{"id":"https://openalex.org/W2168342951","doi":"https://doi.org/10.1162/089976602753712972","title":"Multiple Model-Based Reinforcement Learning","display_name":"Multiple Model-Based Reinforcement Learning","publication_year":2002,"publication_date":"2002-06-01","ids":{"openalex":"https://openalex.org/W2168342951","doi":"https://doi.org/10.1162/089976602753712972","mag":"2168342951","pmid":"https://pubmed.ncbi.nlm.nih.gov/12020450"},"language":"en","primary_location":{"id":"doi:10.1162/089976602753712972","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089976602753712972","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"],"host_organization_lineage_names":["The MIT Press"],"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/A5004840638","display_name":"Kenji Doya","orcid":"https://orcid.org/0000-0002-2446-6820"},"institutions":[{"id":"https://openalex.org/I46980622","display_name":"Kyoto Seika University","ror":"https://ror.org/05g4f0342","country_code":"JP","type":"education","lineage":["https://openalex.org/I46980622"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kenji Doya","raw_affiliation_strings":["Human Information Science Laboratories, ATR International, Seika, Soraku, Kyoto 619-0288, Japan; CREST, Japan Science and Technology Corporation, Seika, Soraku, Kyoto 619-0288, Japan; Kawato Dynamic Brain Project, ERATO, Japan Science and Technology Corporation, Seika, Soraku, Kyoto 619-0288, Japan; and Nara Institute of Science and Technology, Ikoma, Nara 630-0101, Japan,","CREST, Japan Science and Technology Corporation, Seika, Soraku, Kyoto 619-0288, Japan","Nara Institute of Science and Technology, Ikoma, Nara 630-0101, Japan,","Human Information Science Laboratories, ATR International, Seika, Soraku, Kyoto 619-0288, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Information Science Laboratories, ATR International, Seika, Soraku, Kyoto 619-0288, Japan; CREST, Japan Science and Technology Corporation, Seika, Soraku, Kyoto 619-0288, Japan; Kawato Dynamic Brain Project, ERATO, Japan Science and Technology Corporation, Seika, Soraku, Kyoto 619-0288, Japan; and Nara Institute of Science and Technology, Ikoma, Nara 630-0101, Japan,","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"CREST, Japan Science and Technology Corporation, Seika, Soraku, Kyoto 619-0288, Japan","institution_ids":["https://openalex.org/I46980622"]},{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Nara 630-0101, Japan,","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Human Information Science Laboratories, ATR International, Seika, Soraku, Kyoto 619-0288, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085590930","display_name":"Kazuyuki Samejima","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kazuyuki Samejima","raw_affiliation_strings":["Human Information Science Laboratories, ATR International, Seika, Soraku, Kyoto 619-0288, Japan, and Kawato Dynamic Brain Project, ERATO, Japan Science and Technology Corporation, Seika, Soraku, Kyoto 619-0288, Japan,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Information Science Laboratories, ATR International, Seika, Soraku, Kyoto 619-0288, Japan, and Kawato Dynamic Brain Project, ERATO, Japan Science and Technology Corporation, Seika, Soraku, Kyoto 619-0288, Japan,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002301447","display_name":"Ken-ichi Katagiri","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ken-ichi Katagiri","raw_affiliation_strings":["ATR Human Information Processing Research Laboratories, Seika, Soraku, Kyoto 619-0288, Japan, and Nara Institute of Science and Technology, Ikoma, Nara 630-0101, Japan,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Human Information Processing Research Laboratories, Seika, Soraku, Kyoto 619-0288, Japan, and Nara Institute of Science and Technology, Ikoma, Nara 630-0101, Japan,","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028840283","display_name":"Mitsuo Kawato","orcid":"https://orcid.org/0000-0001-8185-1197"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Mitsuo Kawato","raw_affiliation_strings":["Human Information Science Laboratories, ATR International, Seika, Soraku, Kyoto 619-0288, Japan; Kawato Dynamic Brain Project, ERATO, Japan Science and Technology Corporation, Seika, Soraku, Kyoto 619-0288, Japan; and Nara Institute of Science and Technology, Ikoma, Nara 630-0101, Japan,","Human Information Science Laboratories, ATR International, Seika, Soraku, Kyoto 619-0288, Japan","Nara Institute of Science and Technology, Ikoma, Nara 630-0101, Japan,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Information Science Laboratories, ATR International, Seika, Soraku, Kyoto 619-0288, Japan; Kawato Dynamic Brain Project, ERATO, Japan Science and Technology Corporation, Seika, Soraku, Kyoto 619-0288, Japan; and Nara Institute of Science and Technology, Ikoma, Nara 630-0101, Japan,","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Human Information Science Laboratories, ATR International, Seika, Soraku, Kyoto 619-0288, Japan","institution_ids":[]},{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Nara 630-0101, Japan,","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002301447","https://openalex.org/A5004840638","https://openalex.org/A5028840283","https://openalex.org/A5085590930"],"corresponding_institution_ids":["https://openalex.org/I46980622","https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":14.9224,"has_fulltext":false,"cited_by_count":484,"citation_normalized_percentile":{"value":0.99137706,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"14","issue":"6","first_page":"1347","last_page":"1369"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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/T10581","display_name":"Neural dynamics and brain function","score":0.987500011920929,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9603000283241272,"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/softmax-function","display_name":"Softmax