{"id":"https://openalex.org/W1549543673","doi":"https://doi.org/10.1007/978-3-642-27645-3_3","title":"Least-Squares Methods for Policy Iteration","display_name":"Least-Squares Methods for Policy Iteration","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W1549543673","doi":"https://doi.org/10.1007/978-3-642-27645-3_3","mag":"1549543673"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-27645-3_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3_3","pdf_url":null,"source":{"id":"https://openalex.org/S4210169857","display_name":"Adaptation, learning, and optimization","issn_l":"1867-4534","issn":["1867-4534","1867-4542"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptation, Learning, and Optimization","raw_type":"book-chapter"},"type":"book-chapter","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/A5058935509","display_name":"Lucian Bu\u015foniu","orcid":"https://orcid.org/0000-0001-8017-1296"},"institutions":[{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]},{"id":"https://openalex.org/I4210110792","display_name":"Centre de Recherche en Automatique de Nancy","ror":"https://ror.org/022r5hc56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210099203","https://openalex.org/I4210100260","https://openalex.org/I4210110792","https://openalex.org/I4210159245","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Lucian Bu\u015foniu","raw_affiliation_strings":["Research Center for Automatic Control (CRAN), University of Lorraine, Lorraine, France"],"affiliations":[{"raw_affiliation_string":"Research Center for Automatic Control (CRAN), University of Lorraine, Lorraine, France","institution_ids":["https://openalex.org/I4210110792","https://openalex.org/I90183372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014791481","display_name":"Alessandro Lazaric","orcid":"https://orcid.org/0000-0002-8970-413X"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210138412","display_name":"Centre de recherche Inria Lille - Nord Europe","ror":"https://ror.org/04eej9726","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210138412"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alessandro Lazaric","raw_affiliation_strings":["Team SequeL, INRIA Lille-Nord Europe, Lille, France"],"affiliations":[{"raw_affiliation_string":"Team SequeL, INRIA Lille-Nord Europe, Lille, France","institution_ids":["https://openalex.org/I4210138412","https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013843778","display_name":"Mohammad Ghavamzadeh","orcid":"https://orcid.org/0000-0003-0930-8688"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210138412","display_name":"Centre de recherche Inria Lille - Nord Europe","ror":"https://ror.org/04eej9726","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210138412"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mohammad Ghavamzadeh","raw_affiliation_strings":["Team SequeL, INRIA Lille-Nord Europe, Lille, France"],"affiliations":[{"raw_affiliation_string":"Team SequeL, INRIA Lille-Nord Europe, Lille, France","institution_ids":["https://openalex.org/I4210138412","https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016419651","display_name":"R\u00e9mi Munos","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210138412","display_name":"Centre de recherche Inria Lille - Nord Europe","ror":"https://ror.org/04eej9726","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210138412"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"R\u00e9mi Munos","raw_affiliation_strings":["Team SequeL, INRIA Lille-Nord Europe, Lille, France"],"affiliations":[{"raw_affiliation_string":"Team SequeL, INRIA Lille-Nord Europe, Lille, France","institution_ids":["https://openalex.org/I4210138412","https://openalex.org/I1326498283"]}]},{"author_position":"middle","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 Babu\u0161ka","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","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":"Bart De Schutter","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058935509"],"corresponding_institution_ids":["https://openalex.org/I4210110792","https://openalex.org/I90183372"],"apc_list":null,"apc_paid":null,"fwci":3.1719,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.92715017,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"75","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9939000010490417,"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":0.9939000010490417,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9667999744415283,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9336000084877014,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8136139512062073},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5703673362731934},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5215901732444763},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5214537978172302},{"id":"https://openalex.org/keywords/least-squares-function-approximation","display_name":"Least-squares function approximation","score":0.49848031997680664},{"id":"https://openalex.org/keywords/asymptotically-optimal-algorithm","display_name":"Asymptotically optimal algorithm","score":0.4555888772010803},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.43487492203712463},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4150252640247345},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35619163513183594},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.33132022619247437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.205732524394989}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8136139512062073},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5703673362731934},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5215901732444763},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5214537978172302},{"id":"https://openalex.org/C9936470","wikidata":"https://www.wikidata.org/wiki/Q6510405","display_name":"Least-squares function approximation","level":3,"score":0.49848031997680664},{"id":"https://openalex.org/C181789720","wikidata":"https://www.wikidata.org/wiki/Q4812191","display_name":"Asymptotically optimal algorithm","level":2,"score":0.4555888772010803},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.43487492203712463},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4150252640247345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35619163513183594},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.33132022619247437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.205732524394989},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-642-27645-3_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3_3","pdf_url":null,"source":{"id":"https://openalex.org/S4210169857","display_name":"Adaptation, learning, and optimization","issn_l":"1867-4534","issn":["1867-4534","1867-4542"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptation, Learning, and Optimization","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.672.9697","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.672.9697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://researchers.lille.inria.fr/%7Emunos/papers/files/lspi_chapter.pdf","raw_type":"text"}],"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":63,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W86816279","https://openalex.org/W1501190258","https://openalex.org/W1507222174","https://openalex.org/W1518539242","https://openalex.org/W1576452626","https://openalex.org/W1579026795","https://openalex.org/W1580425441","https://openalex.org/W1597303641","https://openalex.org/W1626155273","https://openalex.org/W1646707810","https://openalex.org/W1730555343","https://openalex.org/W1966195676","https://openalex.org/W1981745143","https://openalex.org/W1995515585","https://openalex.org/W1995713768","https://openalex.org/W2040766536","https://openalex.org/W2046513829","https://openalex.org/W2072931156","https://openalex.org/W2073384958","https://openalex.org/W2075268401","https://openalex.org/W2084202551","https://openalex.org/W2100677568","https://openalex.org/W2103263764","https://openalex.org/W2104753538","https://openalex.org/W2108596215","https://openalex.org/W2112264645","https://openalex.org/W2117355432","https://openalex.org/W2118556122","https://openalex.org/W2120346334","https://openalex.org/W2121825831","https://openalex.org/W2124144580","https://openalex.org/W2124477018","https://openalex.org/W2124599560","https://openalex.org/W2126410641","https://openalex.org/W2131490088","https://openalex.org/W2132351269","https://openalex.org/W2132849848","https://openalex.org/W2134289401","https://openalex.org/W2139418546","https://openalex.org/W2140778663","https://openalex.org/W2147839652","https://openalex.org/W2150923691","https://openalex.org/W2151268438","https://openalex.org/W2154761920","https://openalex.org/W2156737235","https://openalex.org/W2156974606","https://openalex.org/W2158738729","https://openalex.org/W2163712217","https://openalex.org/W2165060096","https://openalex.org/W2165418472","https://openalex.org/W2165905123","https://openalex.org/W2415292238","https://openalex.org/W2487144912","https://openalex.org/W2497090499","https://openalex.org/W2501213684","https://openalex.org/W2798909945","https://openalex.org/W2963705262","https://openalex.org/W3099235411","https://openalex.org/W4211221179","https://openalex.org/W4250419630","https://openalex.org/W4285719527","https://openalex.org/W4405868324"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370","https://openalex.org/W3038962357","https://openalex.org/W2189613824"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}