388306},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.43214553594589233},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4156322479248047},{"id":"https://openalex.org/keywords/trust-region","display_name":"Trust region","score":0.41203773021698},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.34434202313423157},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3224891424179077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14339160919189453},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.13376069068908691}],"concepts":[{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.7196546196937561},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5926923751831055},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.5817955732345581},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5663312673568726},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5537921190261841},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5327831506729126},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5232240557670593},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.47926756739616394},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.4725857973098755},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4368094801902771},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.43632227182388306},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.43214553594589233},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4156322479248047},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.41203773021698},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.34434202313423157},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3224891424179077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14339160919189453},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.13376069068908691},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C178635117","wikidata":"https://www.wikidata.org/wiki/Q747499","display_name":"RADIUS","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3687553019","display_name":null,"funder_award_id":"62033006,62325305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5400309841","display_name":null,"funder_award_id":"2022ZD0116700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2098432798","https://openalex.org/W2145339207","https://openalex.org/W2822752092","https://openalex.org/W2952672134","https://openalex.org/W2967875632","https://openalex.org/W2979207987","https://openalex.org/W2995764727","https://openalex.org/W2999535065","https://openalex.org/W3119438804","https://openalex.org/W3137642493","https://openalex.org/W3166923021","https://openalex.org/W3199938616","https://openalex.org/W3209135762","https://openalex.org/W3213835390","https://openalex.org/W4210265003","https://openalex.org/W4229706427","https://openalex.org/W4288345424","https://openalex.org/W4313591116","https://openalex.org/W4315472091","https://openalex.org/W4367841446","https://openalex.org/W4385127973","https://openalex.org/W6684921986","https://openalex.org/W6754297394","https://openalex.org/W6756870468","https://openalex.org/W6757029329","https://openalex.org/W6763624801","https://openalex.org/W6773334542"],"related_works":["https://openalex.org/W2080108722","https://openalex.org/W2752681920","https://openalex.org/W1997473290","https://openalex.org/W2353911672","https://openalex.org/W2393042414","https://openalex.org/W2062145486","https://openalex.org/W2058731384","https://openalex.org/W2069101571","https://openalex.org/W2154146583","https://openalex.org/W778450153"],"abstract_inverted_index":{"Policy":[0],"optimization":[1,55],"(PO),":[2],"an":[3,43,116,144],"essential":[4],"approach":[5],"of":[6,13,64,94,125,138],"reinforcement":[7],"learning":[8],"for":[9],"a":[10,61,78,92,107],"broad":[11],"range":[12],"system":[14,19],"classes,":[15],"requires":[16,59],"significantly":[17],"more":[18],"data":[20,67],"than":[21],"indirect":[22],"(identification-followed-by-control)":[23],"methods":[24,28,131],"or":[25],"behavioral-based":[26],"direct":[27],"even":[29],"in":[30],"the":[31,52,71,88,102,122,134,139],"simplest":[32],"linear":[33],"quadratic":[34],"regulator":[35],"(LQR)":[36],"problem.":[37],"In":[38],"this":[39,48],"paper,":[40],"we":[41,82,99,128,149],"take":[42],"initial":[44],"step":[45],"towards":[46],"bridging":[47],"gap":[49],"by":[50,112],"proposing":[51],"data-enabled":[53],"policy":[54,89],"(DeePO)":[56],"method,":[57],"which":[58],"only":[60],"finite":[62],"number":[63],"sufficiently":[65],"exciting":[66,96],"to":[68,85,115,121,132,152],"iteratively":[69],"solve":[70],"LQR":[72],"problem":[73,105],"via":[74],"PO.":[75],"Based":[76],"on":[77],"data-driven":[79],"closed-loop":[80],"parameterization,":[81],"are":[83],"able":[84],"directly":[86],"compute":[87],"gradient":[90,109],"from":[91],"batch":[93],"persistently":[95],"data.":[97],"Next,":[98],"show":[100,143],"that":[101],"nonconvex":[103],"PO":[104],"satisfies":[106],"projected":[108],"dominance":[110],"property":[111],"relating":[113],"it":[114],"equivalent":[117],"convex":[118],"program,":[119],"leading":[120],"global":[123],"convergence":[124],"DeePO.":[126],"Moreover,":[127],"apply":[129],"regularization":[130,146],"enhance":[133],"certainty-equivalence":[135],"and":[136,142],"robustness":[137],"resulting":[140],"controller":[141],"implicit":[145],"property.":[147],"Finally,":[148],"perform":[150],"simulations":[151],"validate":[153],"our":[154],"results.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}