{"id":"https://openalex.org/W2141562047","doi":"https://doi.org/10.1109/adprl.2009.4927543","title":"Kalman Temporal Differences: The deterministic case","display_name":"Kalman Temporal Differences: The deterministic case","publication_year":2009,"publication_date":"2009-03-01","ids":{"openalex":"https://openalex.org/W2141562047","doi":"https://doi.org/10.1109/adprl.2009.4927543","mag":"2141562047"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927543","pdf_url":null,"source":{"id":"https://openalex.org/S4306422848","display_name":"IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://centralesupelec.hal.science/hal-00380870/document","any_repository_has_fulltext":true},"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/I4210114269","display_name":"ArcelorMittal (France)","ror":"https://ror.org/024xs2z82","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210114269","https://openalex.org/I50754188"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matthieu Geist","raw_affiliation_strings":["ArcelorMittal Maizi\u00e8res Research SA (Voie romaine, BP 30320, 57283 Maizi\u00e8res-l\u00e8s-Metz - France)","SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)"],"affiliations":[{"raw_affiliation_string":"SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)","institution_ids":["https://openalex.org/I102475099"]},{"raw_affiliation_string":"ArcelorMittal Maizi\u00e8res Research SA (Voie romaine, BP 30320, 57283 Maizi\u00e8res-l\u00e8s-Metz - France)","institution_ids":["https://openalex.org/I4210114269"]}]},{"author_position":"middle","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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Pietquin","raw_affiliation_strings":["SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)"],"affiliations":[{"raw_affiliation_string":"SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)","institution_ids":["https://openalex.org/I102475099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055682887","display_name":"Gabriel Fricout","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114269","display_name":"ArcelorMittal (France)","ror":"https://ror.org/024xs2z82","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210114269","https://openalex.org/I50754188"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gabriel Fricout","raw_affiliation_strings":["ArcelorMittal Maizi\u00e8res Research SA (Voie romaine, BP 30320, 57283 Maizi\u00e8res-l\u00e8s-Metz - France)"],"affiliations":[{"raw_affiliation_string":"ArcelorMittal Maizi\u00e8res Research SA (Voie romaine, BP 30320, 57283 Maizi\u00e8res-l\u00e8s-Metz - France)","institution_ids":["https://openalex.org/I4210114269"]}]}],"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":"pdf","cited_by_count":23,"citation_normalized_percentile":{"value":0.930563,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":90},"biblio":{"volume":null,"issue":null,"first_page":"185","last_page":"192"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9976,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9976,"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9892,"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"}},{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.954,"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/value","display_name":"Value (mathematics)","score":0.4747722},{"id":"https://openalex.org/keywords/representation","display_name":"Representation","score":0.4372039}],"concepts":[{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.63810027},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.61005765},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4747722},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.47406596},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.45568514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44187573},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4372039},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4315304},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4184279},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35840243},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32862118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29181308},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15881386},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.072645575},{"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/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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927543","pdf_url":null,"source":{"id":"https://openalex.org/S4306422848","display_name":"IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","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":"conference"},"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-00380870","pdf_url":"https://centralesupelec.hal.science/hal-00380870/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":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://hal-centralesupelec.archives-ouvertes.fr/hal-00380870/file/Supelec471.pdf","pdf_url":"https://hal-centralesupelec.archives-ouvertes.fr/hal-00380870/file/Supelec471.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":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://centralesupelec.hal.science/hal-00380870/file/Supelec471.pdf","pdf_url":"https://centralesupelec.hal.science/hal-00380870/file/Supelec471.pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://hal-supelec.archives-ouvertes.fr/hal-00380870","pdf_url":"https://centralesupelec.hal.science/hal-00380870/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":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"score":0.78,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":21,"referenced_works":["https://openalex.org/W1520710862","https://openalex.org/W1554663460","https://openalex.org/W1574840339","https://openalex.org/W1576452626","https://openalex.org/W1603631609","https://openalex.org/W1646707810","https://openalex.org/W2007655795","https://openalex.org/W2062541405","https://openalex.org/W2072931156","https://openalex.org/W2104753538","https://openalex.org/W2105934661","https://openalex.org/W2109330238","https://openalex.org/W2116274100","https://openalex.org/W2123487311","https://openalex.org/W2132351269","https://openalex.org/W2133733518","https://openalex.org/W2790374560","https://openalex.org/W2794413559","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W4388297464"],"related_works":["https://openalex.org/W4206770590","https://openalex.org/W3191856393","https://openalex.org/W2760382975","https://openalex.org/W2745986669","https://openalex.org/W2379462184","https://openalex.org/W2349716249","https://openalex.org/W2146909562","https://openalex.org/W2120941928","https://openalex.org/W2062195135","https://openalex.org/W1611787488"],"abstract_inverted_index":{"This":[0,131],"paper":[1],"deals":[2],"with":[3],"value":[4,36,106],"function":[5,107],"and":[6,48,80,98,118,128,135,138],"Q-function":[7,113],"approximation":[8,83],"in":[9],"deterministic":[10],"Markovian":[11],"decision":[12],"processes.":[13],"A":[14],"general":[15,64],"statistical":[16],"framework":[17,132],"based":[18],"on":[19,58],"the":[20,35,40,51,55,86,105,112,119],"Kalman":[21],"filtering":[22],"paradigm":[23],"is":[24,28,93,133],"introduced.":[25],"Its":[26],"principle":[27],"to":[29,38,49],"adopt":[30],"a":[31,45,89,109,115],"parametric":[32],"representation":[33],"of":[34,54,91,108,114],"function,":[37],"model":[39],"associated":[41],"parameter":[42],"vector":[43],"as":[44],"random":[46],"variable":[47],"minimize":[50],"mean-squared":[52],"error":[53],"parameters":[56],"conditioned":[57],"past":[59],"observed":[60],"transitions.":[61],"From":[62],"this":[63],"framework,":[65],"which":[66,100],"will":[67],"be":[68],"called":[69,85],"Kalman":[72],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Temporal":[75],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Differences":[78],"(KTD),":[79],"using":[81],"an":[82],"scheme":[84],"unscented":[87],"transform,":[88],"family":[90],"algorithms":[92],"derived,":[94],"namely":[95],"KTD-V,":[96],"KTD-SARSA":[97],"KTD-Q,":[99],"aim":[101],"respectively":[102],"at":[103],"estimating":[104],"given":[110,116],"policy,":[111],"policy":[117],"optimal":[120],"Q-function.":[121],"The":[122],"proposed":[123],"approach":[124],"holds":[125],"for":[126],"linear":[127],"nonlinear":[129],"parameterization.":[130],"discussed":[134],"potential":[136],"advantages":[137],"shortcomings":[139],"are":[140],"highlighted.":[141]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2141562047","counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2024-12-10T13:20:56.262370","created_date":"2016-06-24"}