{"id":"https://openalex.org/W1979638690","doi":"https://doi.org/10.1109/cdc.2012.6426427","title":"Model learning actor-critic algorithms: Performance evaluation in a motion control task","display_name":"Model learning actor-critic algorithms: Performance evaluation in a motion control task","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W1979638690","doi":"https://doi.org/10.1109/cdc.2012.6426427","mag":"1979638690"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2012.6426427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2012.6426427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 51st IEEE Conference on Decision and Control (CDC)","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/A5028459687","display_name":"I. Grondman","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ivo Grondman","raw_affiliation_strings":["Delft Center for Systems and Contro, University of Technology, Netherlands","Delft Center for Systems and Control of Delft University of Technology, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Contro, University of Technology, Netherlands","institution_ids":[]},{"raw_affiliation_string":"Delft Center for Systems and Control of Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058935509","display_name":"Lucian Bu\u015foniu","orcid":"https://orcid.org/0000-0001-8017-1296"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Lucian Busoniu","raw_affiliation_strings":["Delft Center for Systems and Contro, University of Technology, Netherlands","Department of Automation, Technical University of Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Contro, University of Technology, Netherlands","institution_ids":[]},{"raw_affiliation_string":"Department of Automation, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084264842","display_name":"Robert Babu\u0161ka","orcid":"https://orcid.org/0000-0001-9578-8598"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Robert Babuska","raw_affiliation_strings":["Delft Center for Systems and Control of Delft University of Technology, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control of Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9966999888420105,"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":0.9966999888420105,"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":0.9776999950408936,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9390000104904175,"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":0.7561990022659302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6601332426071167},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6063029170036316},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5644994378089905},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.5096039772033691},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4592115879058838},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.45002633333206177},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.441012978553772},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4379558861255646},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.42902493476867676},{"id":"https://openalex.org/keywords/radial-basis-function","display_name":"Radial basis function","score":0.4219474494457245},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.41822463274002075},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4155175983905792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4140598773956299},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3645329773426056},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3313973546028137},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.27450066804885864},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.24801695346832275},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21625405550003052},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07868430018424988}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7561990022659302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6601332426071167},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6063029170036316},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5644994378089905},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.5096039772033691},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4592115879058838},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.45002633333206177},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.441012978553772},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4379558861255646},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.42902493476867676},{"id":"https://openalex.org/C98856871","wikidata":"https://www.wikidata.org/wiki/Q1588488","display_name":"Radial basis function","level":3,"score":0.4219474494457245},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.41822463274002075},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4155175983905792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4140598773956299},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3645329773426056},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3313973546028137},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27450066804885864},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24801695346832275},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21625405550003052},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07868430018424988},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2012.6426427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2012.6426427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 51st IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1626155273","https://openalex.org/W1966086707","https://openalex.org/W2009303086","https://openalex.org/W2048226872","https://openalex.org/W2054940200","https://openalex.org/W2091565802","https://openalex.org/W2094387729","https://openalex.org/W2111779831","https://openalex.org/W2120968583","https://openalex.org/W2121863487","https://openalex.org/W4214717370","https://openalex.org/W4245108548"],"related_works":["https://openalex.org/W4289355352","https://openalex.org/W3036075344","https://openalex.org/W2066360887","https://openalex.org/W2134042548","https://openalex.org/W2110098766","https://openalex.org/W2473364827","https://openalex.org/W1589342126","https://openalex.org/W2332399992","https://openalex.org/W3164513830","https://openalex.org/W2058895704"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,54,79,93,166],"(RL)":[2],"control":[3,15,30,124,173],"provides":[4],"a":[5,58,120],"means":[6],"to":[7,48,76,96],"deal":[8],"with":[9,14,32,102,131],"uncertainty":[10],"and":[11,35,143,167],"nonlinearity":[12],"associated":[13],"tasks":[16],"in":[17,86,136,144],"an":[18,103,113],"optimal":[19],"way.":[20],"The":[21,126,151],"class":[22],"of":[23,112,119,138,146],"actor-critic":[24,42,94,156],"RL":[25,157],"algorithms":[26,43,95],"proved":[27],"useful":[28],"for":[29,100],"systems":[31],"continuous":[33],"state":[34],"input":[36],"variables.":[37],"In":[38],"the":[39,52,53,72,77,82,91,110,139,147,159],"literature,":[40],"model-based":[41],"have":[44],"recently":[45],"been":[46,68],"introduced":[47],"considerably":[49],"speed":[50],"up":[51],"by":[55],"constructing":[56],"online":[57],"model":[59,78,92],"through":[60,116],"local":[61],"linear":[62],"regression":[63],"(LLR).":[64],"It":[65],"has":[66],"not":[67],"analyzed":[69],"yet":[70],"whether":[71],"speed-up":[73],"is":[74,129],"due":[75],"structure":[80],"or":[81,169],"LLR":[83,127],"approximator.":[84,106],"Therefore,":[85],"this":[87],"paper":[88],"we":[89,108],"generalize":[90],"make":[97],"them":[98],"suitable":[99],"use":[101],"arbitrary":[104],"function":[105],"Furthermore,":[107],"present":[109],"results":[111,152],"extensive":[114],"analysis":[115],"numerical":[117],"simulations":[118],"typical":[121],"nonlinear":[122],"motion":[123],"problem.":[125],"approximator":[128],"compared":[130],"radial":[132],"basis":[133],"functions":[134],"(RBFs)":[135],"terms":[137,145],"initial":[140,165],"convergence":[141],"rate":[142],"final":[148,172],"performance":[149],"obtained.":[150],"show":[153],"that":[154],"LLR-based":[155],"outperforms":[158],"RBF":[160],"counterpart:":[161],"it":[162],"gives":[163],"quick":[164],"comparable":[168],"even":[170],"superior":[171],"performance.":[174]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}