{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T09:36:53Z","timestamp":1778060213354,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2013,10,2]],"date-time":"2013-10-02T00:00:00Z","timestamp":1380672000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biol Cybern"],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1007\/s00422-013-0571-5","type":"journal-article","created":{"date-parts":[[2013,10,1]],"date-time":"2013-10-01T15:24:09Z","timestamp":1380641049000},"page":"711-719","source":"Crossref","is-referenced-by-count":99,"title":["Adaptive properties of differential learning rates for positive and negative outcomes"],"prefix":"10.1007","volume":"107","author":[{"given":"Romain D.","family":"Caz\u00e9","sequence":"first","affiliation":[]},{"given":"Matthijs A. A.","family":"van der Meer","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,10,2]]},"reference":[{"issue":"9","key":"571_CR1","doi-asserted-by":"crossref","first-page":"1214","DOI":"10.1038\/nn1954","volume":"10","author":"TEJ Behrens","year":"2007","unstructured":"Behrens TEJ, Woolrich MW, Walton ME, Rushworth MFS (2007) Learning the value of information in an uncertain world. Nat Neurosci 10(9):1214\u20131221","journal-title":"Nat Neurosci"},{"issue":"5","key":"571_CR2","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1016\/j.neuron.2010.11.022","volume":"68","author":"ES Bromberg-Martin","year":"2010","unstructured":"Bromberg-Martin ES, Matsumoto M, Hikosaka O (2010) Dopamine in motivational control: rewarding, aversive, and alerting. Neuron 68(5):815\u2013834","journal-title":"Neuron"},{"issue":"3","key":"571_CR3","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1093\/scan\/nsq041","volume":"6","author":"JF Cavanagh","year":"2011","unstructured":"Cavanagh JF, Frank MJ (2011) Social stress reactivity alters reward and punishment learning. Soc Cogn Affect Neurosci 6(3):311\u2013320","journal-title":"Soc Cogn Affect Neurosci"},{"issue":"18","key":"571_CR4","doi-asserted-by":"crossref","first-page":"6180","DOI":"10.1523\/JNEUROSCI.5758-09.2010","volume":"30","author":"HW Chase","year":"2010","unstructured":"Chase HW, Clark L (2010) Gambling severity predicts midbrain response to near-miss outcomes. J Neurosci 30(18):6180\u20136187","journal-title":"J Neurosci"},{"issue":"4","key":"571_CR5","doi-asserted-by":"crossref","first-page":"363","DOI":"10.3758\/CABN.8.4.363","volume":"8","author":"M D\u2019Acremont","year":"2008","unstructured":"D\u2019Acremont M, Bossaerts P (2008) Neurobiological studies of risk assessment: a comparison of expected utility and mean-variance approaches. Cogn Affect Behav Neurosci 8(4):363\u2013374","journal-title":"Cogn Affect Behav Neurosci"},{"issue":"3","key":"571_CR6","doi-asserted-by":"crossref","first-page":"784","DOI":"10.1037\/0033-295X.114.3.784","volume":"114","author":"AD Redish","year":"2007","unstructured":"Redish AD, Jensen S, Johnson A, Kurth-Nelson Z (2007) Reconciling reinforcement learning models with behavioral extinction and renewal: implications for addiction, relapse, and problem gambling. Psychol Rev 114(3):784\u2013805","journal-title":"Psychol Rev"},{"issue":"7095","key":"571_CR7","doi-asserted-by":"crossref","first-page":"876","DOI":"10.1038\/nature04766","volume":"441","author":"ND Daw","year":"2006","unstructured":"Daw ND, O\u2019Doherty JP, Dayan P, Seymour B, Dolan RJ (2006) Cortical substrates for exploratory decisions in humans. Nature 441(7095):876\u2013879","journal-title":"Nature"},{"issue":"6","key":"571_CR8","doi-asserted-by":"crossref","first-page":"1204","DOI":"10.1016\/j.neuron.2011.02.027","volume":"69","author":"ND Daw","year":"2011","unstructured":"Daw