{"id":"https://openalex.org/W1980241579","doi":"https://doi.org/10.1109/adprl.2011.5967355","title":"Parametric value function approximation: A unified view","display_name":"Parametric value function approximation: A unified view","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W1980241579","doi":"https://doi.org/10.1109/adprl.2011.5967355","mag":"1980241579"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2011.5967355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},"type":"preprint","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/A5110482875","display_name":"Matthieu Geist","orcid":null},"institutions":[{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]},{"id":"https://openalex.org/I1288283403","display_name":"Georgia Tech Lorraine","ror":"https://ror.org/02m5dy175","country_code":"FR","type":"education","lineage":["https://openalex.org/I1288283403"]},{"id":"https://openalex.org/I4210089931","display_name":"Georgia Tech-CNRS Laboratory","ror":"https://ror.org/00avmbz91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1288283403","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I130701444","https://openalex.org/I4210089931","https://openalex.org/I4210095849","https://openalex.org/I4405256580","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Matthieu Geist","raw_affiliation_strings":["Sup\u00e9lec, IMS Research Group, Metz, France","SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)","Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)"],"affiliations":[{"raw_affiliation_string":"Sup\u00e9lec, IMS Research Group, Metz, France","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]},{"raw_affiliation_string":"SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)","institution_ids":["https://openalex.org/I102475099"]},{"raw_affiliation_string":"Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)","institution_ids":["https://openalex.org/I1288283403","https://openalex.org/I4210089931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065100569","display_name":"Olivier Pietquin","orcid":"https://orcid.org/0000-0002-5386-465X"},"institutions":[{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]},{"id":"https://openalex.org/I1288283403","display_name":"Georgia Tech Lorraine","ror":"https://ror.org/02m5dy175","country_code":"FR","type":"education","lineage":["https://openalex.org/I1288283403"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210089931","display_name":"Georgia Tech-CNRS Laboratory","ror":"https://ror.org/00avmbz91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1288283403","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I130701444","https://openalex.org/I4210089931","https://openalex.org/I4210095849","https://openalex.org/I4405256580","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Pietquin","raw_affiliation_strings":["Sup\u00e9lec, IMS Research Group, Metz, France","UMI 2958, Georgia-Tech, CNRS, Metz, France","Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)","SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)"],"affiliations":[{"raw_affiliation_string":"Sup\u00e9lec, IMS Research Group, Metz, France","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]},{"raw_affiliation_string":"UMI 2958, Georgia-Tech, CNRS, Metz, France","institution_ids":["https://openalex.org/I1288283403","https://openalex.org/I1294671590","https://openalex.org/I4210089931"]},{"raw_affiliation_string":"Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)","institution_ids":["https://openalex.org/I1288283403","https://openalex.org/I4210089931"]},{"raw_affiliation_string":"SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)","institution_ids":["https://openalex.org/I102475099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110482875"],"corresponding_institution_ids":["https://openalex.org/I102475099","https://openalex.org/I1288283403","https://openalex.org/I4210089931","https://openalex.org/I4210160189"],"apc_list":null,"apc_paid":null,"fwci":6.1391,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.96174489,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"49","issue":null,"first_page":"9","last_page":"16"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.9939000010490417,"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":0.7982603311538696},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.7093240022659302},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6880686283111572},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.6362310647964478},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6218085289001465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.612191915512085},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5856307148933411},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5637387037277222},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5528528094291687},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5496240854263306},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.476403146982193},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4147699177265167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33321160078048706},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32378172874450684},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.18108054995536804},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10726329684257507},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.09581318497657776}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7982603311538696},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.7093240022659302},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6880686283111572},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.6362310647964478},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6218085289001465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.612191915512085},