{"id":"https://openalex.org/W2963093491","doi":"https://doi.org/10.1109/cdc.2014.7040183","title":"Model-based reinforcement learning for infinite-horizon approximate optimal tracking","display_name":"Model-based reinforcement learning for infinite-horizon approximate optimal tracking","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2963093491","doi":"https://doi.org/10.1109/cdc.2014.7040183","mag":"2963093491"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2014.7040183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2014.7040183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"53rd IEEE Conference on Decision and Control","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/A5071224574","display_name":"Rushikesh Kamalapurkar","orcid":"https://orcid.org/0000-0001-9963-5361"},"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":"Rushikesh Kamalapurkar","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070648347","display_name":"Lindsey Andrews","orcid":null},"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":"Lindsey Andrews","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081019368","display_name":"Patrick Walters","orcid":"https://orcid.org/0000-0001-8157-2542"},"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":"Patrick Walters","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032651215","display_name":"Warren E. Dixon","orcid":"https://orcid.org/0000-0002-5091-181X"},"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":"Warren E. Dixon","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5083","last_page":"5088"},"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9779999852180481,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9688000082969666,"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":0.884503960609436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6247398853302002},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5875273942947388},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.584650993347168},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5805612802505493},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5542471408843994},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5517053604125977},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5054550170898438},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.49274566769599915},{"id":"https://openalex.org/keywords/tracking-error","display_name":"Tracking error","score":0.4887115955352783},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4875771403312683},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.46295127272605896},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.4610852599143982},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4387959837913513},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4357324540615082},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29873126745224},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2476511001586914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23744866251945496},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16059792041778564}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.884503960609436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6247398853302002},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5875273942947388},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.584650993347168},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5805612802505493},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5542471408843994},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5517053604125977},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5054550170898438},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49274566769599915},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.4887115955352783},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4875771403312683},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.46295127272605896},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.4610852599143982},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4387959837913513},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4357324540615082},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29873126745224},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2476511001586914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23744866251945496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16059792041778564},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2014.7040183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2014.7040183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"53rd IEEE Conference on Decision and Control","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":37,"referenced_works":["https://openalex.org/W13127292","https://openalex.org/W1574514837","https://openalex.org/W1584101032","https://openalex.org/W1914756871","https://openalex.org/W1977237536","https://openalex.org/W1983523797","https://openalex.org/W2002007892","https://openalex.org/W2003183707","https://openalex.org/W2013895638","https://openalex.org/W2033394144","https://openalex.org/W2048687352","https://openalex.org/W2052305027","https://openalex.org/W2052369206","https://openalex.org/W2085194340","https://openalex.org/W2093831009","https://openalex.org/W2097253853","https://openalex.org/W2098035803","https://openalex.org/W2098432798","https://openalex.org/W2104843094","https://openalex.org/W2111034649","https://openalex.org/W2113501460","https://openalex.org/W2116479681","https://openalex.org/W2120249358","https://openalex.org/W2121863487","https://openalex.org/W2150514620","https://openalex.org/W2150841368","https://openalex.org/W2160698719","https://openalex.org/W2179284380","https://openalex.org/W2476930474","https://openalex.org/W2484646121","https://openalex.org/W2963273254","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W6634206955","https://openalex.org/W6674691550","https://openalex.org/W6674995601","https://openalex.org/W6685744914"],"related_works":["https://openalex.org/W4378651134","https://openalex.org/W4252684102","https://openalex.org/W2352307597","https://openalex.org/W1979633005","https://openalex.org/W2163724607","https://openalex.org/W3135403405","https://openalex.org/W2023227762","https://openalex.org/W2608983118","https://openalex.org/W1980092392","https://openalex.org/W2726582213"],"abstract_inverted_index":{"This":[0],"paper":[1],"provides":[2],"an":[3],"approximate":[4],"online":[5],"adaptive":[6],"solution":[7],"to":[8,29,47,73],"the":[9,31,52,59,64,70,77],"infinite-horizon":[10],"optimal":[11,78],"tracking":[12],"problem":[13],"for":[14],"control-affine":[15],"continuous-time":[16],"nonlinear":[17],"systems":[18],"with":[19],"unknown":[20],"drift":[21],"dynamics":[22],"where":[23],"model-based":[24],"reinforcement":[25,37],"learning":[26,38],"is":[27,39,80],"used":[28],"relax":[30],"persistence":[32],"of":[33,58,63,69,76],"excitation":[34],"condition.":[35],"Model-based":[36],"implemented":[40],"using":[41],"a":[42,74],"concurrent":[43],"learning-based":[44],"system":[45],"identifier":[46],"simulate":[48],"experience":[49],"by":[50],"evaluating":[51],"Bellman":[53],"error":[54],"over":[55],"unexplored":[56],"areas":[57],"state":[60],"space.":[61],"Tracking":[62],"desired":[65],"trajectory":[66],"and":[67],"convergence":[68],"developed":[71],"policy":[72,79],"neighborhood":[75],"established":[81],"via":[82],"Lyapunov-based":[83],"stability":[84],"analysis.":[85]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}