ND, Gershman SJ, Seymour B, Dayan P, Dolan RJ (2011) Model-based influences on humans\u2019 choices and striatal prediction errors. Neuron 69(6):1204\u20131215","journal-title":"Neuron"},{"issue":"2","key":"571_CR9","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/j.conb.2008.08.003","volume":"18","author":"P Dayan","year":"2008","unstructured":"Dayan P, Niv Y (2008) Reinforcement learning: the good, the bad and the ugly. Curr Opin Neurobiol 18(2):185\u2013196","journal-title":"Curr Opin Neurobiol"},{"key":"571_CR10","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.brainres.2009.07.007","volume":"1299","author":"BB Doll","year":"2009","unstructured":"Doll BB, Jacobs WJ, Sanfey AG, Frank MJ (2009) Instructional control of reinforcement learning: a behavioral and neurocomputational investigation. Brain Res 1299:74\u201394","journal-title":"Brain Res"},{"issue":"4\u20136","key":"571_CR11","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1016\/S0893-6080(02)00044-8","volume":"15","author":"K Doya","year":"2002","unstructured":"Doya K (2002) Metalearning and neuromodulation. Neural Netw 15(4\u20136):495\u2013506","journal-title":"Neural Netw"},{"issue":"6","key":"571_CR12","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1162\/089976602753712972","volume":"14","author":"K Doya","year":"2002","unstructured":"Doya K, Samejima K, Katagiri K, Kawato M (2002) Multiple model-based reinforcement learning. Neural Comput 14(6):1347\u20131369","journal-title":"Neural Comput"},{"issue":"6145","key":"571_CR13","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1126\/science.1238699","volume":"341","author":"CD Fiorillo","year":"2013","unstructured":"Fiorillo CD (2013) Two dimensions of value: dopamine neurons represent reward but not aversiveness. Science 341(6145):546\u2013549","journal-title":"Science"},{"issue":"5703","key":"571_CR14","doi-asserted-by":"crossref","first-page":"1940","DOI":"10.1126\/science.1102941","volume":"306","author":"MJ Frank","year":"2004","unstructured":"Frank MJ, Seeberger LC, O\u2019reilly RC (2004) By carrot or by stick: cognitive reinforcement learning in parkinsonism. Science 306(5703):1940\u20131943","journal-title":"Science"},{"issue":"41","key":"571_CR15","doi-asserted-by":"crossref","first-page":"16311","DOI":"10.1073\/pnas.0706111104","volume":"104","author":"MJ Frank","year":"2007","unstructured":"Frank MJ, Moustafa AA, Haughey HM, Curran T, Hutchison KE (2007) Genetic triple dissociation reveals multiple roles for dopamine in reinforcement learning. Proc Natl Acad Sci 104(41):16311\u201316316","journal-title":"Proc Natl Acad Sci"},{"issue":"8","key":"571_CR16","doi-asserted-by":"crossref","first-page":"1062","DOI":"10.1038\/nn.2342","volume":"12","author":"MJ Frank","year":"2009","unstructured":"Frank MJ, Doll BB, Oas-Terpstra J, Moreno F (2009) Prefrontal and striatal dopaminergic genes predict individual differences in exploration and exploitation. Nat Neurosci 12(8):1062\u20131068","journal-title":"Nat Neurosci"},{"key":"571_CR17","doi-asserted-by":"crossref","first-page":"1429","DOI":"10.1126\/science.2147780","volume":"250","author":"CR Gerfen","year":"1990","unstructured":"Gerfen CR, Engber TM, Mahan LC, Susel Z, Chase TN, Monsma FJ Jr, Sibley DR (1990) $$\\text{ D }_1$$ D 1 and $$\\text{ D }_2$$ D 2 dopamine receptor-regulated gene expression of striatonigral and striatopallidal neurons. Science 250:1429\u20131432","journal-title":"Science"},{"issue":"2","key":"571_CR18","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.conb.2010.02.008","volume":"20","author":"SJ Gershman","year":"2010","unstructured":"Gershman SJ, Niv Y (2010) Learning latent structure: