{"id":"https://openalex.org/W7225761507","doi":"https://doi.org/10.64898/2026.11.07.765111","title":"The neural circuit implementation of distributional reinforcement learning","display_name":"The neural circuit implementation of distributional reinforcement learning","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225761507","doi":"https://doi.org/10.64898/2026.11.07.765111"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.07.765111","doi":"https://doi.org/10.64898/2026.11.07.765111","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.07.765111","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.64898/2026.11.07.765111","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053312187","display_name":"Sara Matias","orcid":"https://orcid.org/0000-0002-7432-6754","observed_orcids":["https://orcid.org/0000-0002-7432-6754"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sara Matias","raw_affiliation_strings":["Harvard University;"],"raw_orcid":"https://orcid.org/0000-0002-7432-6754","affiliations":[{"raw_affiliation_string":"Harvard University;","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084741641","display_name":"Camille E. Rull\u00e1n Bux\u00f3","orcid":"https://orcid.org/0000-0003-4026-1224","observed_orcids":["https://orcid.org/0000-0003-4026-1224"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Camille Rull\u00e1n Bux\u00f3","raw_affiliation_strings":["Harvard Medical School"],"raw_orcid":"https://orcid.org/0000-0003-4026-1224","affiliations":[{"raw_affiliation_string":"Harvard Medical School","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161388946","display_name":"Shudi Xu","orcid":"https://orcid.org/0009-0000-2573-6856","observed_orcids":["https://orcid.org/0009-0000-2573-6856"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shudi Xu","raw_affiliation_strings":["Harvard University;"],"raw_orcid":"https://orcid.org/0009-0000-2573-6856","affiliations":[{"raw_affiliation_string":"Harvard University;","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061621316","display_name":"Malcolm Campbell","orcid":"https://orcid.org/0000-0002-1971-8923","observed_orcids":["https://orcid.org/0000-0002-1971-8923","https://orcid.org/0000-0001-7376-5301","https://orcid.org/0000-0002-6125-5731","https://orcid.org/0000-0002-7058-4318"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Malcolm G Campbell","raw_affiliation_strings":["Harvard University;"],"raw_orcid":"https://orcid.org/0000-0002-1971-8923","affiliations":[{"raw_affiliation_string":"Harvard University;","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020543607","display_name":"Adam S. Lowet","orcid":"https://orcid.org/0000-0003-4527-3937","observed_orcids":["https://orcid.org/0000-0003-4527-3937"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam S Lowet","raw_affiliation_strings":["Harvard University;"],"raw_orcid":"https://orcid.org/0000-0003-4527-3937","affiliations":[{"raw_affiliation_string":"Harvard University;","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002768492","display_name":"Xiaotang Lu","orcid":"https://orcid.org/0000-0002-8575-5394","observed_orcids":["https://orcid.org/0000-0002-8575-5394"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaotang Lu","raw_affiliation_strings":["Harvard University;"],"raw_orcid":"https://orcid.org/0000-0002-8575-5394","affiliations":[{"raw_affiliation_string":"Harvard University;","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101781080","display_name":"Yuelong Wu","orcid":"https://orcid.org/0000-0003-0075-1237","observed_orcids":["https://orcid.org/0000-0003-0075-1237","https://orcid.org/0000-0002-4417-8236"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuelong Wu","raw_affiliation_strings":["Harvard University;"],"raw_orcid":"https://orcid.org/0000-0003-0075-1237","affiliations":[{"raw_affiliation_string":"Harvard University;","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036909597","display_name":"Richard Lee Schalek","orcid":"https://orcid.org/0000-0003-2450-1718","observed_orcids":["https://orcid.org/0000-0003-2450-1718"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Schalek","raw_affiliation_strings":["Harvard University;"],"raw_orcid":"https://orcid.org/0000-0003-2450-1718","affiliations":[{"raw_affiliation_string":"Harvard University;","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037495122","display_name":"Jeff William Lichtman","orcid":"https://orcid.org/0000-0002-0208-3212","observed_orcids":["https://orcid.org/0000-0002-0208-3212"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeff W Lichtman","raw_affiliation_strings":["Harvard University;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University;","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038901409","display_name":"Mitsuko Watabe\u2010Uchida","orcid":"https://orcid.org/0000-0001-7864-754X","observed_orcids":["https://orcid.org/0000-0001-7864-754X"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitsuko Watabe-Uchida","raw_affiliation_strings":["Harvard University;"],"raw_orcid":"https://orcid.org/0000-0001-7864-754X","affiliations":[{"raw_affiliation_string":"Harvard University;","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037361379","display_name":"Jan Drugowitsch","orcid":"https://orcid.org/0000-0002-7846-0408","observed_orcids":["https://orcid.org/0000-0002-7846-0408"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jan Drugowitsch","raw_affiliation_strings":["Harvard Medical School"],"raw_orcid":"https://orcid.org/0000-0002-7846-0408","affiliations":[{"raw_affiliation_string":"Harvard Medical School","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085316776","display_name":"Naoshige