{"id":"https://openalex.org/W3204222741","doi":"https://doi.org/10.1109/cdc45484.2021.9683721","title":"Reinforcement Learning Policies With Local LQR Guarantees For Nonlinear Discrete-Time Systems","display_name":"Reinforcement Learning Policies With Local LQR Guarantees For Nonlinear Discrete-Time Systems","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W3204222741","doi":"https://doi.org/10.1109/cdc45484.2021.9683721","mag":"3204222741"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9683721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683721","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-03353584v1/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047917238","display_name":"Samuele Zoboli","orcid":"https://orcid.org/0009-0006-9225-4551"},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210143168","display_name":"Laboratoire d'Automatique, de G\u00e9nie des Proc\u00e9d\u00e9s et de G\u00e9nie Pharmaceutique","ror":"https://ror.org/03kfjwy31","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I203339264","https://openalex.org/I4210095849","https://openalex.org/I4210143168","https://openalex.org/I59692284"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Samuele Zoboli","raw_affiliation_strings":["Université Claude Bernard Lyon 1, CNRS, LAGEPP UMR 5007,Villeurbanne,France,F-69100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Claude Bernard Lyon 1, CNRS, LAGEPP UMR 5007,Villeurbanne,France,F-69100","institution_ids":["https://openalex.org/I100532134","https://openalex.org/I1294671590","https://openalex.org/I4210143168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082790000","display_name":"Vincent Andrieu","orcid":"https://orcid.org/0000-0003-1877-6205"},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210143168","display_name":"Laboratoire d'Automatique, de G\u00e9nie des Proc\u00e9d\u00e9s et de G\u00e9nie Pharmaceutique","ror":"https://ror.org/03kfjwy31","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I203339264","https://openalex.org/I4210095849","https://openalex.org/I4210143168","https://openalex.org/I59692284"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vincent Andrieu","raw_affiliation_strings":["Université Claude Bernard Lyon 1, CNRS, LAGEPP UMR 5007,Villeurbanne,France,F-69100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Claude Bernard Lyon 1, CNRS, LAGEPP UMR 5007,Villeurbanne,France,F-69100","institution_ids":["https://openalex.org/I100532134","https://openalex.org/I1294671590","https://openalex.org/I4210143168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074286208","display_name":"Daniele Astolfi","orcid":"https://orcid.org/0000-0003-2690-7420"},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210143168","display_name":"Laboratoire d'Automatique, de G\u00e9nie des Proc\u00e9d\u00e9s et de G\u00e9nie Pharmaceutique","ror":"https://ror.org/03kfjwy31","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I203339264","https://openalex.org/I4210095849","https://openalex.org/I4210143168","https://openalex.org/I59692284"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Daniele Astolfi","raw_affiliation_strings":["Université Claude Bernard Lyon 1, CNRS, LAGEPP UMR 5007,Villeurbanne,France,F-69100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Claude Bernard Lyon 1, CNRS, LAGEPP UMR 5007,Villeurbanne,France,F-69100","institution_ids":["https://openalex.org/I100532134","https://openalex.org/I1294671590","https://openalex.org/I4210143168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035749456","display_name":"Giacomo Casadei","orcid":"https://orcid.org/0000-0002-6597-1137"},"institutions":[{"id":"https://openalex.org/I112936343","display_name":"\u00c9cole Centrale de Lyon","ror":"https://ror.org/05s6rge65","country_code":"FR","type":"education","lineage":["https://openalex.org/I112936343","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I4210145913","display_name":"Laboratoire Amp\u00e8re","ror":"https://ror.org/04xbczw40","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I112936343","https://openalex.org/I1294671590","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210145913","https://openalex.org/I48430043"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Giacomo Casadei","raw_affiliation_strings":["Université de Lyon,Laboratoire Ampere Dpt. EEA of the \u00c9cole Centrale de Lyon,Ecully,France,69134"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lyon,Laboratoire Ampere Dpt. EEA of the \u00c9cole Centrale de Lyon,Ecully,France,69134","institution_ids":["https://openalex.org/I112936343","https://openalex.org/I4210145913"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032392204","display_name":"Jilles Dibangoye","orcid":"https://orcid.org/0000-0001-8826-4438"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I48430043","display_name":"Institut National des Sciences Appliqu\u00e9es de Lyon","ror":"https://ror.org/050jn9y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I203339264","https://openalex.org/I48430043"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jilles S. Dibangoye","raw_affiliation_strings":["INRIA Chroma Team,CITI Lab. INSA Lyon,Villeubanne,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Chroma Team,CITI Lab. INSA Lyon,Villeubanne,France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I48430043"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090803163","display_name":"Madiha Nadri","orcid":"https://orcid.org/0000-0002-9705-6101"},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210143168","display_name":"Laboratoire d'Automatique, de G\u00e9nie des Proc\u00e9d\u00e9s et de G\u00e9nie Pharmaceutique","ror":"https://ror.org/03kfjwy31","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I203339264","https://openalex.org/I4210095849","https://openalex.org/I4210143168","https://openalex.org/I59692284"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Madiha Nadri","raw_affiliation_strings":["Université Claude Bernard Lyon 1, CNRS, LAGEPP UMR 5007,Villeurbanne,France,F-69100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Claude Bernard Lyon 1, CNRS, LAGEPP UMR 