{"id":"https://openalex.org/W2018405866","doi":"https://doi.org/10.1109/jproc.2014.2307022","title":"The Misbehavior of Reinforcement Learning","display_name":"The Misbehavior of Reinforcement Learning","publication_year":2014,"publication_date":"2014-03-14","ids":{"openalex":"https://openalex.org/W2018405866","doi":"https://doi.org/10.1109/jproc.2014.2307022","mag":"2018405866"},"language":"en","primary_location":{"id":"doi:10.1109/jproc.2014.2307022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jproc.2014.2307022","pdf_url":null,"source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE","raw_type":"journal-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/A5020750894","display_name":"Gianluigi Mongillo","orcid":"https://orcid.org/0000-0002-6885-9394"},"institutions":[{"id":"https://openalex.org/I110736937","display_name":"D\u00e9l\u00e9gation Paris 5","ror":"https://ror.org/02e0y6e06","country_code":"FR","type":"government","lineage":["https://openalex.org/I110736937","https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4210094404","display_name":"Brain Physiology Lab","ror":"https://ror.org/00hdncs36","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I204730241","https://openalex.org/I4210094404","https://openalex.org/I4210096427"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gianluigi Mongillo","raw_affiliation_strings":["Laboratory of Neurophysics and Physiology, Paris Descartes University, Paris, France","Lab. of Neurophysics & Physiol., Paris Descartes Univ., Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Neurophysics and Physiology, Paris Descartes University, Paris, France","institution_ids":["https://openalex.org/I4210094404","https://openalex.org/I204730241"]},{"raw_affiliation_string":"Lab. of Neurophysics & Physiol., Paris Descartes Univ., Paris, France","institution_ids":["https://openalex.org/I204730241","https://openalex.org/I110736937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089822963","display_name":"Hanan Shteingart","orcid":"https://orcid.org/0000-0002-7117-4337"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Hanan Shteingart","raw_affiliation_strings":["Edmond and Lily Safra Center for Brain Sciences, Hebrew University of Jerusalem, Jerusalem, Israel","Edmond and Lily Safra Center for Brain Science, Hebrew University of Jerusalem, Jerusalem, Israel;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Edmond and Lily Safra Center for Brain Sciences, Hebrew University of Jerusalem, Jerusalem, Israel","institution_ids":["https://openalex.org/I197251160"]},{"raw_affiliation_string":"Edmond and Lily Safra Center for Brain Science, Hebrew University of Jerusalem, Jerusalem, Israel;","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074945649","display_name":"Yonatan Loewenstein","orcid":"https://orcid.org/0000-0003-2577-2317"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yonatan Loewenstein","raw_affiliation_strings":["Department of Neurobiology, Department of Cognitive Science, Alexander Silberman Institute of Life Sciences, Edmond and Lily Safra Center for Brain Sciences, and Center for the Study of Rationality, Hebrew University of Jerusalem, Jerusalem, Israel","Dept. of Neurobiol., Hebrew Univ. of Jerusalem, Jerusalem, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Neurobiology, Department of Cognitive Science, Alexander Silberman Institute of Life Sciences, Edmond and Lily Safra Center for Brain Sciences, and Center for the Study of Rationality, Hebrew University of Jerusalem, Jerusalem, Israel","institution_ids":["https://openalex.org/I197251160"]},{"raw_affiliation_string":"Dept. of Neurobiol., Hebrew Univ. of Jerusalem, Jerusalem, Israel","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9624,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.69300163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"102","issue":"4","first_page":"528","last_page":"541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10423","display_name":"Neurobiology and Insect Physiology Research","score":0.9937999844551086,"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/T10423","display_name":"Neurobiology and Insect Physiology Research","score":0.9937999844551086,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9911999702453613,"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/T10174","display_name":"Animal Behavior and Reproduction","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/1105","display_name":"Ecology, Evolution, Behavior and