{"id":"https://openalex.org/W1977671496","doi":"https://doi.org/10.1109/tnnls.2015.2511658","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":2016,"publication_date":"2016-02-03","ids":{"openalex":"https://openalex.org/W1977671496","doi":"https://doi.org/10.1109/tnnls.2015.2511658","mag":"1977671496","pmid":"https://pubmed.ncbi.nlm.nih.gov/26863674"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2015.2511658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2015.2511658","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1506.00685","any_repository_has_fulltext":true},"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","Department of Mechanical and Aerospace Engineering; University of Florida; Gainesville FL USA"],"raw_orcid":"https://orcid.org/0000-0001-9963-5361","affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"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","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"]},{"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","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"]},{"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","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"]},{"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":17.5592,"has_fulltext":true,"cited_by_count":139,"citation_normalized_percentile":{"value":0.99272349,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"28","issue":"3","first_page":"753","last_page":"758"},"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":0.982699990272522,"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":0.9703999757766724,"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":0.8305060863494873},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6550253033638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6151438355445862},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5784932971000671},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5727514624595642},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5639420747756958},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5437811613082886},{"id":"https://openalex.org/keywords/tracking-error","display_name":"Tracking error","score":0.5404679775238037},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5185375809669495},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5000514984130859},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.49880337715148926},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4922894537448883},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.48321568965911865},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.4648731052875519},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.4582667946815491},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3334779739379883},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2684272229671478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17977017164230347},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11362835764884949}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8305060863494873},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6550253033638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6151438355445862},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5784932971000671},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5727514624595642},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5639420747756958},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5437811613082886},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.5404679775238037},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5185375809669495},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5000514984130859},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.49880337715148926},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4922894537448883},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.48321568965911865},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.4648731052875519},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.4582667946815491},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3334779739379883},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2684272229671478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17977017164230347},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11362835764884949},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2015.2511658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2015.2511658","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:26863674","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26863674","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:arXiv.org:1506.00685","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1506.00685","pdf_url":"https://arxiv.org/pdf/1506.00685","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1506.00685","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1506.00685","pdf_url":"https://arxiv.org/pdf/1506.00685","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4297280941","display_name":null,"funder_award_id":"N00014-13-1-0151","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4309261220","display_name":"Adaptive dynamic programming for uncertain nonlinear systems through coupling of nonlinear analysis and data-based learning","funder_award_id":"1509516","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1977671496.pdf","grobid_xml":"https://content.openalex.org/works/W1977671496.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W13127292","https://openalex.org/W1517236425","https://openalex.org/W1574514837","https://openalex.org/W1793264465","https://openalex.org/W1914756871","https://openalex.org/W1968908471","https://openalex.org/W1977237536","https://openalex.org/W1983523797","https://openalex.org/W2002007892","https://openalex.org/W2003183707","https://openalex.org/W2013895638","https://openalex.org/W2048687352","https://openalex.org/W2052305027","https://openalex.org/W2052369206","https://openalex.org/W2085194340","https://openalex.org/W2086975818","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/W2121863487","https://openalex.org/W2150514620","https://openalex.org/W2150841368","https://openalex.org/W2157577161","https://openalex.org/W2184126965","https://openalex.org/W2476930474","https://openalex.org/W2484646121","https://openalex.org/W2798534591","https://openalex.org/W2963093491","https://openalex.org/W4214717370","https://openalex.org/W6686464875"],"related_works":["https://openalex.org/W4378651134","https://openalex.org/W4252684102","https://openalex.org/W2608983118","https://openalex.org/W2352307597","https://openalex.org/W1979633005","https://openalex.org/W2163724607","https://openalex.org/W3135403405","https://openalex.org/W2023227762","https://openalex.org/W1980092392","https://openalex.org/W2726582213"],"abstract_inverted_index":{"This":[0],"brief":[1],"paper":[2],"provides":[3],"an":[4],"approximate":[5],"online":[6],"adaptive":[7],"solution":[8],"to":[9,41,67],"the":[10,26,46,53,58,64,71,83,86],"infinite-horizon":[11],"optimal":[12,72],"tracking":[13],"problem":[14],"for":[15],"control-affine":[16],"continuous-time":[17],"nonlinear":[18],"systems":[19],"with":[20],"unknown":[21],"drift":[22],"dynamics.":[23],"To":[24],"relax":[25],"persistence":[27],"of":[28,52,57,63,70,85],"excitation":[29],"condition,":[30],"model-based":[31],"reinforcement":[32],"learning":[33],"is":[34],"implemented":[35],"using":[36],"a":[37,68],"concurrent-learning-based":[38],"system":[39],"identifier":[40],"simulate":[42],"experience":[43],"by":[44],"evaluating":[45],"Bellman":[47],"error":[48],"over":[49],"unexplored":[50],"areas":[51],"state":[54],"space.":[55],"Tracking":[56],"desired":[59],"trajectory":[60],"and":[61],"convergence":[62],"developed":[65,87],"policy":[66,73],"neighborhood":[69],"are":[74],"established":[75],"via":[76],"Lyapunov-based":[77],"stability":[78],"analysis.":[79],"Simulation":[80],"results":[81],"demonstrate":[82],"effectiveness":[84],"technique.":[88]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}