{"id":"https://openalex.org/W2164210234","doi":"https://doi.org/10.1109/ijcnn.2004.1380884","title":"A solving method for MDPs by minimizing variational free energy","display_name":"A solving method for MDPs by minimizing variational free energy","publication_year":2005,"publication_date":"2005-01-31","ids":{"openalex":"https://openalex.org/W2164210234","doi":"https://doi.org/10.1109/ijcnn.2004.1380884","mag":"2164210234"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2004.1380884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5071281836","display_name":"Junichiro Yoshimoto","orcid":"https://orcid.org/0000-0001-7995-0321"},"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"]},{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I4210086780"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"J. Yoshimoto","raw_affiliation_strings":["CREST Doya Project, Japan Science and Technology Agency, Ikoma, Nara, Japan","Nara Institute of Science and Technology, Ikoma, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"CREST Doya Project, Japan Science and Technology Agency, Ikoma, Nara, Japan","institution_ids":["https://openalex.org/I4210086780"]},{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072540019","display_name":"Shin Ishii","orcid":"https://orcid.org/0000-0001-9385-8230"},"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"]},{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I4210086780"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Ishii","raw_affiliation_strings":["CREST Doya Project, Japan Science and Technology Agency, Ikoma, Nara, Japan","Nara Institute of Science and Technology, Ikoma, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"CREST Doya Project, Japan Science and Technology Agency, Ikoma, Nara, Japan","institution_ids":["https://openalex.org/I4210086780"]},{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071281836"],"corresponding_institution_ids":["https://openalex.org/I4210086780","https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.16028834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"1817","last_page":"1822"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9916999936103821,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9879999756813049,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5970181226730347},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5694706439971924},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5424019694328308},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5299209952354431},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.5259711146354675},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.5103966593742371},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4718484878540039},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.46812525391578674},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4528560936450958},{"id":"https://openalex.org/keywords/linear-quadratic-gaussian-control","display_name":"Linear-quadratic-Gaussian control","score":0.43996939063072205},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.4361257255077362},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.37885063886642456},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.272970050573349},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26803433895111084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14687788486480713},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08513477444648743}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5970181226730347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5694706439971924},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5424019694328308},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5299209952354431},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.5259711146354675},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.5103966593742371},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4718484878540039},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.46812525391578674},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4528560936450958},{"id":"https://openalex.org/C204495892","wikidata":"https://www.wikidata.org/wiki/Q1798304","display_name":"Linear-quadratic-Gaussian control","level":3,"score":0.43996939063072205},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.4361257255077362},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.37885063886642456},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.272970050573349},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26803433895111084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14687788486480713},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08513477444648743},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2004.1380884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8799999952316284,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1485905671","https://openalex.org/W1510461155","https://openalex.org/W1576452626","https://openalex.org/W1646707810","https://openalex.org/W2013891788","https://openalex.org/W2028145673","https://openalex.org/W2082261506","https://openalex.org/W2103139809","https://openalex.org/W2105934661","https://openalex.org/W2113501460","https://openalex.org/W2119333483","https://openalex.org/W2119717200","https://openalex.org/W2124175081","https://openalex.org/W2135194391","https://openalex.org/W2139418546","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2161767008","https://openalex.org/W4214717370","https://openalex.org/W6678114464","https://openalex.org/W6683204974","https://openalex.org/W6683852811"],"related_works":["https://openalex.org/W1999291921","https://openalex.org/W4245839115","https://openalex.org/W2111439273","https://openalex.org/W2144691561","https://openalex.org/W2107169685","https://openalex.org/W2115005925","https://openalex.org/W2101783086","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,11,25,30,70,81],"novel":[3],"approach":[4],"to":[5,45],"acquire":[6],"the":[7,40,48],"optimal":[8,49],"policy":[9,34,50,72],"for":[10],"continuous":[12],"Markov":[13],"decision":[14],"process.":[15],"Based":[16],"on":[17],"an":[18],"analogy":[19],"from":[20],"statistical":[21],"mechanics,":[22],"we":[23],"introduce":[24],"variational":[26,41],"free":[27,42],"energy":[28],"over":[29],"policy.":[31],"A":[32],"good":[33],"can":[35,56,73],"be":[36,57,74],"obtained":[37,58,75],"by":[38,59,76],"minimizing":[39],"energy.":[43],"According":[44],"our":[46],"approach,":[47],"in":[51,67],"linear":[52],"quadratic":[53],"regulator":[54],"problems":[55],"using":[60],"Kalman":[61],"filtering":[62],"and":[63],"smoothing":[64],"techniques.":[65],"Even":[66],"non-linear":[68],"problems,":[69],"semi-optimal":[71],"Monte":[77],"Carlo":[78],"technique":[79],"with":[80],"Gaussian":[82],"process":[83],"method.":[84]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}