{"id":"https://openalex.org/W2822752092","doi":"https://doi.org/10.1146/annurev-control-053018-023825","title":"A Tour of Reinforcement Learning: The View from Continuous Control","display_name":"A Tour of Reinforcement Learning: The View from Continuous Control","publication_year":2018,"publication_date":"2018-12-14","ids":{"openalex":"https://openalex.org/W2822752092","doi":"https://doi.org/10.1146/annurev-control-053018-023825","mag":"2822752092"},"language":"en","primary_location":{"id":"doi:10.1146/annurev-control-053018-023825","is_oa":false,"landing_page_url":"https://doi.org/10.1146/annurev-control-053018-023825","pdf_url":null,"source":{"id":"https://openalex.org/S4210191328","display_name":"Annual Review of Control Robotics and Autonomous Systems","issn_l":"2573-5144","issn":["2573-5144"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320373","host_organization_name":"Annual Reviews","host_organization_lineage":["https://openalex.org/P4310320373"],"host_organization_lineage_names":["Annual Reviews"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annual Review of Control, Robotics, and Autonomous Systems","raw_type":"journal-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/A5012870568","display_name":"Benjamin Recht","orcid":"https://orcid.org/0000-0002-0293-593X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Benjamin Recht","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, California 94720, USA;"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, California 94720, USA;","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5012870568"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":43.3264,"has_fulltext":false,"cited_by_count":588,"citation_normalized_percentile":{"value":0.99819582,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"2","issue":"1","first_page":"253","last_page":"279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.991599977016449,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9814000129699707,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.8767801523208618},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.8243879079818726},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.7094993591308594},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6643329858779907},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.5606127977371216},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5340140461921692},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5107057690620422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45144128799438477},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4359542727470398},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.41724878549575806},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3587937355041504},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.21821022033691406},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17184951901435852}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8767801523208618},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.8243879079818726},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.7094993591308594},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6643329858779907},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.5606127977371216},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5340140461921692},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5107057690620422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45144128799438477},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4359542727470398},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.41724878549575806},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3587937355041504},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.21821022033691406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17184951901435852},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1146/annurev-control-053018-023825","is_oa":false,"landing_page_url":"https://doi.org/10.1146/annurev-control-053018-023825","pdf_url":null,"source":{"id":"https://openalex.org/S4210191328","display_name":"Annual Review of Control Robotics and Autonomous Systems","issn_l":"2573-5144","issn":["2573-5144"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320373","host_organization_name":"Annual Reviews","host_organization_lineage":["https://openalex.org/P4310320373"],"host_organization_lineage_names":["Annual Reviews"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annual Review of Control, Robotics, and