{"id":"https://openalex.org/W2772589676","doi":"https://doi.org/10.1109/tnnls.2017.2773458","title":"Optimal and Autonomous Control Using Reinforcement Learning: A Survey","display_name":"Optimal and Autonomous Control Using Reinforcement Learning: A Survey","publication_year":2017,"publication_date":"2017-12-07","ids":{"openalex":"https://openalex.org/W2772589676","doi":"https://doi.org/10.1109/tnnls.2017.2773458","mag":"2772589676","pmid":"https://pubmed.ncbi.nlm.nih.gov/29771662"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2017.2773458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2017.2773458","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":["crossref","pubmed"],"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/A5089224471","display_name":"Bahare Kiumarsi","orcid":"https://orcid.org/0000-0002-9701-8375"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bahare Kiumarsi","raw_affiliation_strings":["UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-9701-8375","affiliations":[{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040301558","display_name":"Kyriakos G. Vamvoudakis","orcid":"https://orcid.org/0000-0003-1978-4848"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyriakos G. Vamvoudakis","raw_affiliation_strings":["Kevin T. Crofton Department of Aerospace and Ocean Engineering, Virginia Tech, Blacksburg, VA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1978-4848","affiliations":[{"raw_affiliation_string":"Kevin T. Crofton Department of Aerospace and Ocean Engineering, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063118155","display_name":"Hamidreza Modares","orcid":"https://orcid.org/0000-0003-0800-5140"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamidreza Modares","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USA"],"raw_orcid":"https://orcid.org/0000-0003-0800-5140","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USA","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-4074-1615","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":44.2046,"has_fulltext":false,"cited_by_count":902,"citation_normalized_percentile":{"value":0.99920184,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"29","issue":"6","first_page":"2042","last_page":"2062"},"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":0.992900013923645,"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":0.9746999740600586,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7073847651481628},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5291778445243835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4521428048610687},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4247528612613678},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.356731116771698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33077701926231384},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.13081711530685425}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7073847651481628},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5291778445243835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4521428048610687},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4247528612613678},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.356731116771698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33077701926231384},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13081711530685425}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2017.2773458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2017.2773458","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:29771662","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29771662","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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":127,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W130083205","https://openalex.org/W173093232","https://openalex.org/W234738007","https://openalex.org/W601351931","https://openalex.org/W644523282","https://openalex.org/W648594167","https://openalex.org/W1503398984","https://openalex.org/W1513689897","https://openalex.org/W1567906773","https://openalex.org/W1614417283","https://openalex.org/W1616818660","https://openalex.org/W1708020878","https://openalex.org/W1771410628","https://openalex.org/W1793264465","https://openalex.org/W1891098503","https://openalex.org/W1901616594","https://openalex.org/W1907796993","https://openalex.org/W1914756871","https://openalex.org/W1968315580","https://openalex.org/W1968908471","https://openalex.org/W1969959431","https://openalex.org/W1972243698","https://openalex.org/W1972809999","https://openalex.org/W1976956127","https://openalex.org/W1983523797","https://openalex.org/W1990654347","https://openalex.org/W2003807250","https://openalex.org/W2005229381","https://openalex.org/W2005437559","https://openalex.org/W2007641405","https://openalex.org/W2012451615","https://