{"id":"https://openalex.org/W2109504867","doi":"https://doi.org/10.1109/icumt.2010.5676598","title":"Statistically linearized least-squares temporal differences","display_name":"Statistically linearized least-squares temporal differences","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W2109504867","doi":"https://doi.org/10.1109/icumt.2010.5676598","mag":"2109504867"},"language":"en","primary_location":{"id":"doi:10.1109/icumt.2010.5676598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icumt.2010.5676598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Congress on Ultra Modern Telecommunications and Control Systems","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/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Matthieu Geist","raw_affiliation_strings":["IMS Research Group Sup\u00e9lec, Metz, France","IMS Res. Group, SUPELEC, Metz, France"],"affiliations":[{"raw_affiliation_string":"IMS Research Group Sup\u00e9lec, Metz, France","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]},{"raw_affiliation_string":"IMS Res. Group, SUPELEC, Metz, France","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]}]},{"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/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":["IMS Research Group Sup\u00e9lec, Metz, France","IMS Res. Group, SUPELEC, Metz, France"],"affiliations":[{"raw_affiliation_string":"IMS Research Group Sup\u00e9lec, Metz, France","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]},{"raw_affiliation_string":"IMS Res. Group, SUPELEC, Metz, France","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]}]}],"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/I4210160189"],"apc_list":null,"apc_paid":null,"fwci":3.2845,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92582801,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"13","issue":null,"first_page":"450","last_page":"457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958000183105469,"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":0.9958000183105469,"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":0.9670000076293945,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9624999761581421,"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/linearization","display_name":"Linearization","score":0.6922307014465332},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6885663270950317},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6509703397750854},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5884677171707153},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5568215847015381},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5046113729476929},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4648434519767761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4587545394897461},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4559129476547241},{"id":"https://openalex.org/keywords/parametrization","display_name":"Parametrization (atmospheric modeling)","score":0.4316253662109375},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3517867624759674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15717178583145142}],"concepts":[{"id":"https://openalex.org/C11210021","wikidata":"https://www.wikidata.org/wiki/Q1520713","display_name":"Linearization","level":3,"score":0.6922307014465332},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6885663270950317},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6509703397750854},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5884677171707153},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5568215847015381},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5046113729476929},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4648434519767761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4587545394897461},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4559129476547241},{"id":"https://openalex.org/C202887219","wikidata":"https://www.wikidata.org/wiki/Q3895221","display_name":"Parametrization (atmospheric modeling)","level":3,"score":0.4316253662109375},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3517867624759674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15717178583145142},{"id":"https://openalex.org/C74902906","wikidata":"https://www.wikidata.org/wiki/Q1190858","display_name":"Radiative transfer","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icumt.2010.5676598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icumt.2010.5676598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Congress on Ultra Modern Telecommunications and Control Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00553913v1","is_oa":false,"landing_page_url":"https://centralesupelec.hal.science/hal-00553913","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICUMT 2010, Oct 2010, Moscow, Russia. pp.450-457, ⟨10.1109/ICUMT.2010.5676598⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W1507222174","https://openalex.org/W1594783240","https://openalex.org/W1646707810","https://openalex.org/W2035814233","https://openalex.org/W2044271447","https://openalex.org/W2062541405","https://openalex.org/W2063698478","https://openalex.org/W2072931156","https://openalex.org/W2076186907","https://openalex.org/W2082997771","https://openalex.org/W2104753538","https://openalex.org/W2121863487","https://openalex.org/W2123487311","https://openalex.org/W2132849848","https://openalex.org/W2134042548","https://openalex.org/W2139418546","https://openalex.org/W2141562047","https://openalex.org/W2156974606","https://openalex.org/W2586680856","https://openalex.org/W4230727635","https://openalex.org/W4285719527","https://openalex.org/W6635508374","https://openalex.org/W6679599195","https://openalex.org/W7065010408"],"related_works":["https://openalex.org/W2153421756","https://openalex.org/W2054489697","https://openalex.org/W2077818434","https://openalex.org/W2361081803","https://openalex.org/W2036241269","https://openalex.org/W2109057766","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"A":[0,30,137],"common":[1],"drawback":[2],"of":[3,23,51,81,117],"standard":[4],"reinforcement":[5],"learning":[6],"algorithms":[7,120],"is":[8,25,35,47,83,140],"their":[9],"inability":[10],"to":[11,13,86],"scale-up":[12],"real-world":[14],"problems.":[15],"For":[16],"this":[17,77,79],"reason,":[18],"a":[19,87,124,134],"current":[20],"important":[21],"trend":[22],"research":[24],"(state-action)":[26],"value":[27,32,53],"function":[28,33,54],"approximation.":[29],"prominent":[31],"approximator":[34],"the":[36,49,52,66,97,118],"least-squares":[37],"temporal":[38],"differences":[39],"(LSTD)":[40],"algorithm.":[41],"However,":[42],"for":[43],"technical":[44],"reasons,":[45],"linearity":[46],"mandatory:":[48],"parameterization":[50],"must":[55],"be":[56,71,102],"linear":[57,125],"(compact":[58],"nonlinear":[59,94],"representations":[60],"are":[61,121],"not":[62],"allowed)":[63],"and":[64,96,127],"only":[65],"Bellman":[67,98],"evaluation":[68],"operator":[69,100],"can":[70,101],"considered":[72],"(imposing":[73],"policy-iteration-like":[74],"schemes).":[75,114],"In":[76],"paper,":[78],"restriction":[80],"LSTD":[82],"lifted":[84],"thanks":[85],"derivative-free":[88],"statistical":[89],"linearization":[90],"approach.":[91],"This":[92],"way,":[93],"parameterizations":[95],"optimality":[99],"taken":[103],"into":[104,111],"account":[105,112],"(this":[106],"last":[107],"point":[108],"allows":[109],"taking":[110],"value-iteration-like":[113],"The":[115],"efficiency":[116],"resulting":[119],"demonstrated":[122],"using":[123],"parametrization":[126],"neural":[128],"networks":[129],"as":[130,132],"well":[131],"on":[133],"Q-learning-like":[135],"problem.":[136],"theoretical":[138],"analysis":[139],"also":[141],"provided.":[142]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}