{"id":"https://openalex.org/W2120772353","doi":"https://doi.org/10.1162/089976604772744884","title":"Kalman Filter Control Embedded into the Reinforcement Learning Framework","display_name":"Kalman Filter Control Embedded into the Reinforcement Learning Framework","publication_year":2004,"publication_date":"2004-02-09","ids":{"openalex":"https://openalex.org/W2120772353","doi":"https://doi.org/10.1162/089976604772744884","mag":"2120772353","pmid":"https://pubmed.ncbi.nlm.nih.gov/15022677"},"language":"en","primary_location":{"id":"doi:10.1162/089976604772744884","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089976604772744884","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718","https://openalex.org/P4310316440"],"host_organization_lineage_names":["The MIT Press","Massachusetts Institute of Technology"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5053869649","display_name":"Istv\u00e1n Szita","orcid":null},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Istv\u00e1n Szita","raw_affiliation_strings":["Department of Information Systems, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1/C, H-1117 Budapest, Hungary,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1/C, H-1117 Budapest, Hungary,","institution_ids":["https://openalex.org/I106118109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066832439","display_name":"Andr\u00e1s L\u00f6rincz","orcid":"https://orcid.org/0000-0002-1280-3447"},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Andr\u00e1s L\u0151rincz","raw_affiliation_strings":["Department of Information Systems, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1/C, H-1117 Budapest, Hungary,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1/C, H-1117 Budapest, Hungary,","institution_ids":["https://openalex.org/I106118109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I106118109"],"apc_list":null,"apc_paid":null,"fwci":0.9511,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.73457801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"16","issue":"3","first_page":"491","last_page":"499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12805","display_name":"Cognitive Science and Mapping","score":0.987500011920929,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.8101359009742737},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6793621778488159},{"id":"https://openalex.org/keywords/extended-kalman-filter","display_name":"Extended Kalman filter","score":0.6533945798873901},{"id":"https://openalex.org/keywords/invariant-extended-kalman-filter","display_name":"Invariant extended Kalman filter","score":0.6253719329833984},{"id":"https://openalex.org/keywords/recursion","display_name":"Recursion (computer science)","score":0.5800010561943054},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5570039749145508},{"id":"https://openalex.org/keywords/fast-kalman-filter","display_name":"Fast Kalman filter","score":0.5512849688529968},{"id":"https://openalex.org/keywords/ensemble-kalman-filter","display_name":"Ensemble Kalman filter","score":0.5388637781143188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5387149453163147},{"id":"https://openalex.org/keywords/alpha-beta-filter","display_name":"Alpha beta filter","score":0.5214909315109253},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.448606014251709},{"id":"https://openalex.org/keywords/kernel-adaptive-filter","display_name":"Kernel adaptive filter","score":0.4455980956554413},{"id":"https://openalex.org/keywords/linear-quadratic-gaussian-control","display_name":"Linear-quadratic-Gaussian control","score":0.4149208664894104},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4099717140197754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34912997484207153},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3086131513118744},{"id":"https://openalex.org/keywords/moving-horizon-estimation","display_name":"Moving horizon estimation","score":0.26669830083847046},{"id":"https://openalex.org/keywords/filter-design","display_name":"Filter design","score":0.25401657819747925},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.20668208599090576},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10747790336608887}],"concepts":[{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.8101359009742737},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6793621778488159},{"id":"https://openalex.org/C206833254","wikidata":"https://www.wikidata.org/wiki/Q5421817","display_name":"Extended Kalman filter","level":3,"score":0.6533945798873901},{"id":"https://openalex.org/C8639503","wikidata":"https://www.wikidata.org/wiki/Q6059511","display_name":"Invariant extended Kalman filter","level":4,"score":0.6253719329833984},{"id":"https://openalex.org/C168773036","wikidata":"https://www.wikidata.org/wiki/Q264164","display_name":"Recursion (computer science)","level":2,"score":0.5800010561943054},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5570039749145508},{"id":"https://openalex.org/C150679823","wikidata":"https://www.wikidata.org/wiki/Q5436946","display_name":"Fast Kalman filter","level":4,"score":0.5512849688529968},{"id":"https://openalex.org/C79334102","wikidata":"https://www.wikidata.org/wiki/Q3072268","display_name":"Ensemble