{"id":"https://openalex.org/W2060129082","doi":"https://doi.org/10.1109/cdc.2011.6161108","title":"Reinforcement learning with reference tracking control in continuous state spaces","display_name":"Reinforcement learning with reference tracking control in continuous state spaces","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W2060129082","doi":"https://doi.org/10.1109/cdc.2011.6161108","mag":"2060129082"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2011.6161108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2011.6161108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Conference on Decision and Control and European Control Conference","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/A5112252768","display_name":"Joseph Hall","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joseph Hall","raw_affiliation_strings":["Control Group, Department of Engineering, University of Cambridge, UK","Control Group, Department of Engineering, Cambridge University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Control Group, Department of Engineering, University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Control Group, Department of Engineering, Cambridge University, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108711177","display_name":"Carl Edward Rasmussen","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Carl Edward Rasmussen","raw_affiliation_strings":["Machine Learning Group, Computational and Biological Learning Laboratory, Department of Engineering, University of Cambridge, UK","Machine Learning Group, Computational and Biological Learning Laboratory, Department of Engineering, Cambridge University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Group, Computational and Biological Learning Laboratory, Department of Engineering, University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Machine Learning Group, Computational and Biological Learning Laboratory, Department of Engineering, Cambridge University, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046769542","display_name":"J.M. Maciejowski","orcid":"https://orcid.org/0000-0001-8281-8364"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jan Maciejowski","raw_affiliation_strings":["Control Group, Department of Engineering, University of Cambridge, UK","Control Group, Department of Engineering, Cambridge University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Control Group, Department of Engineering, University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Control Group, Department of Engineering, Cambridge University, UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6019","last_page":"6024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.9987999796867371,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9983000159263611,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9945999979972839,"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":0.825546383857727},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.7803525924682617},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6212337613105774},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.6199115514755249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.587016761302948},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5257038474082947},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5248422622680664},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4819200336933136},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46397241950035095},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4585646390914917},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4533859193325043},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.42836862802505493},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4017130136489868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38331595063209534},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3164159059524536},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23097294569015503},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.186905175447464}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.825546383857727},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.7803525924682617},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6212337613105774},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.6199115514755249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.587016761302948},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5257038474082947},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5248422622680664},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4819200336933136},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46397241950035095},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4585646390914917},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4533859193325043},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.42836862802505493},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4017130136489868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38331595063209534},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3164159059524536},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23097294569015503},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.186905175447464},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cdc.2011.6161108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2011.6161108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Conference on Decision and Control and European Control Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.3090","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.3090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-control.eng.cam.ac.uk/Homepage//papers/cued_control_1139.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.363.7051","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.363.7051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mlg.eng.cam.ac.uk/pub/pdf/HalRasMac11.pdf","raw_type":"text"},{"id":"pmh:oai:generic.eprints.org:443845","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/443845/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1663973292","https://openalex.org/W1746819321","https://openalex.org/W1797739565","https://openalex.org/W2009086942","https://openalex.org/W2014617596","https://openalex.org/W2113501460","https://openalex.org/W2121863487","https://openalex.org/W2123246446","https://openalex.org/W2146851580","https://openalex.org/W2179284380","https://openalex.org/W3011120880","https://openalex.org/W4211049957","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W962423920","https://openalex.org/W2387968248","https://openalex.org/W2775112436","https://openalex.org/W3326829","https://openalex.org/W2350013143","https://openalex.org/W3046172785","https://openalex.org/W2385948153","https://openalex.org/W2353814909","https://openalex.org/W2147778705","https://openalex.org/W2598699656"],"abstract_inverted_index":{"The":[0],"contribution":[1],"described":[2],"in":[3,50],"this":[4,54],"paper":[5],"is":[6],"an":[7],"algorithm":[8,55,110],"for":[9],"learning":[10,32],"nonlinear,":[11],"reference":[12,72],"tracking,":[13],"control":[14,45,126],"policies":[15],"given":[16],"no":[17],"prior":[18],"knowledge":[19],"of":[20,38,53,63,71,102],"the":[21,28,31,36,51,69,88,93,106,109,116],"dynamical":[22],"system":[23,29],"and":[24,43],"limited":[25],"interaction":[26,104],"with":[27,105],"through":[30],"process.":[33],"Concepts":[34],"from":[35,92],"field":[37],"reinforcement":[39],"learning,":[40],"Bayesian":[41],"statistics":[42],"classical":[44],"have":[46],"been":[47],"brought":[48],"together":[49],"formulation":[52],"which":[56],"can":[57],"be":[58],"viewed":[59],"as":[60],"a":[61,75],"form":[62],"indirect":[64],"self":[65],"tuning":[66],"regulator.":[67],"On":[68],"task":[70],"tracking":[73],"using":[74,98],"simulated":[76,117],"inverted":[77],"pendulum":[78,119],"it":[79],"was":[80,111],"shown":[81,112],"to":[82,113,123],"yield":[83],"generally":[84],"improved":[85],"performance":[86],"on":[87,115],"best":[89],"controller":[90],"derived":[91],"standard":[94],"linear":[95],"quadratic":[96],"method":[97],"only":[99],"30":[100],"s":[101],"total":[103],"system.":[107],"Finally,":[108],"work":[114],"double":[118],"proving":[120],"its":[121],"ability":[122],"solve":[124],"nontrivial":[125],"tasks.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
