乐胖代购免代理版

{"id":"https://openalex.org/W2158984235","doi":"https://doi.org/10.1613/jair.3077","title":"Kalman Temporal Differences","display_name":"Kalman Temporal Differences","publication_year":2010,"publication_date":"2010-10-29","ids":{"openalex":"https://openalex.org/W2158984235","doi":"https://doi.org/10.1613/jair.3077","mag":"2158984235"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.3077","pdf_url":"https://jair.org/index.php/jair/article/download/10675/25513","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://jair.org/index.php/jair/article/download/10675/25513","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 research group Sup\u00e9lec Metz, France"],"affiliations":[{"raw_affiliation_string":"IMS 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/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":"O. Pietquin","raw_affiliation_strings":["IMS research group Sup\u00e9lec Metz, France"],"affiliations":[{"raw_affiliation_string":"IMS research group Sup\u00e9lec 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":{"value":0,"currency":"USD","value_usd":0,"provenance":"doaj"},"apc_paid":null,"fwci":9.906,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":84,"citation_normalized_percentile":{"value":0.999967,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"39","issue":null,"first_page":"483","last_page":"532"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9888,"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":0.9888,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9873,"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9793,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/stochastic-approximation","display_name":"Stochastic Approximation","score":0.6571803},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function Approximation","score":0.4116367}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.68757033},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.6571803},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.65583557},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.60042334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5819763},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.5720349},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5387401},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4683026},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4613},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4116367},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.36769992},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34628934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33918288},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3337729},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32814413},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1035071},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0809924},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":9,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.3077","pdf_url":"https://jair.org/index.php/jair/article/download/10675/25513","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://hal-centralesupelec.archives-ouvertes.fr/hal-00351297","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":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":null,"is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://hal-supelec.archives-ouvertes.fr/hal-00858687","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":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":null,"is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://hal-supelec.archives-ouvertes.fr/hal-00351297","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":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":null,"is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://centralesupelec.hal.science/hal-00858687","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":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":null,"is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://hal-centralesupelec.archives-ouvertes.fr/hal-00858687","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":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":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1406.3270","pdf_url":"https://arxiv.org/pdf/1406.3270","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://centralesupelec.hal.science/hal-00351297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.1406.3270","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.3077","pdf_url":"https://jair.org/index.php/jair/article/download/10675/25513","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"score":0.77,"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16"}],"grants":[],"datasets":[],"versions":["https://openalex.org/W2158984235","https://openalex.org/W3098088044"],"referenced_works_count":50,"referenced_works":["https://openalex.org/W105751747","https://openalex.org/W1514587017","https://openalex.org/W1520710862","https://openalex.org/W1533285455","https://openalex.org/W1552327263","https://openalex.org/W1554663460","https://openalex.org/W1569320505","https://openalex.org/W1574840339","https://openalex.org/W1576452626","https://openalex.org/W1591803298","https://openalex.org/W1603631609","https://openalex.org/W1646707810","https://openalex.org/W2007240904","https://openalex.org/W2007655795","https://openalex.org/W2009303086","https://openalex.org/W2035814233","https://openalex.org/W2044271447","https://openalex.org/W2062541405","https://openalex.org/W2072931156","https://openalex.org/W2082997771","https://openalex.org/W2100379997","https://openalex.org/W2104753538","https://openalex.org/W2105934661","https://openalex.org/W2109330238","https://openalex.org/W2109504867","https://openalex.org/W2112264645","https://openalex.org/W2114537044","https://openalex.org/W2119567691","https://openalex.org/W2122945138","https://openalex.org/W2123487311","https://openalex.org/W2127530277","https://openalex.org/W2129670787","https://openalex.org/W2130801532","https://openalex.org/W2132351269","https://openalex.org/W2132849848","https://openalex.org/W2133733518","https://openalex.org/W2136602922","https://openalex.org/W2139418546","https://openalex.org/W2141562047","https://openalex.org/W2156737235","https://openalex.org/W2156974606","https://openalex.org/W2163533082","https://openalex.org/W2586680856","https://openalex.org/W2737668828","https://openalex.org/W4241680091","https://openalex.org/W4285719527","https://openalex.org/W4297234538","https://openalex.org/W4307347247","https://openalex.org/W4388297464","https://openalex.org/W86816279"],"related_works":["https://openalex.org/W4399157305","https://openalex.org/W4281791088","https://openalex.org/W3105579180","https://openalex.org/W2903299703","https://openalex.org/W2808418668","https://openalex.org/W2386410636","https://openalex.org/W2156021013","https://openalex.org/W2152670157","https://openalex.org/W2016648086","https://openalex.org/W176737593"],"abstract_inverted_index":{"Because":[0],"reinforcement":[1],"learning":[2],"suffers":[3],"from":[4],"a":[5,25],"lack":[6],"of":[7,68,107],"scalability,":[8],"online":[9],"value":[10],"(and":[11],"Q-)":[12],"function":[13],"approximation":[14,27],"has":[15],"received":[16],"increasing":[17],"interest":[18],"this":[19],"last":[20],"decade.":[21],"This":[22],"contribution":[23],"introduces":[24],"novel":[26],"scheme,":[28],"namely":[29],"the":[30,38,66,72,105,108,112],"Kalman":[31],"Temporal":[32],"Differences":[33],"(KTD)":[34],"framework,":[35],"that":[36],"exhibits":[37],"following":[39],"features:":[40],"sample-efficiency,":[41],"non-linear":[42],"approximation,":[43],"non-stationarity":[44],"handling":[45],"and":[46,91],"uncertainty":[47],"management.":[48],"A":[49],"first":[50],"KTD-based":[51],"algorithm":[52],"is":[53,80,83],"provided":[54],"for":[55,85,88],"deterministic":[56,90],"Markov":[57],"Decision":[58],"Processes":[59],"(MDP)":[60],"which":[61],"produces":[62],"biased":[63],"estimates":[64],"in":[65],"case":[67],"stochastic":[69,78,92],"transitions.":[70,93],"Than":[71],"eXtended":[73],"KTD":[74],"framework":[75],"(XKTD),":[76],"solving":[77],"MDP,":[79],"described.":[81],"Convergence":[82],"analyzed":[84],"special":[86],"cases":[87],"both":[89],"Related":[94],"algorithms":[95],"are":[96],"experimented":[97],"on":[98],"classical":[99],"benchmarks.":[100],"They":[101],"compare":[102],"favorably":[103],"to":[104],"state":[106],"art":[109],"while":[110],"exhibiting":[111],"announced":[113],"features.":[114]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2158984235","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":12}],"updated_date":"2024-12-14T15:16:44.886240","created_date":"2016-06-24"}