Autonomous Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W16011919","https://openalex.org/W32403112","https://openalex.org/W178056938","https://openalex.org/W1505731132","https://openalex.org/W1564897360","https://openalex.org/W1569296262","https://openalex.org/W1576660662","https://openalex.org/W1616818660","https://openalex.org/W1970916399","https://openalex.org/W2003132288","https://openalex.org/W2006707952","https://openalex.org/W2006791053","https://openalex.org/W2006859604","https://openalex.org/W2009551863","https://openalex.org/W2011418219","https://openalex.org/W2032100464","https://openalex.org/W2053572490","https://openalex.org/W2055561145","https://openalex.org/W2072931156","https://openalex.org/W2087617385","https://openalex.org/W2098432798","https://openalex.org/W2107726111","https://openalex.org/W2109008048","https://openalex.org/W2113789941","https://openalex.org/W2117897510","https://openalex.org/W2119717200","https://openalex.org/W2124289529","https://openalex.org/W2136504847","https://openalex.org/W2144771820","https://openalex.org/W2145339207","https://openalex.org/W2148965922","https://openalex.org/W2149479912","https://openalex.org/W2158091072","https://openalex.org/W2158782408","https://openalex.org/W2162725061","https://openalex.org/W2165418472","https://openalex.org/W2168359464","https://openalex.org/W2168405694","https://openalex.org/W2257979135","https://openalex.org/W2327088997","https://openalex.org/W2334782222","https://openalex.org/W2400458653","https://openalex.org/W2411577903","https://openalex.org/W2559655401","https://openalex.org/W2596585349","https://openalex.org/W2604272474","https://openalex.org/W2604738573","https://openalex.org/W2607662938","https://openalex.org/W2612690371","https://openalex.org/W2754517384","https://openalex.org/W2782694813","https://openalex.org/W2783297289","https://openalex.org/W2808980893","https://openalex.org/W2913668833","https://openalex.org/W2914238450","https://openalex.org/W2914933231","https://openalex.org/W2963683522","https://openalex.org/W2963898834","https://openalex.org/W3041202696","https://openalex.org/W4214717370","https://openalex.org/W4233696721","https://openalex.org/W4239207475"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W4381094582","https://openalex.org/W1978893398","https://openalex.org/W1977906818","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1522139108","https://openalex.org/W2353528968","https://openalex.org/W2203843426","https://openalex.org/W2049369111"],"abstract_inverted_index":{"This":[0],"article":[1,136],"surveys":[2],"reinforcement":[3,30,132,164],"learning":[4,31,78,133,148,165],"from":[5,77,163],"the":[6,21,42,54,63,108,120,127,144],"perspective":[7],"of":[8,29,45,53,86,107,124,129,141,143],"optimization":[9],"and":[10,25,65,80,89,117,122,126,152,157,160,166],"control,":[11],"with":[12,59,138,155],"a":[13,50,139],"focus":[14],"on":[15],"continuous":[16],"control":[17,81,167],"applications.":[18],"It":[19,71],"reviews":[20],"general":[22],"formulation,":[23],"terminology,":[24],"typical":[26],"experimental":[27,97],"implementations":[28],"as":[32,34],"well":[33],"competing":[35],"solution":[36],"paradigms.":[37],"In":[38,99,114],"order":[39],"to":[40,95,171],"compare":[41],"relative":[43],"merits":[44],"various":[46],"techniques,":[47],"it":[48],"presents":[49],"case":[51],"study":[52],"linear":[55],"quadratic":[56],"regulator":[57],"(LQR)":[58],"unknown":[60],"dynamics,":[61],"perhaps":[62],"simplest":[64],"best-studied":[66],"problem":[67],"in":[68,111,131,146],"optimal":[69],"control.":[70],"also":[72],"describes":[73],"how":[74,161],"merging":[75],"techniques":[76],"theory":[79,116],"can":[82],"provide":[83],"nonasymptotic":[84],"characterizations":[85,93],"LQR":[87,112],"performance":[88],"shows":[90],"that":[91,150],"these":[92,173],"tend":[94],"match":[96],"behavior.":[98],"turn,":[100],"when":[101],"revisiting":[102],"more":[103],"complex":[104,156],"applications,":[105],"many":[106],"observed":[109],"phenomena":[110],"persist.":[113],"particular,":[115],"experiment":[118],"demonstrate":[119],"role":[121],"importance":[123],"models":[125],"cost":[128],"generality":[130],"algorithms.":[134],"The":[135],"concludes":[137],"discussion":[140],"some":[142],"challenges":[145],"designing":[147],"systems":[149],"safely":[151],"reliably":[153],"interact":[154],"uncertain":[158],"environments":[159],"tools":[162],"might":[168],"be":[169],"combined":[170],"approach":[172],"challenges.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":22},{"year":2025,"cited_by_count":69},{"year":2024,"cited_by_count":66},{"year":2023,"cited_by_count":97},{"year":2022,"cited_by_count":78},{"year":2021,"cited_by_count":109},{"year":2020,"cited_by_count":111},{"year":2019,"cited_by_count":36}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}