carving nature at its joints. Curr Opin Neurobiol 20(2):251\u2013256","journal-title":"Curr Opin Neurobiol"},{"issue":"3","key":"571_CR19","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1016\/j.neuropharm.2011.05.011","volume":"62","author":"AA Grace","year":"2012","unstructured":"Grace AA (2012) Dopamine system dysregulation by the hippocampus: implications for the pathophysiology and treatment of schizophrenia. Neuropharmacology 62(3):1342\u20131348","journal-title":"Neuropharmacology"},{"issue":"February","key":"571_CR20","first-page":"9","volume":"6","author":"MD Humphries","year":"2012","unstructured":"Humphries MD, Khamassi M, Gurney K (2012) Dopaminergic control of the exploration-exploitation trade-off via the basal ganglia. Front Neurosci 6(February):9","journal-title":"Front Neurosci"},{"issue":"2","key":"571_CR21","first-page":"263","volume":"47","author":"D Kahneman","year":"1979","unstructured":"Kahneman D, Tversky A (1979) Prospect theory: an analysis of decision under risk. Econ J Econ Soc 47(2):263\u2013292","journal-title":"Econ J Econ Soc"},{"issue":"July","key":"571_CR22","first-page":"1","volume":"5","author":"M Khamassi","year":"2011","unstructured":"Khamassi M, Lall\u00e9e S, Enel P, Procyk E, Dominey PF (2011) Robot cognitive control with a neurophysiologically inspired reinforcement learning model. Front Neurorobotic 5(July):1","journal-title":"Front Neurorobotic"},{"key":"571_CR23","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/B978-0-444-62604-2.00022-8","volume":"202","author":"M Khamassi","year":"2013","unstructured":"Khamassi M, Enel P, Dominey PF, Procyk E (2013) Medial prefrontal cortex and the adaptive regulation of reinforcement learning parameters. Prog Brain Res 202:441\u2013464","journal-title":"Prog Brain Res"},{"key":"571_CR24","doi-asserted-by":"crossref","unstructured":"Kravitz AV, Tye LD, Kreitzer AC (2012) Distinct roles for direct and indirect pathway striatal neurons in reinforcement. Nat Neurosci 15:816\u2013818","DOI":"10.1038\/nn.3100"},{"issue":"10","key":"571_CR25","doi-asserted-by":"crossref","first-page":"e7362","DOI":"10.1371\/journal.pone.0007362","volume":"4","author":"Z Kurth-Nelson","year":"2009","unstructured":"Kurth-Nelson Z, Redish AD (2009) Temporal-difference reinforcement learning with distributed representations. PLoS One 4(10):e7362","journal-title":"PLoS One"},{"issue":"2","key":"571_CR26","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1038\/nn.2723","volume":"14","author":"TV Maia","year":"2011","unstructured":"Maia TV, Frank MJ (2011) From reinforcement learning models to psychiatric and neurological disorders. Nat Neurosci 14(2):154\u2013162","journal-title":"Nat Neurosci"},{"key":"571_CR27","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1023\/A:1017940631555","volume":"49","author":"O Mihatsch","year":"2002","unstructured":"Mihatsch O, Neuneier R (2002) Risk-sensitive reinforcement learning. Mach Learn 49:267\u2013290","journal-title":"Mach Learn"},{"key":"571_CR28","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/1744-9081-1-6","volume":"1","author":"Y Niv","year":"2005","unstructured":"Niv Y, Duff MO, Dayan P (2005) Dopamine, uncertainty and TD learning. Behav Brain Funct 1:6","journal-title":"Behav Brain Funct"},{"issue":"3","key":"571_CR29","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1007\/s00213-006-0502-4","volume":"191","author":"Y Niv","year":"2007","unstructured":"Niv Y, Daw ND, Joel D, Dayan P (2007) Tonic dopamine: opportunity costs and the control of response vigor. Psychopharmacology 191(3):507\u2013520","journal-title":"Psychopharmacology"},{"key":"571_CR30","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1196\/annals.1390.022","volume":"1104","author":"JP