Uchida","orcid":"https://orcid.org/0000-0002-5755-9409","observed_orcids":["https://orcid.org/0000-0002-5755-9409"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Naoshige Uchida","raw_affiliation_strings":["Harvard University;"],"raw_orcid":"https://orcid.org/0000-0002-5755-9409","affiliations":[{"raw_affiliation_string":"Harvard University;","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5085316776"],"corresponding_institution_ids":["https://openalex.org/I136199984"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10056","display_name":"Neurotransmitter Receptor Influence on Behavior","score":0.875,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular 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/T10056","display_name":"Neurotransmitter Receptor Influence on Behavior","score":0.875,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular 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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.08640000224113464,"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":0.01489999983459711,"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":[],"concepts":[{"id":"https://openalex.org/C513476851","wikidata":"https://www.wikidata.org/wiki/Q170304","display_name":"Dopamine","level":2,"score":0.623199999332428},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6129000186920166},{"id":"https://openalex.org/C2778187257","wikidata":"https://www.wikidata.org/wiki/Q464210","display_name":"Basal ganglia","level":3,"score":0.5975000262260437},{"id":"https://openalex.org/C552161191","wikidata":"https://www.wikidata.org/wiki/Q185080","display_name":"Midbrain","level":3,"score":0.5175999999046326},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.5037000179290771},{"id":"https://openalex.org/C2780062018","wikidata":"https://www.wikidata.org/wiki/Q1319792","display_name":"Striatum","level":3,"score":0.4790000021457672},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4659000039100647},{"id":"https://openalex.org/C2776743251","wikidata":"https://www.wikidata.org/wiki/Q1319792","display_name":"Ventral striatum","level":4,"score":0.46549999713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46380001306533813},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.3702000081539154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3319999873638153},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.30820000171661377},{"id":"https://openalex.org/C118403218","wikidata":"https://www.wikidata.org/wiki/Q43283","display_name":"Biological neural network","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C140530291","wikidata":"https://www.wikidata.org/wiki/Q1225063","display_name":"Dorsum","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.07.765111","doi":"https://doi.org/10.64898/2026.11.07.765111","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.07.765111","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.07.765111","doi":"https://doi.org/10.64898/2026.11.07.765111","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.07.765111","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Distributional":[0],"reinforcement":[1],"learning":[2,90],"(RL)":[3],"algorithms":[4],"outperform":[5],"traditional":[6],"RL":[7,41],"by":[8,109,186],"representing":[9],"the":[10,45,50,80,107,150,153,163,166,178,183],"full":[11],"probability":[12],"distribution":[13,145],"of":[14,49,58,98,114,160,168,194,199,209],"future":[15],"outcomes":[16],"rather":[17],"than":[18],"its":[19],"mean.":[20],"Neural":[21],"signatures":[22],"consistent":[23],"with":[24,118],"distributional":[25,40,128,173,188],"coding":[26],"have":[27],"been":[28],"observed":[29],"in":[30,34,136,162,191],"dopamine":[31,104,115,123,140,196],"neurons":[32,197],"and":[33,72,84,91,152],"striatal":[35,202],"value":[36,169],"representations.":[37],"However,":[38],"how":[39,56,79,85,96],"is":[42,147],"implemented":[43],"within":[44],"anatomical":[46,158],"circuit":[47],"organization":[48],"basal":[51,184],"ganglia":[52,185],"remains":[53],"unknown.":[54],"Uncovering":[55],"representations":[57,87,97],"outcome":[59,99],"distributions":[60,100],"are":[61,101,133],"organized":[62,102],"across":[63,103],"brain":[64,81],"circuits":[65],"has":[66],"broad":[67],"implications":[68],"for":[69,172,182],"both":[70],"fundamental":[71],"clinical":[73],"neuroscience,":[74],"providing":[75],"new":[76],"insights":[77],"into":[78],"represents":[82],"uncertainty":[83],"these":[86],"shape":[88],"risk-sensitive":[89],"decision-making.":[92],"Here,":[93],"we":[94],"investigated":[95],"projections":[105],"to":[106,205],"striatum":[108],"combining":[110],"striatum-wide":[111],"fiber":[112],"photometry":[113],"axonal":[116],"activity":[117],"Neuropixels":[119],"recordings":[120],"from":[121],"projection-defined":[122],"neurons.":[124],"We":[125],"found":[126],"that":[127,143],"reward":[129,144],"prediction":[130,189],"error":[131],"signals":[132],"preferentially":[134],"encoded":[135],"lateral":[137],"ventral":[138,151],"striatum-projecting":[139],"neurons,":[141],"but":[142],"information":[146],"shared":[148],"between":[149],"dorsal":[154],"striatum.":[155],"Additionally,":[156],"an":[157],"gradient":[159],"optimism":[161],"midbrain":[164],"supports":[165],"diversity":[167],"predictions":[170],"required":[171],"RL.":[174],"Our":[175],"findings":[176],"extend":[177],"actor-critic":[179],"framework":[180],"proposed":[181],"revealing":[187],"errors":[190],"a":[192],"subpopulation":[193],"mesolimbic":[195],"capable":[198],"training":[200],"parallel":[201],"regions":[203],"thought":[204],"implement":[206],"different":[207],"types":[208],"behavioral":[210],"control.":[211]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-11T00:00:00"}
