{"id":"https://openalex.org/W2145075441","doi":"https://doi.org/10.1162/neco.2010.01-09-948","title":"Posterior Weighted Reinforcement Learning with State Uncertainty","display_name":"Posterior Weighted Reinforcement Learning with State Uncertainty","publication_year":2010,"publication_date":"2010-01-25","ids":{"openalex":"https://openalex.org/W2145075441","doi":"https://doi.org/10.1162/neco.2010.01-09-948","mag":"2145075441","pmid":"https://pubmed.ncbi.nlm.nih.gov/20100078"},"language":"en","primary_location":{"id":"doi:10.1162/neco.2010.01-09-948","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco.2010.01-09-948","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/A5109231056","display_name":"Tobias Larsen","orcid":null},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tobias Larsen","raw_affiliation_strings":["Department of Computer Science, University of Bristol, Bristol, BS8 1UB, U.K","Department of Computer Science, University of Bristol, Bristol BS8 1UB, U.K.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bristol, Bristol, BS8 1UB, U.K","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"Department of Computer Science, University of Bristol, Bristol BS8 1UB, U.K.#TAB#","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040706665","display_name":"David S. Leslie","orcid":"https://orcid.org/0000-0001-5253-7676"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David S. Leslie","raw_affiliation_strings":["Department of Mathematics, University of Bristol, Bristol, BS8 1TW, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Bristol, Bristol, BS8 1TW, U.K","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111404838","display_name":"Edmund J. Collins","orcid":null},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Edmund J. Collins","raw_affiliation_strings":["Department of Mathematics, University of Bristol, Bristol, BS8 1TW, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Bristol, Bristol, BS8 1TW, U.K","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049095056","display_name":"Rafa\u0142 Bogacz","orcid":"https://orcid.org/0000-0002-8994-1661"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rafal Bogacz","raw_affiliation_strings":["Department of Computer Science, University of Bristol, Bristol, BS8 1UB, U.K","Department of Computer Science, University of Bristol, Bristol BS8 1UB, U.K.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bristol, Bristol, BS8 1UB, U.K","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"Department of Computer Science, University of Bristol, Bristol BS8 1UB, U.K.#TAB#","institution_ids":["https://openalex.org/I36234482"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36234482"],"apc_list":null,"apc_paid":null,"fwci":0.4497,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.66447258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"22","issue":"5","first_page":"1149","last_page":"1179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9998999834060669,"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":0.9998999834060669,"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/T10241","display_name":"Functional Brain Connectivity Studies","score":0.9969000220298767,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9937000274658203,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8252165913581848},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6073402762413025},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5363467931747437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5137201547622681},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.49310633540153503},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47881990671157837},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4369164705276489},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4270312786102295},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4062046408653259},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24420085549354553},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2325846254825592},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10650411248207092}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8252165913581848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6073402762413025},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5363467931747437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5137201547622681},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.49310633540153503},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47881990671157837},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4369164705276489},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4270312786102295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4062046408653259},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24420085549354553},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2325846254825592},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10650411248207092},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001921","descriptor_name":"Brain","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D001921","descriptor_name":"Brain","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D001921","descriptor_name":"Brain","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004777","descriptor_name":"Environment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004777","descriptor_name":"Environment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004777","descriptor_name":"Environment","qualifier_ui":null,"qualifier_name":null,"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":"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":"D009434","descriptor_name":"Neural Pathways","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D009434","descriptor_name":"Neural Pathways","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D009434","descriptor_name":"Neural