乐胖代购免代理版

{"id":"https://openalex.org/W1999912147","doi":"https://doi.org/10.1109/tnnls.2013.2247418","title":"Algorithmic Survey of Parametric Value Function Approximation","display_name":"Algorithmic Survey of Parametric Value Function Approximation","publication_year":2013,"publication_date":"2013-04-05","ids":{"openalex":"https://openalex.org/W1999912147","doi":"https://doi.org/10.1109/tnnls.2013.2247418","mag":"1999912147","pmid":"https://pubmed.ncbi.nlm.nih.gov/24808468"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2013.2247418","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://centralesupelec.hal.science/hal-00869725/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111253096","display_name":"M. 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":false,"raw_author_name":"M. Geist","raw_affiliation_strings":["[IMS-MaLIS Research Group, Sup\u00e9lec, Metz, France]"],"affiliations":[{"raw_affiliation_string":"[IMS-MaLIS Research Group, Sup\u00e9lec, Metz, France]","institution_ids":["https://openalex.org/I4210160189","https://openalex.org/I102475099"]}]},{"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":"O. Pietquin","raw_affiliation_strings":["[IMS-MaLIS Research Group, Sup\u00e9lec, Metz, France]"],"affiliations":[{"raw_affiliation_string":"[IMS-MaLIS Research Group, Sup\u00e9lec, Metz, France]","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.806,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":74,"citation_normalized_percentile":{"value":0.999969,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"24","issue":"6","first_page":"845","last_page":"867"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998,"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":0.9998,"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":0.9967,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9886,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.6754036},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function Approximation","score":0.6705996},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic Gradient Descent","score":0.5410271},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic Approximation","score":0.520453},{"id":"https://openalex.org/keywords/representation","display_name":"Representation","score":0.5017841}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7681645},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.6754036},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.6705996},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.66192156},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5724331},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.55949664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5487592},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5410271},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.520453},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5017841},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49293494},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35623363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31557262},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16103566},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.117132455},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.089849085},{"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/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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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":7,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2013.2247418","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal-supelec.archives-ouvertes.fr/hal-00869725","pdf_url":"https://centralesupelec.hal.science/hal-00869725/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal-centralesupelec.archives-ouvertes.fr/hal-00869725/file/vfa_survey.pdf","pdf_url":"https://hal-centralesupelec.archives-ouvertes.fr/hal-00869725/file/vfa_survey.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal-centralesupelec.archives-ouvertes.fr/hal-00869725/document","pdf_url":"https://hal-centralesupelec.archives-ouvertes.fr/hal-00869725/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal-supelec.archives-ouvertes.fr/hal-00869725/document","pdf_url":"https://hal-supelec.archives-ouvertes.fr/hal-00869725/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal-supelec.archives-ouvertes.fr/hal-00869725/file/vfa_survey.pdf","pdf_url":"https://hal-supelec.archives-ouvertes.fr/hal-00869725/file/vfa_survey.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24808468","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://hal-supelec.archives-ouvertes.fr/hal-00869725","pdf_url":"https://centralesupelec.hal.science/hal-00869725/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":118,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W133763854","https://openalex.org/W1460549585","https://openalex.org/W146900863","https://openalex.org/W1507222174","https://openalex.org/W1514587017","https://openalex.org/W1520710862","https://openalex.org/W1533285455","https://openalex.org/W1547105496","https://openalex.org/W1550698229","https://openalex.org/W1569273527","https://openalex.org/W1575592356","https://openalex.org/W1576452626","https://openalex.org/W1583330603","https://openalex.org/W1601081659","