5007,Villeurbanne,France,F-69100","institution_ids":["https://openalex.org/I100532134","https://openalex.org/I1294671590","https://openalex.org/I4210143168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.25,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.884356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2258","last_page":"2263"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9994999766349792,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9994999766349792,"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":0.9987000226974487,"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":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8389919996261597},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.819526195526123},{"id":"https://openalex.org/keywords/linearization","display_name":"Linearization","score":0.7552708387374878},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6834720373153687},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6720160245895386},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5972166061401367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.594933032989502},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.559660017490387},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5386156439781189},{"id":"https://openalex.org/keywords/feedback-linearization","display_name":"Feedback linearization","score":0.5272031426429749},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4713040292263031},{"id":"https://openalex.org/keywords/nonlinear-control","display_name":"Nonlinear control","score":0.4104103446006775},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3587243854999542},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.31410008668899536},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2640800476074219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21885830163955688},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20295274257659912},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08114767074584961}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8389919996261597},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.819526195526123},{"id":"https://openalex.org/C11210021","wikidata":"https://www.wikidata.org/wiki/Q1520713","display_name":"Linearization","level":3,"score":0.7552708387374878},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6834720373153687},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6720160245895386},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5972166061401367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.594933032989502},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.559660017490387},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5386156439781189},{"id":"https://openalex.org/C85736874","wikidata":"https://www.wikidata.org/wiki/Q672139","display_name":"Feedback linearization","level":3,"score":0.5272031426429749},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4713040292263031},{"id":"https://openalex.org/C91581856","wikidata":"https://www.wikidata.org/wiki/Q2707001","display_name":"Nonlinear control","level":3,"score":0.4104103446006775},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3587243854999542},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.31410008668899536},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2640800476074219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21885830163955688},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20295274257659912},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08114767074584961},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc45484.2021.9683721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683721","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03353584v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03353584","pdf_url":"https://hal.science/hal-03353584v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://ieeexplore.ieee.org/document/9683721","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03353584v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03353584","pdf_url":"https://hal.science/hal-03353584v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://ieeexplore.ieee.org/document/9683721","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2384274448","display_name":"Data and Prior, Machine Learning and Control","funder_award_id":"ANR-19-CE23-0006","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3204222741.pdf","grobid_xml":"https://content.openalex.org/works/W3204222741.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1574514837","https://openalex.org/W1687991450","https://openalex.org/W2121832485","https://openalex.org/W2156737235","https://openalex.org/W2164479831","https://openalex.org/W2298163601","https://openalex.org/W2529970964","https://openalex.org/W2736601468","https://openalex.org/W2787938642","https://openalex.org/W2891051118","https://openalex.org/W2902907165","https://openalex.org/W2913300629","https://openalex.org/W2963864421","https://openalex.org/W3045059767","https://openalex.org/W3098713169","https://openalex.org/W3204222741","https://openalex.org/W4294555834","https://openalex.org/W4298857966","https://openalex.org/W4302570325","https://openalex.org/W6637967152","https://openalex.org/W6678518843","https://openalex.org/W6683195989","https://openalex.org/W6684037837","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6738483526","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6758924645"],"related_works":["https://openalex.org/W2349527210","https://openalex.org/W1998462347","https://openalex.org/W1836713364","https://openalex.org/W2131265573","https://openalex.org/W2899783744","https://openalex.org/W2964841342","https://openalex.org/W4300511988","https://openalex.org/W130230158","https://openalex.org/W2381676799","https://openalex.org/W2912982761"],"abstract_inverted_index":{"Optimal":[0],"control":[1],"of":[2,31,63,69],"nonlinear":[3,93],"systems":[4],"is":[5],"a":[6,57,78,91],"difficult":[7],"problem":[8],"which":[9],"has":[10],"been":[11],"addressed":[12],"by":[13],"both":[14,64],"the":[15,25,29,32,61,67,86],"Control":[16],"Theory":[17],"(CT)":[18],"and":[19,99],"Reinforcement":[20],"Learning":[21],"(RL)":[22],"communities.":[23],"Frequently,":[24],"former":[26],"relies":[27,41],"on":[28,42,50,85],"linearization":[30],"system":[33],"thus":[34],"obtaining":[35],"only":[36],"local":[37,72,96],"guarantees.":[38],"The":[39],"latter":[40],"data":[43],"to":[44,59,89],"build":[45],"model-free":[46],"controllers,":[47],"focused":[48],"solely":[49],"performances.":[51,101],"In":[52],"this":[53],"paper":[54],"we":[55],"propose":[56],"methodology":[58],"combine":[60],"advantages":[62],"approaches,":[65],"casting":[66],"formulation":[68],"an":[70],"optimal":[71],"Linear":[73],"Quadratic":[74],"Regulator":[75],"(LQR)":[76],"into":[77],"Deep":[79],"RL":[80],"problem.":[81],"Our":[82],"solution":[83],"builds":[84],"linear":[87],"framework":[88],"derive":[90],"learnt":[92],"controller":[94],"showing":[95],"stability":[97],"properties":[98],"global":[100]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}