{"id":"https://openalex.org/W3213180026","doi":"https://doi.org/10.1162/neco_a_01455","title":"A Normative Account of Confirmation Bias During Reinforcement Learning","display_name":"A Normative Account of Confirmation Bias During Reinforcement Learning","publication_year":2021,"publication_date":"2021-11-10","ids":{"openalex":"https://openalex.org/W3213180026","doi":"https://doi.org/10.1162/neco_a_01455","mag":"3213180026","pmid":"https://pubmed.ncbi.nlm.nih.gov/34758486"},"language":"en","primary_location":{"id":"doi:10.1162/neco_a_01455","is_oa":true,"landing_page_url":"https://doi.org/10.1162/neco_a_01455","pdf_url":"https://direct.mit.edu/neco/article-pdf/34/2/307/2006833/neco_a_01455.pdf","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":true,"oa_status":"bronze","oa_url":"https://direct.mit.edu/neco/article-pdf/34/2/307/2006833/neco_a_01455.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082129219","display_name":"Germain Lefebvre","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108304","display_name":"MRC Brain Network Dynamics Unit","ror":"https://ror.org/01tfjyv98","country_code":"GB","type":"facility","lineage":["https://openalex.org/I40120149","https://openalex.org/I4210087105","https://openalex.org/I4210108304","https://openalex.org/I90344618"]},{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Germain Lefebvre","raw_affiliation_strings":["MRC Brain Network Dynamics Unit, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford OX3 9DU, U.K. germain.lefebvre@outlook.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MRC Brain Network Dynamics Unit, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford OX3 9DU, U.K. germain.lefebvre@outlook.com","institution_ids":["https://openalex.org/I4210108304","https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031878516","display_name":"Christopher Summerfield","orcid":"https://orcid.org/0000-0002-2941-2653"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Christopher Summerfield","raw_affiliation_strings":["Department of Experimental Psychology, University of Oxford, Oxford OX3 9DU, U.K. christopher.summerfield@psy.ox.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Experimental Psychology, University of Oxford, Oxford OX3 9DU, U.K. christopher.summerfield@psy.ox.ac.uk","institution_ids":["https://openalex.org/I40120149"]}]},{"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/I4210108304","display_name":"MRC Brain Network Dynamics Unit","ror":"https://ror.org/01tfjyv98","country_code":"GB","type":"facility","lineage":["https://openalex.org/I40120149","https://openalex.org/I4210087105","https://openalex.org/I4210108304","https://openalex.org/I90344618"]},{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Rafal Bogacz","raw_affiliation_strings":["MRC Brain Network Dynamics Unit, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford OX3 9DU, U.K. rafal.bogacz@ndcn.ox.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MRC Brain Network Dynamics Unit, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford OX3 9DU, U.K. rafal.bogacz@ndcn.ox.ac.uk","institution_ids":["https://openalex.org/I4210108304","https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031878516","https://openalex.org/A5049095056","https://openalex.org/A5082129219"],"corresponding_institution_ids":["https://openalex.org/I40120149","https://openalex.org/I4210108304"],"apc_list":null,"apc_paid":null,"fwci":4.1654,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.94925282,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"34","issue":"2","first_page":"307","last_page":"337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.9933000206947327,"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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.9933000206947327,"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/T10315","display_name":"Decision-Making and Behavioral Economics","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1800","display_name":"General Decision Sciences"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9685999751091003,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7626008987426758},{"id":"https://openalex.org/keywords/converse","display_name":"Converse","score":0.6722976565361023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4997446537017822},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4667155146598816},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.465410977602005},{"id":"https://openalex.org/keywords/normative","display_name":"Normative","score":0.4603547751903534},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4011806845664978},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.3749777674674988},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3602955937385559},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19689542055130005}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7626008987426758},{"id":"https://openalex.org/C2776809875","wikidata":"https://www.wikidata.org/wiki/Q1375963","display_name":"Converse","level":2,"score":0.6722976565361023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4997446537017822},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4667155146598816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.465410977602005},{"id":"https://openalex.org/C44725695","wikidata":"https://www.wikidata.org/wiki/Q288156","display_name":"Normative","level":2,"score":0.4603547751903534},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4011806845664978},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3749777674674988},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3602955937385559},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19689542055130005},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[{"descriptor_ui":"D003657","descriptor_name":"Decision