{"id":"https://openalex.org/W4407988008","doi":"https://doi.org/10.1109/cdc56724.2024.10885957","title":"On the Convergence of Policy Gradient for Designing a Linear Quadratic Regulator by Leveraging a Proxy System","display_name":"On the Convergence of Policy Gradient for Designing a Linear Quadratic Regulator by Leveraging a Proxy System","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407988008","doi":"https://doi.org/10.1109/cdc56724.2024.10885957"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10885957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10885957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-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/A5043334116","display_name":"Lintao Ye","orcid":"https://orcid.org/0000-0001-8608-5815"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lintao Ye","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Artificial Intelligence and Automation,Wuhan,China,430074"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Artificial Intelligence and Automation,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101651422","display_name":"Aritra Mitra","orcid":"https://orcid.org/0000-0002-0472-284X"},"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":"Aritra Mitra","raw_affiliation_strings":["North Carolina State University,Department of Electrical and Computer Engineering,Raleigh,NC,USA,27695"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University,Department of Electrical and Computer Engineering,Raleigh,NC,USA,27695","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024301984","display_name":"Vijay Gupta","orcid":"https://orcid.org/0000-0001-7060-3956"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Gupta","raw_affiliation_strings":["Purdue University,Elmore Family School of Electrical and Computer Engineering,West Lafayette,IN,USA,47906"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,Elmore Family School of Electrical and Computer Engineering,West Lafayette,IN,USA,47906","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31627851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6016","last_page":"6021"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.10589999705553055,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.10589999705553055,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.72402423620224},{"id":"https://openalex.org/keywords/regulator","display_name":"Regulator","score":0.6448978185653687},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5900310277938843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5545991063117981},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.5135576725006104},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.4690081775188446},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.46359533071517944},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43415671586990356},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23489496111869812},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.14544159173965454},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.11909693479537964},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.08658617734909058},{"id":"https://openalex.org/keywords/macroeconomics","display_name":"Macroeconomics","score":0.08138158917427063},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07105123996734619}],"concepts":[{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.72402423620224},{"id":"https://openalex.org/C6929976","wikidata":"https://www.wikidata.org/wiki/Q3771881","display_name":"Regulator","level":3,"score":0.6448978185653687},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5900310277938843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5545991063117981},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.5135576725006104},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.4690081775188446},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.46359533071517944},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43415671586990356},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23489496111869812},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.14544159173965454},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.11909693479537964},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08658617734909058},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.08138158917427063},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07105123996734619},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10885957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10885957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2103979068","https://openalex.org/W2152161277","https://openalex.org/W2948432982","https://openalex.org/W2963248893","https://openalex.org/W3004920191","https://openalex.org/W3098412154","https://openalex.org/W3203485495","https://openalex.org/W3206480318","https://openalex.org/W3209135762","https://openalex.org/W4313003229","https://openalex.org/W4315471887","https://openalex.org/W4367841446","https://openalex.org/W4388430748","https://openalex.org/W4388666639","https://openalex.org/W4400467694","https://openalex.org/W4407690537","https://openalex.org/W6678518843","https://openalex.org/W6746722099","https://openalex.org/W6754297394","https://openalex.org/W6756870468","https://openalex.org/W6763478762","https://openalex.org/W6767019922","https://openalex.org/W6774232178","https://openalex.org/W6781272283","https://openalex.org/W6796995573","https://openalex.org/W6856078685"],"related_works":["https://openalex.org/W2731754693","https://openalex.org/W267916353","https://openalex.org/W3091102817","https://openalex.org/W2326995340","https://openalex.org/W1985169903","https://openalex.org/W2152693275","https://openalex.org/W311622956","https://openalex.org/W1592622096","https://openalex.org/W4283732277","https://openalex.org/W2122083069"],"abstract_inverted_index":{"Policy":[0],"gradient":[1,46,61,78,84],"algorithms":[2],"have":[3],"been":[4],"shown":[5],"to":[6,8,91],"converge":[7,90],"the":[9,24,64,73,95,106,114,134,139],"optimal":[10,97],"controller":[11,123],"in":[12,40,85],"a":[13,30,38,49,56,68,92,120,125],"linear":[14],"quadratic":[15],"regulator":[16],"(LQR)":[17],"design":[18],"problem.":[19],"Calculating":[20],"policy":[21,83],"gradients":[22],"using":[23],"true":[25,65,115],"system":[26,53,66,116,136],"such":[27,54],"as":[28,55],"for":[29,137],"robot":[31],"may,":[32],"however,":[33],"be":[34],"costly.":[35],"We":[36],"consider":[37],"formulation":[39],"which":[41],"an":[42],"ample":[43],"number":[44],"of":[45,76,94,110],"calculations":[47,62],"from":[48,63],"proxy":[50,135],"or":[51],"approximate":[52],"simulator":[57],"are":[58],"mixed":[59],"with":[60],"at":[67],"few":[69],"time":[70],"steps.":[71],"Under":[72],"simplifying":[74],"assumption":[75],"exact":[77],"calculation,":[79],"we":[80],"show":[81],"that":[82,130],"this":[86,100],"framework":[87],"can":[88,103],"still":[89],"neighborhood":[93],"desired":[96],"controller.":[98,140],"In":[99],"sense,":[101],"it":[102],"reduce":[104],"both":[105],"burden":[107],"and":[108,117],"cost":[109],"experimenting":[111],"only":[112,132],"on":[113,133],"potentially":[118],"obtain":[119],"less":[121],"conservative":[122],"than":[124],"purely":[126],"robust":[127],"control":[128],"approach":[129],"relies":[131],"designing":[138]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