Kalman filter","level":4,"score":0.5388637781143188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5387149453163147},{"id":"https://openalex.org/C11588082","wikidata":"https://www.wikidata.org/wiki/Q4735154","display_name":"Alpha beta filter","level":5,"score":0.5214909315109253},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.448606014251709},{"id":"https://openalex.org/C13107197","wikidata":"https://www.wikidata.org/wiki/Q6394192","display_name":"Kernel adaptive filter","level":4,"score":0.4455980956554413},{"id":"https://openalex.org/C204495892","wikidata":"https://www.wikidata.org/wiki/Q1798304","display_name":"Linear-quadratic-Gaussian control","level":3,"score":0.4149208664894104},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4099717140197754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34912997484207153},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3086131513118744},{"id":"https://openalex.org/C50050547","wikidata":"https://www.wikidata.org/wiki/Q6927137","display_name":"Moving horizon estimation","level":4,"score":0.26669830083847046},{"id":"https://openalex.org/C22597639","wikidata":"https://www.wikidata.org/wiki/Q5449227","display_name":"Filter design","level":3,"score":0.25401657819747925},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.20668208599090576},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10747790336608887}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D008959","descriptor_name":"Models, Neurological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008959","descriptor_name":"Models, Neurological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008959","descriptor_name":"Models, Neurological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1162/089976604772744884","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089976604772744884","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718","https://openalex.org/P4310316440"],"host_organization_lineage_names":["The MIT Press","Massachusetts Institute of Technology"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:15022677","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15022677","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":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural computation","raw_type":"Journal Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.1099","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.1099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eotvoscollegium.hu/~szityu/papers/SzitaLorincz03Kalman.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.6145","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.6145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eotvoscollegium.hu/~szityu/papers/SzitaLorincz03Kalman.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320326184","display_name":"Hungarian Science Foundation","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W10933137","https://openalex.org/W1501869728","https://openalex.org/W1506298490","https://openalex.org/W1507713211","https://openalex.org/W1580901834","https://openalex.org/W1646707810","https://openalex.org/W1652173018","https://openalex.org/W1854034080","https://openalex.org/W1980440818","https://openalex.org/W1983628429","https://openalex.org/W2000775105","https://openalex.org/W2001101397","https://openalex.org/W2023699349","https://openalex.org/W2032677875","https://openalex.org/W2037120890","https://openalex.org/W2112376384","https://openalex.org/W2117726420","https://openalex.org/W2119885245","https://openalex.org/W2121832485","https://openalex.org/W2131385612","https://openalex.org/W2137466452","https://openalex.org/W2139418546","https://openalex.org/W2148848065","https://openalex.org/W2170900501"],"related_works":["https://openalex.org/W2543755345","https://openalex.org/W2765341233","https://openalex.org/W2371898751","https://openalex.org/W1986956626","https://openalex.org/W2361755829","https://openalex.org/W2388798063","https://openalex.org/W2374292697","https://openalex.org/W2371115672","https://openalex.org/W2043845914","https://openalex.org/W2240989071"],"abstract_inverted_index":{"There":[0],"is":[1,47,55,95],"a":[2,58,91],"growing":[3],"interest":[4],"in":[5,10],"using":[6,75],"Kalman":[7,17,38,64],"filter":[8,18,39,65],"models":[9,19],"brain":[11],"modeling.":[12],"The":[13,31],"question":[14],"arises":[15],"whether":[16],"can":[20],"be":[21],"used":[22],"on-line":[23,69],"not":[24,48],"only":[25],"for":[26,29,50,87],"estimation":[27,70,89],"but":[28],"control.":[30],"usual":[32],"method":[33],"of":[34,37,42,61,71,100],"optimal":[35,72],"control":[36,73],"makes":[40],"use":[41],"off-line":[43],"backward":[44],"recursion,":[45],"which":[46,94],"satisfactory":[49],"this":[51,80],"purpose.":[52],"Here,":[53],"it":[54],"shown":[56],"that":[57],"slight":[59],"modification":[60],"the":[62,68,83,98,101],"linear-quadratic-gaussian":[63],"model":[66],"allows":[67],"by":[74,97],"reinforcement":[76],"learning":[77,85],"and":[78],"overcomes":[79],"difficulty.":[81],"Moreover,":[82],"emerging":[84],"rule":[86],"value":[88,102],"exhibits":[90],"Hebbian":[92],"form,":[93],"weighted":[96],"error":[99],"estimation.":[103]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}