Systematics"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8089028596878052},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.7201970219612122},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6106339693069458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5927687883377075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5486180186271667},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5327627062797546},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4946126639842987},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4909070134162903},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46112650632858276},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.4356100559234619},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.41482222080230713},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4144122898578644},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.393984854221344},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.33408623933792114},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.27999112010002136},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.18849661946296692},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1377522051334381},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11599895358085632}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8089028596878052},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.7201970219612122},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6106339693069458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5927687883377075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5486180186271667},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5327627062797546},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4946126639842987},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4909070134162903},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46112650632858276},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.4356100559234619},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.41482222080230713},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4144122898578644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.393984854221344},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.33408623933792114},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27999112010002136},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.18849661946296692},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1377522051334381},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11599895358085632},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jproc.2014.2307022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jproc.2014.2307022","pdf_url":null,"source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":112,"referenced_works":["https://openalex.org/W151356793","https://openalex.org/W297984285","https://openalex.org/W1512746852","https://openalex.org/W1522486277","https://openalex.org/W1540136915","https://openalex.org/W1541084404","https://openalex.org/W1554663460","https://openalex.org/W1563965851","https://openalex.org/W1592847719","https://openalex.org/W1626837244","https://openalex.org/W1777078982","https://openalex.org/W1887460322","https://openalex.org/W1968363585","https://openalex.org/W1972815966","https://openalex.org/W1974795190","https://openalex.org/W1983624302","https://openalex.org/W1984785177","https://openalex.org/W1986984034","https://openalex.org/W1989325827","https://openalex.org/W1994483275","https://openalex.org/W1994616650","https://openalex.org/W2004011965","https://openalex.org/W2004014356","https://openalex.org/W2019310225","https://openalex.org/W2023624637","https://openalex.org/W2023916971","https://openalex.org/W2025018010","https://openalex.org/W2027648864","https://openalex.org/W2029514605","https://openalex.org/W2031170958","https://openalex.org/W2041151088","https://openalex.org/W2041176801","https://openalex.org/W2041355031","https://openalex.org/W2043028940","https://openalex.org/W2047790410","https://openalex.org/W2049801983","https://openalex.org/W2050066016","https://openalex.org/W2050233777","https://openalex.org/W2059095731","https://openalex.org/W2061897041","https://openalex.org/W2062670775","https://openalex.org/W2064126294","https://openalex.org/W2067166479","https://openalex.org/W2069258922","https://openalex.org/W2069538478","https://openalex.org/W2071391019","https://openalex.org/W2072698517","https://openalex.org/W2072891170","https://openalex.org/W2072996399","https://openalex.org/W2073003335","https://openalex.org/W2075268401","https://openalex.org/W2076256116","https://openalex.org/W2076457657","https://openalex.org/W2081616632","https://openalex.org/W2081930647","https://openalex.org/W2082430497","https://openalex.org/W2083058253","https