function","score":0.933340311050415},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8768059015274048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5992341637611389},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5389701724052429},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5312680006027222},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5063983201980591},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.46186476945877075},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4477262794971466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4297179877758026},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.34387925267219543},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.32954955101013184},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2749559283256531},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18274179100990295},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15351933240890503}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.933340311050415},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8768059015274048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5992341637611389},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5389701724052429},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5312680006027222},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5063983201980591},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.46186476945877075},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4477262794971466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4297179877758026},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.34387925267219543},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32954955101013184},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2749559283256531},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18274179100990295},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15351933240890503},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[{"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":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008606","descriptor_name":"Mental Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008606","descriptor_name":"Mental Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008606","descriptor_name":"Mental Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","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}],"locations_count":2,"locations":[{"id":"doi:10.1162/089976602753712972","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089976602753712972","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"],"host_organization_lineage_names":["The MIT Press"],"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:12020450","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12020450","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":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.6000000238418579,"display_name":"Life in Land"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309369","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1539216098","https://openalex.org/W1632095576","https://openalex.org/W1779974355","https://openalex.org/W1968164759","https://openalex.org/W1973615355","https://openalex.org/W1999642580","https://openalex.org/W2012036715","https://openalex.org/W2043385819","https://openalex.org/W2064527179","https://openalex.org/W2069913713","https://openalex.org/W2091565802","https://openalex.org/W2097815751","https://openalex.org/W2097861969","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2103617625","https://openalex.org/W2109910161","https://openalex.org/W2113501460","https://openalex.org/W2122775046","https://openalex.org/W2123956999","https://openalex.org/W2142789491","https://openalex.org/W2144104178","https://openalex.org/W2150884987","https://openalex.org/W2158548602","https://openalex.org/W2160371091","https://openalex.org/W2167647761","https://openalex.org/W2172116616","https://openalex.org/W2911283634","https://openalex.org/W2912185451","https://openalex.org/W2914656440","https://openalex.org/W3041202696"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W2980176872","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"We":[0,104],"propose":[1],"a":[2,26,56,61,126,131,139,147],"modular":[3],"reinforcement":[4,17,62,101],"learning":[5,18,63,94,102],"architecture":[6],"for":[7,107,122,135],"nonlinear,":[8,140],"nonstationary":[9,127,141],"control":[10,142],"tasks,":[11],"which":[12,53,68],"we":[13],"call":[14],"multiple":[15,30,49,86],"model-based":[16],"(MMRL).":[19],"The":[20,44,65,116],"basic":[21],"idea":[22],"is":[23,46,69,79],"to":[24,81,91],"decompose":[25],"complex":[27],"task":[28,129,143],"into":[29],"domains":[31],"in":[32,125,130,138],"space":[33],"and":[34,60,99,112,134],"time":[35],"based":[36],"on":[37],"the":[38,41,72,76,83,93,96,100],"predictability":[39],"of":[40,48,52,55,75,85,95,118,144],"environmental":[42],"dynamics.":[43],"system":[45],"composed":[47],"modules,":[50,87],"each":[51],"consists":[54],"state":[57],"prediction":[58,77,97],"model":[59],"controller.":[64],"\"responsibility":[66],"signal,\"":[67],"given":[70],"by":[71],"softmax":[73],"function":[74],"errors,":[78],"used":[80],"weight":[82],"outputs":[84],"as":[88,90],"well":[89],"gate":[92],"models":[98],"controllers.":[103],"formulate":[105],"MMRL":[106,119],"both":[108],"discrete-time,":[109],"finite-state":[110],"case":[111,124,137],"continuous-time,":[113],"continuous-state":[114],"case.":[115],"performance":[117],"was":[120],"demonstrated":[121],"discrete":[123],"hunting":[128],"grid":[132],"world":[133],"continuous":[136],"swinging":[145],"up":[146],"pendulum":[148],"with":[149],"variable":[150],"physical":[151],"parameters.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":41},{"year":2020,"cited_by_count":31},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":21},{"year":2015,"cited_by_count":28},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":21},{"year":2012,"cited_by_count":15}],"updated_date":"2026-06-02T09:04:35.204637","created_date":"2025-10-10T00:00:00"}