{"id":"https://openalex.org/W1966170972","doi":"https://doi.org/10.1109/iros.2013.6696506","title":"Locally weighted least squares policy iteration for model-free learning in uncertain environments","display_name":"Locally weighted least squares policy iteration for model-free learning in uncertain environments","publication_year":2013,"publication_date":"2013-11-01","ids":{"openalex":"https://openalex.org/W1966170972","doi":"https://doi.org/10.1109/iros.2013.6696506","mag":"1966170972"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2013.6696506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE/RSJ International Conference on Intelligent Robots and Systems","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/A5050881123","display_name":"Matthew Howard","orcid":"https://orcid.org/0000-0003-2534-4865"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matthew Howard","raw_affiliation_strings":["Dept. Informatics, Kings College London, UK","Dept. Inf., Kings Coll. London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Informatics, Kings College London, UK","institution_ids":["https://openalex.org/I183935753"]},{"raw_affiliation_string":"Dept. Inf., Kings Coll. London, London, UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040633710","display_name":"Yoshihiko Nakamura","orcid":"https://orcid.org/0000-0001-7162-5102"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Nakamura","raw_affiliation_strings":["Dept. Mechano-informatics, University of Tokyo, Japan","Dept. Mechano-Inf., Univ. of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Mechano-informatics, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Dept. Mechano-Inf., Univ. of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"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":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1223","last_page":"1229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9944999814033508,"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":0.9944999814033508,"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":0.9919000267982483,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9911999702453613,"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/computer-science","display_name":"Computer science","score":0.6099718809127808},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5553589463233948},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5508496761322021},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.548467755317688},{"id":"https://openalex.org/keywords/least-squares-function-approximation","display_name":"Least-squares function approximation","score":0.5102505683898926},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.49802446365356445},{"id":"https://openalex.org/keywords/swing","display_name":"Swing","score":0.4890064001083374},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4887378215789795},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4845820665359497},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4716690480709076},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4485161602497101},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4243672788143158},{"id":"https://openalex.org/keywords/system-dynamics","display_name":"System dynamics","score":0.4228243827819824},{"id":"https://openalex.org/keywords/pendulum","display_name":"Pendulum","score":0.4142674207687378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39016789197921753},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2903742790222168},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2407536506652832},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10855185985565186},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08219829201698303}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6099718809127808},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5553589463233948},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5508496761322021},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.548467755317688},{"id":"https://openalex.org/C9936470","wikidata":"https://www.wikidata.org/wiki/Q6510405","display_name":"Least-squares function approximation","level":3,"score":0.5102505683898926},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.49802446365356445},{"id":"https://openalex.org/C65655974","wikidata":"https://www.wikidata.org/wiki/Q14867674","display_name":"Swing","level":2,"score":0.4890064001083374},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4887378215789795},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4845820665359497},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4716690480709076},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4485161602497101},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4243672788143158},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.4228243827819824},{"id":"https://openalex.org/C110639684","wikidata":"https://www.wikidata.org/wiki/Q20702","display_name":"Pendulum","level":2,"score":0.4142674207687378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39016789197921753},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2903742790222168},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2407536506652832},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10855185985565186},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08219829201698303},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iros.2013.6696506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.700.1351","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.700.1351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.inf.kcl.ac.uk/staff/mhoward/pdf/Howard2013b.pdf","raw_type":"text"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/c0c2b684-6a3d-43b2-aa10-00b81db4cb5b","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=84893734760&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Howard, M & Nakamura, Y 2013, Locally weighted least squares policy iteration for model-free learning in uncertain environments. in 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 1223-1229, 2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013, Tokyo, United Kingdom, 3/11/2013. https://doi.org/10.1109/IROS.2013.6696506","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W195033972","https://openalex.org/W658381347","https://openalex.org/W1603365166","https://openalex.org/W1925816294","https://openalex.org/W1976606095","https://openalex.org/W2017977879","https://openalex.org/W2025752438","https://openalex.org/W2052117683","https://openalex.org/W2072931156","https://openalex.org/W2113501460","https://openalex.org/W2121863487","https://openalex.org/W2124144580","https://openalex.org/W2130094217","https://openalex.org/W2132351269","https://openalex.org/W2167804690","https://openalex.org/W2233496237","https://openalex.org/W3005581722","https://openalex.org/W4214717370","https://openalex.org/W4242606736","https://openalex.org/W4253365321","https://openalex.org/W4285719527","https://openalex.org/W6607786297","https://openalex.org/W6640290305","https://openalex.org/W6678573530","https://openalex.org/W6689690058"],"related_works":["https://openalex.org/W4308702637","https://openalex.org/W4289355352","https://openalex.org/W2149418961","https://openalex.org/W1501190258","https://openalex.org/W2134042548","https://openalex.org/W2473364827","https://openalex.org/W2332399992","https://openalex.org/W1963273549","https://openalex.org/W4240668504","https://openalex.org/W2011233848"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"Locally":[3],"Weighted":[4],"Least":[5,36],"Squares":[6,37],"Policy":[7],"Iteration":[8],"for":[9,79],"learning":[10,77],"approximate":[11],"optimal":[12],"control":[13,62,81],"in":[14,35,56],"settings":[15],"where":[16],"models":[17,67],"of":[18,68],"the":[19,41,69],"dynamics":[20],"and":[21,89],"cost":[22],"function":[23],"are":[24,74],"either":[25],"unavailable":[26],"or":[27],"hard":[28],"to":[29,46,58],"obtain.":[30],"Building":[31],"on":[32,65],"recent":[33],"advances":[34],"Temporal":[38],"Difference":[39],"Learning,":[40],"proposed":[42],"approach":[43],"is":[44],"able":[45],"learn":[47],"from":[48,51],"data":[49],"collected":[50],"interactions":[52],"with":[53],"a":[54,60,90],"system,":[55],"order":[57],"build":[59],"global":[61],"policy":[63],"based":[64],"localised":[66],"state-action":[70],"value":[71],"function.":[72],"Evaluations":[73],"reported":[75],"characterising":[76],"performance":[78],"non-linear":[80],"problems":[82],"including":[83],"an":[84],"under-powered":[85],"pendulum":[86],"swing-up":[87],"task,":[88],"robotic":[91],"door-opening":[92],"problem":[93],"under":[94],"different":[95],"dynamical":[96],"conditions.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}