{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T12:53:51Z","timestamp":1765976031971},"reference-count":104,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2014,4,1]],"date-time":"2014-04-01T00:00:00Z","timestamp":1396310400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2014,4]]},"DOI":"10.1109\/jproc.2014.2307022","type":"journal-article","created":{"date-parts":[[2014,3,14]],"date-time":"2014-03-14T18:02:06Z","timestamp":1394820126000},"page":"528-541","source":"Crossref","is-referenced-by-count":36,"title":["The Misbehavior of Reinforcement Learning"],"prefix":"10.1109","volume":"102","author":[{"given":"Gianluigi","family":"Mongillo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanan","family":"Shteingart","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonatan","family":"Loewenstein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2258"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.051508.135409"},{"key":"ref33","first-page":"1057","volume":"12","author":"sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S0306-4522(00)00019-1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.0053-12.2012"},{"key":"ref37","author":"dayan","year":"2001","journal-title":"Theoretical Neuroscience Computational and Mathematical Modeling of Neural Systems"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001","author":"bishop","year":"1995","journal-title":"Neural Networks for Pattern Recognition"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1613\/jair.806"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.tins.2013.03.003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2010.11.022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2005.05.020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s00213-006-0510-4"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.275.5306.1593"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.1590-07.2007"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1014269108"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1186\/1744-9081-6-24"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2006.03.002"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0033612"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2012.0683"},{"key":"ref25","author":"gallistel","year":"1990","journal-title":"The Organization of Learning"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.97.048104"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0505220103"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.2307\/1907381"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1037\/h0054051"},{"key":"ref57","first-page":"91","article-title":"Gq<ref_formula><tex Notation=\"TeX\">$(\\lambda)$<\/tex><\/ref_formula>: A general gradient algorithm for temporal-difference prediction learning with eligibility traces","volume":"1","author":"maei","year":"0","journal-title":"Proc 3rd Conf Artif Gen Intell"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553501"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252792"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2068-12.2013"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000007"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2010.00017"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1146\/annurev.physiol.64.092501.114547","article-title":"Short-term synaptic plasticity","volume":"64","author":"zucker","year":"2002","journal-title":"Annu Rev Physiol"},{"key":"ref4","author":"thorndike","year":"1911","journal-title":"Animal Intelligence"},{"key":"ref3","author":"hyman","year":"1997","journal-title":"The Case Against Spanking"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1037\/14496-000"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1038\/nn.2264"},{"key":"ref9","first-page":"541","article-title":"On the undecidability of probabilistic planning and infinite-horizon partially observable Markov decision problems","author":"madani","year":"1999","journal-title":"Proc Nat Conf Artif Intell"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0900546106"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbr.2008.10.030"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.69.041909"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(03)00761-X"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2004.09.012"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2004.09.007"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.4402-07.2008"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/S0301-0082(03)00085-6"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1901\/jeab.1987.47-261"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2009.09-08-854"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2013.12.004"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0080683"},{"key":"ref76","volume":"2","author":"heyman","year":"1982","journal-title":"Quantitative Analyses of Behavior"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.3758\/BF03210960"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1037\/h0055873"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1901\/jeab.1981.35-367"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1037\/0097-7403.27.4.354"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1901\/jeab.1961.4-267"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1901\/jeab.1975.24-107"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1111\/1467-6419.00106"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s002130050651"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1002\/bdm.413"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1111\/j.1559-1816.2009.00551.x"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.20.1.227"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1001709107"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2009.07.003"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.2307\/1419951"},{"key":"ref2","author":"matthews","year":"1991","journal-title":"Old Testament Parallels Laws and Stories From the Ancient Near Est"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1037\/h0024137"},{"key":"ref1","author":"mcgreevy","year":"2007","journal-title":"Carrots and Sticks Principles of Animal Training"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000894"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms1580"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.5445-12.2013"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025696116075"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2012.00024"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1037\/h0040090"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1037\/a0029550"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.3758\/BF03200092"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2012.08.004"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0006421"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2013.00598"},{"key":"ref96","article-title":"Selecting the state-representation in reinforcement learning","author":"maillard","year":"2011","journal-title":"Proc Neural Inf Process Syst Conf"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143963"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50042-8"},{"key":"ref11","author":"hasinoff","year":"2003","journal-title":"Reinforcement learning for problems with hidden state"},{"key":"ref12","author":"murphy","year":"2000","journal-title":"A survey of POMDP solution techniques"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2976\/1.2732246\/10.2976\/1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/35097575"},{"key":"ref15","author":"miller","year":"2007","journal-title":"The Neuroscience of Rule-Guided Behavior"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1126\/science.1094765"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0306-4522(98)00319-4"},{"key":"ref81","author":"herrnstein","year":"1997","journal-title":"The Matching Law"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1126\/science.1115270"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1901\/jeab.1974.22-231"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"12?860","DOI":"10.1523\/JNEUROSCI.2496-07.2007","article-title":"Reinforcement learning signals in the human striatum distinguish learners from nonlearners during reward-based decision making","volume":"27","author":"sch\ufffdnberg","year":"2007","journal-title":"J Neurosci"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1126\/science.185.4145.78"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0166-2236(90)90107-L"},{"key":"ref80","author":"davison","year":"1988","journal-title":"The Matching Law A Research Review"},{"key":"ref89","author":"erev","year":"0","journal-title":"The Handbook of Experimental Economics"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2008.02.021"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1901\/jeab.2005.23-05"},{"key":"ref87","first-page":"93","article-title":"Deviations from the matching law reflect reward integration over multiple timescales","author":"iigaya","year":"2013","journal-title":"Proc Cosyne Abstracts 2013"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-012-0324-9"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5\/6777968\/06767062.pdf?arnumber=6767062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,25]],"date-time":"2024-05-25T00:52:42Z","timestamp":1716598362000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6767062\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4]]},"references-count":104,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2014.2307022","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,4]]}}}