https://openalex.org/W1626155273","https://openalex.org/W1646707810","https://openalex.org/W166862392","https://openalex.org/W1721038333","https://openalex.org/W1730555343","https://openalex.org/W1745373831","https://openalex.org/W1991859114","https://openalex.org/W1998172110","https://openalex.org/W2007240904","https://openalex.org/W2007655795","https://openalex.org/W2009303086","https://openalex.org/W2011233848","https://openalex.org/W2012547817","https://openalex.org/W2019172585","https://openalex.org/W2020934227","https://openalex.org/W2027648864","https://openalex.org/W2040123554","https://openalex.org/W2044271447","https://openalex.org/W2046513829","https://openalex.org/W2062541405","https://openalex.org/W2063698478","https://openalex.org/W2072931156","https://openalex.org/W2073384958","https://openalex.org/W2075268401","https://openalex.org/W2076186907","https://openalex.org/W2080834410","https://openalex.org/W2082997771","https://openalex.org/W2091565802","https://openalex.org/W2097379307","https://openalex.org/W2097575529","https://openalex.org/W2100677568","https://openalex.org/W2100752967","https://openalex.org/W2101167844","https://openalex.org/W2101786389","https://openalex.org/W2104753538","https://openalex.org/W2107073969","https://openalex.org/W2107802551","https://openalex.org/W2107961737","https://openalex.org/W2108430473","https://openalex.org/W2108596215","https://openalex.org/W2109504867","https://openalex.org/W2112264645","https://openalex.org/W2118556122","https://openalex.org/W2120346334","https://openalex.org/W2122945138","https://openalex.org/W2123917165","https://openalex.org/W2123979492","https://openalex.org/W2124144580","https://openalex.org/W2125510930","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/W2138178898","https://openalex.org/W2138326839","https://openalex.org/W2139418546","https://openalex.org/W2141022000","https://openalex.org/W2147839652","https://openalex.org/W2151661095","https://openalex.org/W2151904921","https://openalex.org/W2155027007","https://openalex.org/W2156974606","https://openalex.org/W2158883409","https://openalex.org/W2158984235","https://openalex.org/W2159312714","https://openalex.org/W2161795906","https://openalex.org/W2165905123","https://openalex.org/W2167519341","https://openalex.org/W2172968643","https://openalex.org/W2180877127","https://openalex.org/W2292112492","https://openalex.org/W2415292238","https://openalex.org/W2487144912","https://openalex.org/W2596585349","https://openalex.org/W2597289420","https://openalex.org/W2604272474","https://openalex.org/W2615953416","https://openalex.org/W2737668828","https://openalex.org/W2787259794","https://openalex.org/W2913806414","https://openalex.org/W2951143668","https://openalex.org/W2970419211","https://openalex.org/W2990138404","https://openalex.org/W3027095131","https://openalex.org/W3041202696","https://openalex.org/W3103512641","https://openalex.org/W3139377883","https://openalex.org/W3198350258","https://openalex.org/W32403112","https://openalex.org/W359568995","https://openalex.org/W4212774754","https://openalex.org/W4214717370","https://openalex.org/W4230727635","https://openalex.org/W4236439427","https://openalex.org/W4242606736","https://openalex.org/W4245296547","https://openalex.org/W4251263574","https://openalex.org/W4285719527","https://openalex.org/W4299401133","https://openalex.org/W52170320","https://openalex.org/W86816279"],"related_works":["https://openalex.org/W4399282524","https://openalex.org/W4323366756","https://openalex.org/W4286899070","https://openalex.org/W4285259204","https://openalex.org/W4256087190","https://openalex.org/W4240668504","https://openalex.org/W3207830353","https://openalex.org/W3119329039","https://openalex.org/W2979432606","https://openalex.org/W1501190258"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,6,16],"(RL)":[2],"is":[3,57],"a":[4,100,105,110],"machine":[5],"answer":[7],"to":[8,26],"the":[9,24,29,37,55,95],"optimal":[10,18],"control":[11,19],"problem.":[12],"It":[13],"consists":[14],"of":[15,31,44,50,94],"an":[17,48,61],"policy":[20,33],"through":[21],"interactions":[22],"with":[23],"system":[25,56],"be":[27],"controlled,":[28],"quality":[30],"this":[32,51],"being":[34],"quantified":[35],"by":[36,74,91],"so-called":[38],"value":[39,52,71],"function.":[40],"A":[41],"recurrent":[42],"subtopic":[43],"RL":[45],"concerns":[46],"computing":[47],"approximation":[49,73],"function":[53,72],"when":[54],"too":[58],"large":[59],"for":[60,69],"exact":[62],"representation.":[63],"This":[64],"survey":[65],"reviews":[66],"state-of-the-art":[67],"methods":[68],"(parametric)":[70],"grouping":[75],"them":[76],"into":[77],"three":[78],"main":[79],"categories:":[80],"bootstrapping,":[81],"residual,":[82],"and":[83,99],"projected":[84],"fixed-point":[85],"approaches.":[86],"Related":[87],"algorithms":[88],"are":[89],"derived":[90],"considering":[92],"one":[93],"associated":[96],"cost":[97],"functions":[98],"specific":[101],"minimization":[102],"method,":[103],"generally":[104],"stochastic":[106],"gradient":[107],"descent":[108],"or":[109],"recursive":[111],"least-squares":[112],"approach.":[113]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1999912147","counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4}],"updated_date":"2024-12-09T14:06:10.828543","created_date":"2016-06-24"}