{"id":"https://openalex.org/W4294692043","doi":"https://doi.org/10.23919/acc53348.2022.9867808","title":"Online Learning-based Optimal Control of Nonlinear Systems with Finite-Time Convergence Guarantees","display_name":"Online Learning-based Optimal Control of Nonlinear Systems with Finite-Time Convergence Guarantees","publication_year":2022,"publication_date":"2022-06-08","ids":{"openalex":"https://openalex.org/W4294692043","doi":"https://doi.org/10.23919/acc53348.2022.9867808"},"language":"en","primary_location":{"id":"doi:10.23919/acc53348.2022.9867808","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867808","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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":"2022 American Control Conference (ACC)","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/A5015440501","display_name":"Nick\u2010Marios T. Kokolakis","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nick-Marios T. Kokolakis","raw_affiliation_strings":["Georgia Institute of Technology,Daniel Guggenheim School of Aerospace Engineering,Atlanta,GA,USA,30332"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Daniel Guggenheim School of Aerospace Engineering,Atlanta,GA,USA,30332","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040301558","display_name":"Kyriakos G. Vamvoudakis","orcid":"https://orcid.org/0000-0003-1978-4848"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyriakos G. Vamvoudakis","raw_affiliation_strings":["Georgia Institute of Technology,Daniel Guggenheim School of Aerospace Engineering,Atlanta,GA,USA,30332"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Daniel Guggenheim School of Aerospace Engineering,Atlanta,GA,USA,30332","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015440501"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":2.0753,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.88778878,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"812","last_page":"817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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":0.9926999807357788,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9793000221252441,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.8931401371955872},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.755612313747406},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7366080284118652},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6296182870864868},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6217954754829407},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5874173641204834},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5660440921783447},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.5076795816421509},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5046571493148804},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.47549211978912354},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.46512529253959656},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4600287675857544},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.4445376992225647},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3966703414916992},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.33429843187332153},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2948800325393677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19362875819206238},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12479358911514282},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.07058823108673096}],"concepts":[{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.8931401371955872},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.755612313747406},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7366080284118652},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6296182870864868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6217954754829407},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5874173641204834},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5660440921783447},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5076795816421509},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5046571493148804},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.47549211978912354},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.46512529253959656},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4600287675857544},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.4445376992225647},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3966703414916992},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.33429843187332153},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2948800325393677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19362875819206238},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12479358911514282},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07058823108673096},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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":1,"locations":[{"id":"doi:10.23919/acc53348.2022.9867808","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867808","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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":"2022 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W560518094","https://openalex.org/W601351931","https://openalex.org/W1513689897","https://openalex.org/W1517236425","https://openalex.org/W1584101032","https://openalex.org/W1854776945","https://openalex.org/W1988837728","https://openalex.org/W2015113370","https://openalex.org/W2027197837","https://openalex.org/W2045005985","https://openalex.org/W2050838777","https://openalex.org/W2085194340","https://openalex.org/W2141559645","https://openalex.org/W2152161277","https://openalex.org/W2157577161","https://openalex.org/W2165726932","https://openalex.org/W2309350575","https://openalex.org/W2314983263","https://openalex.org/W2484646121","https://openalex.org/W2487144912","https://openalex.org/W2570494446","https://openalex.org/W2772589676","https://openalex.org/W2800330509","https://openalex.org/W3102740879","https://openalex.org/W3135791089","https://openalex.org/W4214717370","https://openalex.org/W4244299687","https://openalex.org/W4301018745","https://openalex.org/W4301886962"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W4243706127","https://openalex.org/W3099153698","https://openalex.org/W1859185863","https://openalex.org/W2758222473","https://openalex.org/W2964126589","https://openalex.org/W4285537323","https://openalex.org/W2043536252"],"abstract_inverted_index":{"This":[0],"paper":[1],"develops":[2],"a":[3,21],"critic-only":[4],"reinforcement":[5],"learning-based":[6],"algorithm":[7],"for":[8,34],"learning":[9,25],"the":[10,13,36,41,48,58,63,67,73,82,85],"solution":[11],"to":[12,39,52,65],"Hamilton-Jacobi-Bellman":[14],"equation":[15],"in":[16],"finite":[17],"time.":[18],"In":[19],"particular,":[20],"non-Lipschitz":[22,45],"experience":[23,59],"replay-based":[24,60],"law":[26],"utilizing":[27],"recorded":[28,74],"and":[29,55],"current":[30],"data":[31,75],"is":[32,76],"introduced":[33],"updating":[35],"critic":[37],"weights":[38],"learn":[40],"value":[42],"function.":[43],"The":[44],"property":[46],"of":[47,69,84],"dynamics":[49],"gives":[50],"rise":[51],"finite-time":[53],"convergence":[54],"stability,":[56],"while":[57],"approach":[61],"eliminates":[62],"need":[64],"satisfy":[66],"persistence":[68],"excitation":[70],"condition":[71],"if":[72],"sufficiently":[77],"rich.":[78],"Simulation":[79],"results":[80],"demonstrate":[81],"efficacy":[83],"proposed":[86],"approach.":[87]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}