openalex.org/W2013895638","https://openalex.org/W2024303516","https://openalex.org/W2028145673","https://openalex.org/W2031109139","https://openalex.org/W2032631296","https://openalex.org/W2037751122","https://openalex.org/W2041740097","https://openalex.org/W2042106612","https://openalex.org/W2046972933","https://openalex.org/W2054117986","https://openalex.org/W2059147929","https://openalex.org/W2060914855","https://openalex.org/W2063640990","https://openalex.org/W2066119971","https://openalex.org/W2073601023","https://openalex.org/W2073990179","https://openalex.org/W2081514674","https://openalex.org/W2085194340","https://openalex.org/W2086975818","https://openalex.org/W2090167557","https://openalex.org/W2091565802","https://openalex.org/W2093831009","https://openalex.org/W2095095223","https://openalex.org/W2097440896","https://openalex.org/W2104843094","https://openalex.org/W2107674817","https://openalex.org/W2108286682","https://openalex.org/W2108383324","https://openalex.org/W2109640889","https://openalex.org/W2111034649","https://openalex.org/W2113501460","https://openalex.org/W2116165953","https://openalex.org/W2118819183","https://openalex.org/W2123694750","https://openalex.org/W2129422716","https://openalex.org/W2134491302","https://openalex.org/W2136632951","https://openalex.org/W2138314326","https://openalex.org/W2139416664","https://openalex.org/W2148439597","https://openalex.org/W2151908411","https://openalex.org/W2151966330","https://openalex.org/W2155007355","https://openalex.org/W2156828234","https://openalex.org/W2158625202","https://openalex.org/W2165726932","https://openalex.org/W2171033594","https://openalex.org/W2214884926","https://openalex.org/W2282722544","https://openalex.org/W2287454828","https://openalex.org/W2288654255","https://openalex.org/W2318384021","https://openalex.org/W2329796913","https://openalex.org/W2332438227","https://openalex.org/W2332672415","https://openalex.org/W2400458653","https://openalex.org/W2473265833","https://openalex.org/W2476930474","https://openalex.org/W2478654971","https://openalex.org/W2483158547","https://openalex.org/W2484646121","https://openalex.org/W2484957131","https://openalex.org/W2487144912","https://openalex.org/W2498739565","https://openalex.org/W2504768348","https://openalex.org/W2509783950","https://openalex.org/W2541921436","https://openalex.org/W2546089848","https://openalex.org/W2549392634","https://openalex.org/W2565845380","https://openalex.org/W2569414656","https://openalex.org/W2569832271","https://openalex.org/W2570494446","https://openalex.org/W2570665277","https://openalex.org/W2580629550","https://openalex.org/W2586680856","https://openalex.org/W2594639291","https://openalex.org/W2961703895","https://openalex.org/W2963382853","https://openalex.org/W2963393268","https://openalex.org/W2963864862","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W3135791089","https://openalex.org/W3213472335","https://openalex.org/W4214717370","https://openalex.org/W4231017914","https://openalex.org/W4248048201","https://openalex.org/W6678264118","https://openalex.org/W6680519301","https://openalex.org/W6682188171","https://openalex.org/W6682849425","https://openalex.org/W6775686901","https://openalex.org/W6804409665","https://openalex.org/W6995487115"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W2089013912"],"abstract_inverted_index":{"This":[0],"paper":[1],"reviews":[2],"the":[3,7,46,60,67],"current":[4],"state":[5],"of":[6,21,88],"art":[8],"on":[9],"reinforcement":[10],"learning":[11],"(RL)-based":[12],"feedback":[13],"control":[14,33,50],"solutions":[15,28],"to":[16,29,48],"optimal":[17,31,49],"regulation":[18],"and":[19,23,32,51,55,66,77,94],"tracking":[20],"single":[22],"multiagent":[24],"systems.":[25,96],"Existing":[26],"RL":[27,43,69,90],"both":[30,92],"problems,":[34],"as":[35,37,71],"well":[36],"graphical":[38],"games,":[39],"will":[40],"be":[41],"reviewed.":[42],"methods":[44],"learn":[45],"solution":[47],"game":[52],"problems":[53],"online":[54],"using":[56],"measured":[57],"data":[58],"along":[59],"system":[61],"trajectories.":[62],"We":[63],"discuss":[64,84],"Q-learning":[65],"integral":[68],"algorithm":[70],"core":[72],"algorithms":[73],"for":[74,91],"discrete-time":[75],"(DT)":[76],"continuous-time":[78],"(CT)":[79],"systems,":[80],"respectively.":[81],"Moreover,":[82],"we":[83,98],"a":[85],"new":[86],"direction":[87],"off-policy":[89],"CT":[93],"DT":[95],"Finally,":[97],"review":[99],"several":[100],"applications.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":79},{"year":2025,"cited_by_count":112},{"year":2024,"cited_by_count":121},{"year":2023,"cited_by_count":147},{"year":2022,"cited_by_count":113},{"year":2021,"cited_by_count":128},{"year":2020,"cited_by_count":93},{"year":2019,"cited_by_count":81},{"year":2018,"cited_by_count":26},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2025-10-10T00:00:00"}