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5856307148933411},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5637387037277222},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5528528094291687},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5496240854263306},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.476403146982193},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4147699177265167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33321160078048706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32378172874450684},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18108054995536804},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10726329684257507},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.09581318497657776},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/adprl.2011.5967355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.207.6890","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.6890","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.metz.supelec.fr//metz/personnel/pietquin/pdf/ADPRL_2011_MGOP.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.393.4977","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.393.4977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/61/81/12/PDF/ADPRL_2011_MGOP.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00618112v1","is_oa":false,"landing_page_url":"https://centralesupelec.hal.science/hal-00618112","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"ADPRL 2011, Apr 2011, Paris, France. pp.9-16, ⟨10.1109/ADPRL.2011.5967355⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W86816279","https://openalex.org/W166862392","https://openalex.org/W1507222174","https://openalex.org/W1514587017","https://openalex.org/W1518539242","https://openalex.org/W1547105496","https://openalex.org/W1550698229","https://openalex.org/W1569273527","https://openalex.org/W1576452626","https://openalex.org/W1646707810","https://openalex.org/W1746819321","https://openalex.org/W2007240904","https://openalex.org/W2007655795","https://openalex.org/W2012547817","https://openalex.org/W2019172585","https://openalex.org/W2027648864","https://openalex.org/W2044271447","https://openalex.org/W2062541405","https://openalex.org/W2072931156","https://openalex.org/W2075268401","https://openalex.org/W2082997771","https://openalex.org/W2104753538","https://openalex.org/W2105934661","https://openalex.org/W2109504867","https://openalex.org/W2112264645","https://openalex.org/W2118556122","https://openalex.org/W2119567691","https://openalex.org/W2120346334","https://openalex.org/W2122945138","https://openalex.org/W2127530277","https://openalex.org/W2131600418","https://openalex.org/W2132351269","https://openalex.org/W2132849848","https://openalex.org/W2133733518","https://openalex.org/W2134042548","https://openalex.org/W2136602922","https://openalex.org/W2139418546","https://openalex.org/W2141562047","https://openalex.org/W2147839652","https://openalex.org/W2151661095","https://openalex.org/W2153290280","https://openalex.org/W2154761920","https://openalex.org/W2156974606","https://openalex.org/W2158738729","https://openalex.org/W2158984235","https://openalex.org/W2178806388","https://openalex.org/W2334782222","https://openalex.org/W2586680856","https://openalex.org/W2737668828","https://openalex.org/W2787259794","https://openalex.org/W3198350258","https://openalex.org/W4211049957","https://openalex.org/W4214717370","https://openalex.org/W4245296547","https://openalex.org/W4285719527","https://openalex.org/W4297234538","https://openalex.org/W4307347247","https://openalex.org/W6600556750","https://openalex.org/W6603545158","https://openalex.org/W6606719070","https://openalex.org/W6630907848","https://openalex.org/W6634118891","https://openalex.org/W6677737365","https://openalex.org/W6678313319","https://openalex.org/W6679599195","https://openalex.org/W6679859942","https://openalex.org/W6680194329","https://openalex.org/W6682262797","https://openalex.org/W6682499586","https://openalex.org/W6683356630","https://openalex.org/W6843204366","https://openalex.org/W7065010408"],"related_works":["https://openalex.org/W1501190258","https://openalex.org/W4256087190","https://openalex.org/W2979432606","https://openalex.org/W4399282524","https://openalex.org/W4240668504","https://openalex.org/W4286899070","https://openalex.org/W4323366756","https://openalex.org/W3207830353","https://openalex.org/W4285259204","https://openalex.org/W3119329039"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,6,16],"(RL)":[2],"is":[3,45,53],"a":[4,101,109,114],"machine":[5],"answer":[7],"to":[8,26,46,104],"the":[9,24,29,37,51,67,96],"optimal":[10,18],"control":[11,19],"problem.":[12],"It":[13],"consists":[14],"of":[15,31,66,95],"an":[17,57],"policy":[20,33],"through":[21],"interactions":[22],"with":[23],"system":[25,52],"be":[27],"controlled,":[28],"quality":[30],"this":[32,48],"being":[34],"quantified":[35],"by":[36,75,92],"so-called":[38],"value":[39,72],"function.":[40],"An":[41],"important":[42],"RL":[43],"subtopic":[44],"approximate":[47],"function":[49,73],"when":[50],"too":[54],"large":[55],"for":[56,70],"exact":[58],"representation.":[59],"This":[60],"survey":[61],"reviews":[62],"and":[63,84,100],"unifies":[64],"state":[65],"art":[68],"methods":[69],"parametric":[71],"approximation":[74],"grouping":[76],"them":[77],"into":[78],"three":[79],"main":[80],"categories:":[81],"bootstrapping,":[82],"residuals":[83],"projected":[85],"fixed-point":[86],"approaches.":[87],"Related":[88],"algorithms":[89],"are":[90],"derived":[91],"considering":[93],"one":[94],"associated":[97],"cost":[98],"functions":[99],"specific":[102],"way":[103],"minimize":[105],"it,":[106],"almost":[107],"always":[108],"stochastic":[110],"gradient":[111],"descent":[112],"or":[113],"recursive":[115],"least-squares":[116],"approach.":[117]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}