{"id":"https://openalex.org/W2084202551","doi":"https://doi.org/10.1109/acc.2010.5530856","title":"Online least-squares policy iteration for reinforcement learning control","display_name":"Online least-squares policy iteration for reinforcement learning control","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2084202551","doi":"https://doi.org/10.1109/acc.2010.5530856","mag":"2084202551"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2010.5530856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2010.5530856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 American Control Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbi.uliege.be/handle/2268/65794","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058935509","display_name":"Lucian Bu\u015foniu","orcid":"https://orcid.org/0000-0001-8017-1296"},"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":true,"raw_author_name":"L Busoniu","raw_affiliation_strings":["Delft Center of Systems and Control, Delft University of Technnology, Netherlands","Delft Center for Systems and Control of Delft University of Technology, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft Center of Systems and Control, Delft University of Technnology, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"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/A5077011518","display_name":"Damien Ernst","orcid":"https://orcid.org/0000-0002-3035-8260"},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"D Ernst","raw_affiliation_strings":["Systems and Modeling Unit of University of Li\u00e8ge, Belgium","Belgian FNRS, Belgium"],"affiliations":[{"raw_affiliation_string":"Systems and Modeling Unit of University of Li\u00e8ge, Belgium","institution_ids":["https://openalex.org/I157674565"]},{"raw_affiliation_string":"Belgian FNRS, Belgium","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026547410","display_name":"Bart De Schutter","orcid":"https://orcid.org/0000-0001-9867-6196"},"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":"B De Schutter","raw_affiliation_strings":["Delft Center of Systems and Control, Delft University of Technnology, Netherlands","Delft Center for Systems and Control of Delft University of Technology, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft Center of Systems and Control, Delft University of Technnology, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Center for Systems and Control of Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"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":"R Babuska","raw_affiliation_strings":["Delft Center of Systems and Control, Delft University of Technnology, Netherlands","Delft Center for Systems and Control of Delft University of Technology, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft Center of Systems and Control, Delft University of Technnology, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"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":4,"corresponding_author_ids":["https://openalex.org/A5058935509"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":10.825,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.9832712,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"486","last_page":"491"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9980999827384949,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.994700014591217,"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":0.8278084993362427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6503314971923828},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5392874479293823},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5179589986801147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4521976113319397},{"id":"https://openalex.org/keywords/least-squares-function-approximation","display_name":"Least-squares function approximation","score":0.440122127532959},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.366721510887146},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3284814953804016},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.25746941566467285},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2369736135005951},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11131486296653748}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8278084993362427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503314971923828},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5392874479293823},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5179589986801147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4521976113319397},{"id":"https://openalex.org/C9936470","wikidata":"https://www.wikidata.org/wiki/Q6510405","display_name":"Least-squares function approximation","level":3,"score":0.440122127532959},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.366721510887146},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3284814953804016},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25746941566467285},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2369736135005951},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11131486296653748},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/acc.2010.5530856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2010.5530856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 American Control Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:orbi.ulg.ac.be:2268/65794","is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/65794","pdf_url":null,"source":{"id":"https://openalex.org/S4306400651","display_name":"Open Repository and Bibliography (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2010 American Control Conference, 486-491 (2010); 2010  American  Control  Conference, Baltimore, United States [US], June 30-July 2, 2010","raw_type":"peer reviewed"}],"best_oa_location":{"id":"pmh:oai:orbi.ulg.ac.be:2268/65794","is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/65794","pdf_url":null,"source":{"id":"https://openalex.org/S4306400651","display_name":"Open Repository and Bibliography (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2010 American Control Conference, 486-491 (2010); 2010  American  Control  Conference, Baltimore, United States [US], June 30-July 2, 2010","raw_type":"peer reviewed"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1507222174","https://openalex.org/W2009303086","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2132351269","https://openalex.org/W2147839652","https://openalex.org/W2150339816","https://openalex.org/W2150923691","https://openalex.org/W2156737235","https://openalex.org/W2165418472","https://openalex.org/W2415292238","https://openalex.org/W2586680856","https://openalex.org/W4214717370","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,7,53],"is":[2,54,93,125],"a":[3,48,131,142,155],"promising":[4],"paradigm":[5],"for":[6,16,29,75,130,169],"optimal":[8],"control.":[9],"We":[10],"consider":[11],"policy":[12,30,85,99,170],"iteration":[13,86],"(PI)":[14],"algorithms":[15],"reinforcement":[17,52],"learning,":[18],"which":[19,161],"iteratively":[20],"evaluate":[21],"and":[22,34,89,137,153],"improve":[23],"control":[24],"policies.":[25],"State-of-the-art,":[26],"least-squares":[27,72,84,167],"techniques":[28],"evaluation":[31,113],"are":[32,41],"sample-efficient":[33],"have":[35],"relaxed":[36],"convergence":[37],"requirements.":[38],"However,":[39],"they":[40],"typically":[42],"used":[43],"in":[44,95,141],"offline":[45,91,151],"PI,":[46,160],"whereas":[47],"central":[49],"goal":[50],"of":[51,114,134,158,163],"to":[55,127,138],"develop":[56],"online":[57,63,83,97,123,159],"algorithms.":[58],"Therefore,":[59],"we":[60],"propose":[61],"an":[62,111,119],"PI":[64],"algorithm":[65,88],"that":[66],"evaluates":[67],"policies":[68],"with":[69,150,154],"the":[70,96,115],"so-called":[71],"temporal":[73],"difference":[74,80],"Q-functions":[76],"(LSTD-Q).":[77],"The":[78],"crucial":[79],"between":[81],"this":[82],"(LSPI)":[87],"its":[90,135],"counterpart":[92],"that,":[94],"case,":[98],"improvements":[100],"must":[101],"be":[102],"performed":[103],"once":[104],"every":[105],"few":[106],"state":[107],"transitions,":[108],"using":[109],"only":[110],"incomplete":[112],"current":[116],"policy.":[117],"In":[118],"extensive":[120],"experimental":[121],"evaluation,":[122],"LSPI":[124,146,152],"found":[126],"work":[128],"well":[129],"wide":[132],"range":[133],"parameters,":[136],"learn":[139],"successfully":[140],"real-time":[143],"example.":[144],"Online":[145],"also":[147],"compares":[148],"favorably":[149],"different":[156],"flavor":[157],"instead":[162],"LSTD-Q":[164],"employs":[165],"another":[166],"method":[168],"evaluation.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}