://openalex.org/W2084757290","https://openalex.org/W2085376923","https://openalex.org/W2091789872","https://openalex.org/W2093466600","https://openalex.org/W2097760871","https://openalex.org/W2097872145","https://openalex.org/W2100660722","https://openalex.org/W2101692583","https://openalex.org/W2104463177","https://openalex.org/W2107726111","https://openalex.org/W2112439305","https://openalex.org/W2112927743","https://openalex.org/W2117726420","https://openalex.org/W2118125647","https://openalex.org/W2119170562","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2122234510","https://openalex.org/W2123157758","https://openalex.org/W2124720308","https://openalex.org/W2130550691","https://openalex.org/W2131215403","https://openalex.org/W2135746467","https://openalex.org/W2135886642","https://openalex.org/W2135955567","https://openalex.org/W2137411342","https://openalex.org/W2137966130","https://openalex.org/W2144064768","https://openalex.org/W2144446635","https://openalex.org/W2146760691","https://openalex.org/W2152571732","https://openalex.org/W2154583360","https://openalex.org/W2155027007","https://openalex.org/W2156581621","https://openalex.org/W2156738026","https://openalex.org/W2159162180","https://openalex.org/W2167087276","https://openalex.org/W2168558032","https://openalex.org/W2172030907","https://openalex.org/W2316148471","https://openalex.org/W2322381186","https://openalex.org/W2486153036","https://openalex.org/W2492794003","https://openalex.org/W2549522992","https://openalex.org/W3001500682","https://openalex.org/W3022176009","https://openalex.org/W3103182070","https://openalex.org/W3149412023","https://openalex.org/W4214717370","https://openalex.org/W4235391064","https://openalex.org/W4239224257","https://openalex.org/W4249441547","https://openalex.org/W4388297464","https://openalex.org/W6633696232","https://openalex.org/W6683154691"],"related_works":["https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W66717747","https://openalex.org/W260766989","https://openalex.org/W2054010227","https://openalex.org/W4319083788","https://openalex.org/W2350668434","https://openalex.org/W3022038857"],"abstract_inverted_index":{"Organisms":[0],"modify":[1,129],"their":[2,125,130,157,162,171],"behavior":[3,176],"in":[4,81,124,154,168,179,192],"response":[5],"to":[6,12,77,111,128,173,209],"its":[7],"consequences,":[8],"a":[9,26,52,57,108,210],"phenomenon":[10],"referred":[11],"as":[13,177],"operant":[14,23,214],"learning.":[15,44,215],"The":[16,45],"computational":[17,109,158],"principles":[18],"and":[19,31,40,160,186],"neural":[20,164],"mechanisms":[21],"underlying":[22],"learning":[24],"are":[25,74],"subject":[27],"of":[28,59,61,88,94,97,106,140,144,156,170,188,197,205,213],"extensive":[29],"experimental":[30],"theoretical":[32],"investigations.":[33],"Theoretical":[34],"approaches":[35,153,191],"largely":[36],"rely":[37],"on":[38,92],"concepts":[39],"algorithms":[41],"from":[42,85],"reinforcement":[43],"dominant":[46],"view":[47,102],"is":[48],"that":[49,55,118],"organisms":[50,119],"maintain":[51],"value":[53],"function,":[54],"is,":[56],"set":[58],"estimates":[60],"the":[62,68,86,95,104,121,138,184,194,206],"cumulative":[63],"future":[64],"rewards":[65],"associated":[66],"with":[67],"different":[69],"behavioral":[70],"options.":[71],"These":[72],"values":[73,90],"then":[75],"used":[76],"select":[78],"actions.":[79,99],"Learning":[80],"this":[82,147],"framework":[83],"results":[84],"update":[87],"these":[89,151,189],"depending":[91],"experience":[93],"consequences":[96],"past":[98],"An":[100],"alternative":[101,190],"questions":[103],"applicability":[105],"such":[107],"scheme":[110],"many":[112],"real-life":[113],"situations.":[114],"Instead,":[115],"it":[116],"posits":[117],"exploit":[120],"intrinsic":[122],"variability":[123],"action\u2013selection":[126],"mechanism(s)":[127],"behavior,":[131],"e.g.,":[132],"via":[133],"stochastic":[134],"gradient":[135],"ascent,":[136],"without":[137],"need":[139],"an":[141],"explicit":[142],"representation":[143],"values.":[145],"In":[146],"review,":[148],"we":[149],"compare":[150],"two":[152],"terms":[155,169],"power":[159],"flexibility,":[161],"putative":[163],"correlates,":[165],"and,":[166],"finally,":[167],"ability":[172],"account":[174],"for":[175],"observed":[178,195],"repeated-choice":[180],"experiments.":[181],"We":[182,200],"discuss":[183],"successes":[185],"failures":[187],"explaining":[193],"patterns":[196],"choice":[198],"behavior.":[199],"conclude":[201],"by":[202],"identifying":[203],"some":[204],"important":[207],"challenges":[208],"comprehensive":[211],"theory":[212]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}