{"id":"https://openalex.org/W2127251115","doi":"https://doi.org/10.1109/adprl.2009.4927541","title":"Learning continuous-action control policies","display_name":"Learning continuous-action control policies","publication_year":2009,"publication_date":"2009-03-01","ids":{"openalex":"https://openalex.org/W2127251115","doi":"https://doi.org/10.1109/adprl.2009.4927541","mag":"2127251115"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2009.4927541","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927541","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","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/A5031267271","display_name":"Jason Pazis","orcid":null},"institutions":[{"id":"https://openalex.org/I55741626","display_name":"Technical University of Crete","ror":"https://ror.org/03f8bz564","country_code":"GR","type":"education","lineage":["https://openalex.org/I55741626"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Jason Pazis","raw_affiliation_strings":["Department of Electronic and Computer Engineering, Technical University of Crete, Crete, Greece","Department of Electronic & Computer Engineering; Technical University of Crete; Chania Greece"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, Technical University of Crete, Crete, Greece","institution_ids":["https://openalex.org/I55741626"]},{"raw_affiliation_string":"Department of Electronic & Computer Engineering; Technical University of Crete; Chania Greece","institution_ids":["https://openalex.org/I55741626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084693234","display_name":"Michail G. Lagoudakis","orcid":"https://orcid.org/0000-0003-2803-3755"},"institutions":[{"id":"https://openalex.org/I55741626","display_name":"Technical University of Crete","ror":"https://ror.org/03f8bz564","country_code":"GR","type":"education","lineage":["https://openalex.org/I55741626"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Michail G. Lagoudakis","raw_affiliation_strings":["Department of Electronic and Computer Engineering, Technical University of Crete, Crete, Greece","Department of Electronic & Computer Engineering; Technical University of Crete; Chania Greece"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, Technical University of Crete, Crete, Greece","institution_ids":["https://openalex.org/I55741626"]},{"raw_affiliation_string":"Department of Electronic & Computer Engineering; Technical University of Crete; Chania Greece","institution_ids":["https://openalex.org/I55741626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031267271"],"corresponding_institution_ids":["https://openalex.org/I55741626"],"apc_list":null,"apc_paid":null,"fwci":0.8724,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80785084,"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":"169","last_page":"176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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":0.9986000061035156,"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/T10524","display_name":"Traffic control and management","score":0.9937000274658203,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.983299970626831,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8225841522216797},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.6881340742111206},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6398024559020996},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.606298565864563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5763901472091675},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.513715386390686},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.48261818289756775},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.4378455877304077},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.37651610374450684},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36902034282684326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3645312190055847},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33978527784347534},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32243868708610535},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.32160520553588867},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.08341774344444275}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8225841522216797},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.6881340742111206},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6398024559020996},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.606298565864563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5763901472091675},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.513715386390686},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.48261818289756775},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.4378455877304077},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.37651610374450684},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36902034282684326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3645312190055847},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33978527784347534},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32243868708610535},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.32160520553588867},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08341774344444275},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"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":1,"locations":[{"id":"doi:10.1109/adprl.2009.4927541","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927541","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W206508158","https://openalex.org/W1499408472","https://openalex.org/W1508482627","https://openalex.org/W1550698229","https://openalex.org/W1923769013","https://openalex.org/W2035808435","https://openalex.org/W2068052921","https://openalex.org/W2109102709","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2135396350","https://openalex.org/W2145805610","https://openalex.org/W2154549708","https://openalex.org/W2160279936","https://openalex.org/W2569741183","https://openalex.org/W3011120880","https://openalex.org/W4214717370","https://openalex.org/W4242606736","https://openalex.org/W4245296547","https://openalex.org/W4285719527","https://openalex.org/W6630505628","https://openalex.org/W6675894441","https://openalex.org/W6677737365","https://openalex.org/W6681451320","https://openalex.org/W6683508713"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W4225571923","https://openalex.org/W2166117066","https://openalex.org/W3212257828","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W4376605461","https://openalex.org/W4400868993"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,116,119,130],"for":[2,20,74,118],"control":[3],"in":[4,11,45,54,88],"stochastic":[5],"processes":[6],"has":[7],"received":[8],"significant":[9],"attention":[10],"the":[12,48,60,89,92,150],"last":[13],"few":[14],"years.":[15],"Several":[16],"data-efficient":[17],"methods,":[18],"even":[19],"continuous":[21,39,93,102,151],"state":[22],"spaces,":[23],"have":[24],"been":[25],"proposed,":[26],"however":[27],"most":[28,49],"of":[29,59,91],"them":[30],"assume":[31],"a":[32,66],"small":[33],"and":[34,108,135,139,142,147,155,158],"discrete":[35],"action":[36,40,61,72,94,103],"space.":[37,62],"While":[38],"spaces":[41],"are":[42,144],"quite":[43],"common":[44,50],"real-world":[46],"problems,":[47],"approach":[51,98,123],"still":[52],"employed":[53],"practice":[55],"is":[56,124],"coarse":[57],"discretization":[58],"This":[63],"paper":[64],"presents":[65],"novel,":[67],"computationally-efficient":[68],"method,":[69],"called":[70],"adaptive":[71,83],"modification,":[73],"realizing":[75],"continuous-action":[76,120],"policies,":[77],"using":[78],"binary":[79],"decisions":[80],"corresponding":[81],"to":[82,105],"increment":[84],"or":[85],"decrement":[86],"changes":[87],"values":[90],"variables.":[95],"The":[96],"proposed":[97],"essentially":[99],"approximates":[100],"any":[101,113],"space":[104],"arbitrary":[106],"resolution":[107],"can":[109],"be":[110],"combined":[111],"with":[112,126],"discrete-action":[114],"reinforcement":[115,129],"algorithm":[117],"policies.":[121],"Our":[122],"coupled":[125],"three":[127],"well-known":[128],"algorithms":[131],"(Q-learning,":[132],"fitted":[133],"Q-iteration,":[134],"least-squares":[136],"policy":[137],"iteration)":[138],"its":[140],"use":[141],"properties":[143],"thoroughly":[145],"investigated":[146],"demonstrated":[148],"on":[149],"state-action":[152],"inverted":[153],"pendulum":[154],"bicycle":[156],"balancing":[157],"riding":[159],"domains.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}