Pathways","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1162/neco.2010.01-09-948","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco.2010.01-09-948","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:20100078","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20100078","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},{"id":"pmh:oai:research-information.bris.ac.uk:openaire_cris_publications/1e3216d6-e0a4-41d3-af8c-050de307c6f6","is_oa":false,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/1e3216d6-e0a4-41d3-af8c-050de307c6f6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Larsen, T, Leslie, D S, Collins, EJ & Bogacz, R 2010, 'Posterior weighted reinforcement learning with state uncertainty', Neural Computation, vol. 22, no. 5, pp. 1149 - 1179. https://doi.org/10.1162/neco.2010.01-09-948","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:research-information.bris.ac.uk:publications/1e3216d6-e0a4-41d3-af8c-050de307c6f6","is_oa":false,"landing_page_url":"http://www.cs.bris.ac.uk/Publications/pub_master.jsp?id=2001076","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Larsen, T, Leslie, D S, Collins, EJ & Bogacz, R 2010, 'Posterior weighted reinforcement learning with state uncertainty', Neural Computation, vol. 22, no. 5, pp. 1149 - 1179. https://doi.org/10.1162/neco.2010.01-09-948","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2686334257","display_name":null,"funder_award_id":"EP/C516303/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W634687855","https://openalex.org/W1491706803","https://openalex.org/W1515851193","https://openalex.org/W1522115819","https://openalex.org/W1544729927","https://openalex.org/W1583837637","https://openalex.org/W1652173018","https://openalex.org/W1686266550","https://openalex.org/W1965274432","https://openalex.org/W1968832734","https://openalex.org/W1980871601","https://openalex.org/W1991363287","https://openalex.org/W1994728257","https://openalex.org/W2029786645","https://openalex.org/W2042948989","https://openalex.org/W2043608504","https://openalex.org/W2049633694","https://openalex.org/W2061350749","https://openalex.org/W2063716754","https://openalex.org/W2091789872","https://openalex.org/W2098534820","https://openalex.org/W2100677568","https://openalex.org/W2107564936","https://openalex.org/W2108393070","https://openalex.org/W2109059823","https://openalex.org/W2116459397","https://openalex.org/W2121863487","https://openalex.org/W2122028729","https://openalex.org/W2122066429","https://openalex.org/W2123429050","https://openalex.org/W2128775537","https://openalex.org/W2134825267","https://openalex.org/W2135915258","https://openalex.org/W2136582516","https://openalex.org/W2144095870","https://openalex.org/W2149607218","https://openalex.org/W2150339816","https://openalex.org/W2150367061","https://openalex.org/W2152362761","https://openalex.org/W2154070811","https://openalex.org/W2158640361","https://openalex.org/W2160067530","https://openalex.org/W2163647009","https://openalex.org/W2167987951","https://openalex.org/W2168359464","https://openalex.org/W2524389969","https://openalex.org/W2531891978","https://openalex.org/W2585198072","https://openalex.org/W2597289420","https://openalex.org/W2999905431","https://openalex.org/W3015736691","https://openalex.org/W3041202696","https://openalex.org/W3129711340","https://openalex.org/W4212774754","https://openalex.org/W4214717370","https://openalex.org/W4229926969","https://openalex.org/W4235391064","https://openalex.org/W4254376918","https://openalex.org/W4302033506"],"related_works":["https://openalex.org/W1980276475","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W1914583973","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,85],"models":[2],"generally":[3],"assume":[4],"that":[5,10,30,33,89,116,173],"a":[6,12,28,69,131,154,157,162,195],"stimulus":[7,41],"is":[8,25,42,46,50,117,191,220],"presented":[9],"allows":[11],"learner":[13,155],"to":[14,56,68,98,148,179,193,205],"unambiguously":[15,66],"identify":[16],"the":[17,22,40,61,72,77,92,96,99,104,114,121,140,149,198,214,217],"state":[18,47,70,81,102,143,166],"of":[19,71,79,103,142,197,213,225],"nature,":[20],"and":[21,94,183,222],"reward":[23,63,97,122,158,181],"received":[24],"drawn":[26],"from":[27],"distribution":[29],"depends":[31],"on":[32],"state.":[34],"However,":[35],"in":[36,83,107,125,138,216],"any":[37],"natural":[38],"environment,":[39],"noisy.":[43],"When":[44],"there":[45],"uncertainty,":[48],"it":[49],"no":[51],"longer":[52],"immediately":[53],"obvious":[54],"how":[55],"perform":[57],"reinforcement":[58,84,136],"learning,":[59,137],"since":[60],"observed":[62,150],"cannot":[64],"be":[65,194,206],"allocated":[67],"environment.":[73],"This":[74],"letter":[75],"addresses":[76],"problem":[78],"incorporating":[80],"uncertainty":[82,93],"models.":[86],"We":[87,128,170],"show":[88,171],"simply":[90],"ignoring":[91],"allocating":[95],"most":[100],"likely":[101],"environment":[105],"results":[106,124],"incorrect":[108,126],"value":[109],"estimates.":[110,127],"Furthermore,":[111],"using":[112],"only":[113],"information":[115],"available":[118],"before":[119],"observing":[120],"also":[123],"therefore":[129],"introduce":[130],"new":[132],"technique,":[133],"posterior":[134],"weighted":[135],"which":[139],"estimates":[141,182],"probabilities":[144],"are":[145,228],"updated":[146],"according":[147],"rewards":[151],"(e.g.,":[152],"if":[153],"observes":[156],"usually":[159],"associated":[160],"with":[161,186],"particular":[163],"state,":[164],"this":[165,174,185],"becomes":[167],"more":[168],"likely).":[169],"analytically":[172],"modified":[175],"algorithm":[176,190,215],"can":[177],"converge":[178],"correct":[180],"confirm":[184],"numerical":[187],"experiments.":[188],"The":[189],"shown":[192],"variant":[196],"expectation-maximization":[199],"algorithm,":[200],"allowing":[201],"rigorous":[202],"convergence":[203],"analyses":[204],"carried":[207],"out.":[208],"A":[209],"possible":[210],"neural":[211],"implementation":[212],"cortico-basal-ganglia-thalamic":[218],"network":[219],"presented,":[221],"experimental":[223],"predictions":[224],"our":[226],"model":[227],"discussed.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2016-06-24T00:00:00"}