乐胖代购免代理版

{"id":"https://openalex.org/W1976878861","doi":"https://doi.org/10.1109/icmla.2011.19","title":"A Non-parametric Approach to Approximate Dynamic Programming","display_name":"A Non-parametric Approach to Approximate Dynamic Programming","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W1976878861","doi":"https://doi.org/10.1109/icmla.2011.19","mag":"1976878861"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla.2011.19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://centralesupelec.hal.science/hal-00652438/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080320000","display_name":"Hadrien Glaude","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":"Hadrien Glaude","raw_affiliation_strings":["SUPELEC (IMS Res. Group), Metz, France"],"affiliations":[{"raw_affiliation_string":"SUPELEC (IMS Res. Group), Metz, France","institution_ids":["https://openalex.org/I4210160189","https://openalex.org/I102475099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087489051","display_name":"Fadi Akrimi","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/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":"Fadi Akrimi","raw_affiliation_strings":["SUPELEC (IMS Res. Group), Metz, France"],"affiliations":[{"raw_affiliation_string":"SUPELEC (IMS Res. Group), Metz, France","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]}]},{"author_position":"middle","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":false,"raw_author_name":"Matthieu Geist","raw_affiliation_strings":["SUPELEC (IMS Res. Group), Metz, France"],"affiliations":[{"raw_affiliation_string":"SUPELEC (IMS Res. Group), 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/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":"Olivier Pietquin","raw_affiliation_strings":["SUPELEC (IMS Res. Group), Metz, France"],"affiliations":[{"raw_affiliation_string":"SUPELEC (IMS Res. Group), Metz, France","institution_ids":["https://openalex.org/I4210160189","https://openalex.org/I102475099"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":1,"citation_normalized_percentile":{"value":0.524986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":65,"max":72},"biblio":{"volume":null,"issue":null,"first_page":"317","last_page":"322"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9953,"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":0.9953,"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":0.9948,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9935,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.79173064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.73588395},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7214706},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6260581},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.59120405},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.5641334},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.54527104},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.51392007},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.51166606},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5089257},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.46884122},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.42035165},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38448256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36118716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20783457},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18306148},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla.2011.19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://centralesupelec.hal.science/hal-00652438","pdf_url":"https://centralesupelec.hal.science/hal-00652438/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-centralesupelec.archives-ouvertes.fr/hal-00652438/file/ICMLA_2011_HGFAMGOP.pdf","pdf_url":"https://hal-centralesupelec.archives-ouvertes.fr/hal-00652438/file/ICMLA_2011_HGFAMGOP.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":"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-00652438/document","pdf_url":"https://hal-centralesupelec.archives-ouvertes.fr/hal-00652438/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-supelec.archives-ouvertes.fr/hal-00652438/document","pdf_url":"https://hal-supelec.archives-ouvertes.fr/hal-00652438/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://centralesupelec.hal.science/hal-00652438/file/ICMLA_2011_HGFAMGOP.pdf","pdf_url":"https://centralesupelec.hal.science/hal-00652438/file/ICMLA_2011_HGFAMGOP.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":"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-supelec.archives-ouvertes.fr/hal-00652438/file/ICMLA_2011_HGFAMGOP.pdf","pdf_url":"https://hal-supelec.archives-ouvertes.fr/hal-00652438/file/ICMLA_2011_HGFAMGOP.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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://centralesupelec.hal.science/hal-00652438","pdf_url":"https://centralesupelec.hal.science/hal-00652438/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},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":13,"referenced_works":["https://openalex.org/W1547105496","https://openalex.org/W1574840339","https://openalex.org/W1976606095","https://openalex.org/W1980241579","https://openalex.org/W2072931156","https://openalex.org/W2087400813","https://openalex.org/W2120346334","https://openalex.org/W2127530277","https://openalex.org/W2341171179","https://openalex.org/W2586680856","https://openalex.org/W4214717370","https://openalex.org/W4247446124","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4297873223","https://openalex.org/W4285537323","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W2953025626","https://openalex.org/W2379312070","https://openalex.org/W2136173754","https://openalex.org/W2110050003","https://openalex.org/W1932159282"],"abstract_inverted_index":{"Approximate":[0],"Dynamic":[1],"Programming":[2],"(ADP)":[3],"is":[4,49,72],"a":[5,17,23,40,50,56,68,82,103],"machine":[6],"learning":[7,11,54],"method":[8,126],"aiming":[9],"at":[10],"an":[12],"optimal":[13],"control":[14,57],"policy":[15,58],"for":[16,53],"dynamic":[18],"and":[19,32],"stochastic":[20],"system":[21,31],"from":[22,59,102],"logged":[24],"set":[25],"of":[26,42,65,81,85,105,119,136],"observed":[27],"interactions":[28],"between":[29],"the":[30,63,79,117,120,134],"one":[33],"or":[34],"several":[35],"non-optimal":[36],"controlers.":[37],"It":[38],"defines":[39],"class":[41],"particular":[43],"Reinforcement":[44],"Learning":[45],"(RL)":[46],"algorithms":[47],"which":[48,71],"general":[51],"paradigm":[52],"such":[55],"interactions.":[60],"ADP":[61],"addresses":[62],"problem":[64],"systems":[66],"exhibiting":[67],"state":[69,96,110,147],"space":[70],"too":[73],"large":[74],"to":[75,91,107,127,144],"be":[76],"enumerated":[77],"in":[78],"memory":[80],"computer.":[83],"Because":[84],"this,":[86],"approximation":[87],"schemes":[88],"are":[89],"used":[90],"generalize":[92],"estimates":[93],"over":[94],"continuous":[95,109],"spaces.":[97,111,148],"Nevertheless,":[98],"RL":[99],"still":[100],"suffers":[101],"lack":[104],"scalability":[106,130],"multidimensional":[108],"In":[112],"this":[113,129],"paper,":[114],"we":[115],"propose":[116],"use":[118],"Locally":[121],"Weighted":[122],"Projection":[123],"Regression":[124],"(LWPR)":[125],"handle":[128],"problem.":[131],"We":[132],"prove":[133],"efficacy":[135],"our":[137],"approach":[138],"on":[139],"two":[140],"standard":[141],"benchmarks":[142],"modified":[143],"exhibit":[145],"larger":[146]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1976878861","counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2024-12-14T17:11:22.059446","created_date":"2016-06-24"}