Making","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003657","descriptor_name":"Decision Making","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003657","descriptor_name":"Decision Making","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003657","descriptor_name":"Decision Making","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":"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":"D007858","descriptor_name":"Learning","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":"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":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1162/neco_a_01455","is_oa":true,"landing_page_url":"https://doi.org/10.1162/neco_a_01455","pdf_url":"https://direct.mit.edu/neco/article-pdf/34/2/307/2006833/neco_a_01455.pdf","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:34758486","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34758486","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:pubmedcentral.nih.gov:7612695","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7612695","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Neural Comput","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1162/neco_a_01455","is_oa":true,"landing_page_url":"https://doi.org/10.1162/neco_a_01455","pdf_url":"https://direct.mit.edu/neco/article-pdf/34/2/307/2006833/neco_a_01455.pdf","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"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3660457013","display_name":null,"funder_award_id":"BB/S006338/1","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"},{"id":"https://openalex.org/G420847197","display_name":null,"funder_award_id":"MC_UU_00003/1","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"},{"id":"https://openalex.org/G6685968704","display_name":null,"funder_award_id":"MC_UU_12024/5","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"}],"funders":[{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"},{"id":"https://openalex.org/F4320334629","display_name":"Biotechnology and Biological Sciences Research Council","ror":"https://ror.org/00cwqg982"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3213180026.pdf","grobid_xml":"https://content.openalex.org/works/W3213180026.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W609092168","https://openalex.org/W1982670892","https://openalex.org/W1990119533","https://openalex.org/W1992373090","https://openalex.org/W2033271727","https://openalex.org/W2054327074","https://openalex.org/W2066931620","https://openalex.org/W2075585362","https://openalex.org/W2077611535","https://openalex.org/W2110123411","https://openalex.org/W2114887250","https://openalex.org/W2129554788","https://openalex.org/W2142099443","https://openalex.org/W2143275924","https://openalex.org/W2148821453","https://openalex.org/W2168179260","https://openalex.org/W2290443327","https://openalex.org/W2507447634","https://openalex.org/W2558439382","https://openalex.org/W2561424158","https://openalex.org/W2595891121","https://openalex.org/W2808649721","https://openalex.org/W2884757460","https://openalex.org/W2891654265","https://openalex.org/W2895764062","https://openalex.org/W2949941589","https://openalex.org/W2952259054","https://openalex.org/W2973034539","https://openalex.org/W2981588505","https://openalex.org/W2999778183","https://openalex.org/W3001032801","https://openalex.org/W3006072739","https://openalex.org/W3046554509","https://openalex.org/W3133512724"],"related_works":["https://openalex.org/W2387449261","https://openalex.org/W2418518962","https://openalex.org/W2963377682","https://openalex.org/W2043159103","https://openalex.org/W2391769344","https://openalex.org/W2359260952","https://openalex.org/W4297790016","https://openalex.org/W2769269860","https://openalex.org/W2020701214","https://openalex.org/W4287585143"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,25,167],"involves":[2],"updating":[3,58,102],"estimates":[4,40],"of":[5,8,15,33,77,111,139,147,159],"the":[6,13,31,53,59,75,93,137,145,157],"value":[7,32,62,138,146],"states":[9],"and":[10,114,143],"actions":[11],"on":[12,68,130],"basis":[14],"experience.":[16],"Previous":[17],"work":[18],"has":[19],"shown":[20],"that":[21,89,126],"in":[22,156,170],"humans,":[23],"reinforcement":[24],"exhibits":[26],"a":[27,34,69,78,86,108],"confirmatory":[28,79,90,132],"bias:":[29],"when":[30,57,118],"chosen":[35],"option":[36,61],"is":[37,55,115],"being":[38],"updated,":[39],"are":[41,120,177],"revised":[42],"more":[43,140,154],"radically":[44],"following":[45],"positive":[46],"than":[47],"negative":[48],"reward":[49,82,97,173],"prediction":[50],"errors,":[51],"but":[52],"converse":[54],"observed":[56],"unchosen":[60],"estimate.":[63],"Here,":[64],"we":[65],"simulate":[66],"performance":[67],"multi-arm":[70],"bandit":[71],"task":[72],"to":[73,95,99,135],"examine":[74],"consequences":[76],"bias":[80],"for":[81],"harvesting.":[83],"We":[84,124],"report":[85],"paradoxical":[87],"finding:":[88],"biases":[91,133],"allow":[92],"agent":[94],"maximize":[96],"relative":[98],"an":[100],"unbiased":[101],"rule.":[103],"This":[104],"principle":[105],"holds":[106],"over":[107],"wide":[109],"range":[110],"experimental":[112],"settings":[113],"most":[116],"influential":[117],"decisions":[119,152,176],"corrupted":[121],"by":[122],"noise.":[123,160],"show":[125,163],"this":[127],"occurs":[128],"because":[129],"average,":[131],"lead":[134],"overestimating":[136],"valuable":[141,149],"bandits":[142],"underestimating":[144],"less":[148],"bandits,":[150],"rendering":[151],"overall":[153],"robust":[155],"face":[158],"Our":[161],"results":[162],"how":[164],"apparently":[165],"suboptimal":[166],"rules":[168],"can":[169],"fact":[171],"be":[172],"maximizing":[174],"if":[175],"made":[178],"with":[179],"finite":[180],"computational":[181],"precision.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":4}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}