O\u2019Doherty","year":"2007","unstructured":"O\u2019Doherty JP, Hampton A, Kim H (2007) Model-based fMRI and its application to reward learning and decision making. Ann NY Acad Sci 1104:35\u201353","journal-title":"Ann NY Acad Sci"},{"issue":"5703","key":"571_CR31","doi-asserted-by":"crossref","first-page":"1944","DOI":"10.1126\/science.1102384","volume":"306","author":"AD Redish","year":"2004","unstructured":"Redish AD (2004) Addiction as a computational process gone awry. Science 306(5703):1944\u20131947","journal-title":"Science"},{"key":"571_CR32","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1146\/annurev.psych.56.091103.070229","volume":"57","author":"W Schultz","year":"2006","unstructured":"Schultz W (2006) Behavioral theories and the neurophysiology of reward. Annu Rev Psychol 57:87\u2013115","journal-title":"Annu Rev Psychol"},{"issue":"1","key":"571_CR33","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/S0893-6080(02)00228-9","volume":"16","author":"N Schweighofer","year":"2003","unstructured":"Schweighofer N, Doya K (2003) Meta-learning in reinforcement learning. Neural Netw 16(1):5\u20139","journal-title":"Neural Netw"},{"key":"571_CR34","doi-asserted-by":"crossref","unstructured":"Sharot T (2011) The optimism bias. Curr Biol 21(23):R941\u2013R945","DOI":"10.1016\/j.cub.2011.10.030"},{"issue":"11","key":"571_CR35","doi-asserted-by":"crossref","first-page":"1475","DOI":"10.1038\/nn.2949","volume":"14","author":"T Sharot","year":"2011","unstructured":"Sharot T, Korn CW, Dolan RJ (2011) How unrealistic optimism is maintained in the face of reality. Nat Neurosci 14(11):1475\u20131479","journal-title":"Nat Neurosci"},{"issue":"2","key":"571_CR36","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.neuron.2013.07.007","volume":"79","author":"A Shenhav","year":"2013","unstructured":"Shenhav A, Botvinick MM, Cohen JD (2013) The expected value of control: an integrative theory of anterior cingulate cortex function. Neuron 79(2):217\u2013240","journal-title":"Neuron"},{"key":"571_CR37","unstructured":"Sutton RS (1984) Temporal credit assignment in reinforcement learning. Doctoral Dissertation, UMass Amherst"},{"key":"571_CR38","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT Press, Cambridge, MA"},{"issue":"4","key":"571_CR39","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1177\/1073858411435128","volume":"18","author":"M Meer van der","year":"2012","unstructured":"van der Meer M, Kurth-Nelson Z, Redish AD (2012) Information processing in decision-making systems. Neuroscientist 18(4):342\u2013359","journal-title":"Neuroscientist"},{"key":"571_CR40","unstructured":"Watkins C (1989) Learning from delayed rewards. PhD thesis"},{"issue":"22","key":"571_CR41","doi-asserted-by":"crossref","first-page":"R977","DOI":"10.1016\/j.cub.2007.09.007","volume":"17","author":"AJ Yu","year":"2007","unstructured":"Yu AJ (2007) Adaptive behavior: humans act as bayesian learners. Curr Biol 17(22):R977\u2013R980","journal-title":"Curr Biol"}],"container-title":["Biological Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00422-013-0571-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00422-013-0571-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00422-013-0571-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T20:31:19Z","timestamp":1559075479000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00422-013-0571-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,10,2]]},"references-count":41,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2013,12]]}},"alternative-id":["571"],"URL":"https:\/\/doi.org\/10.1007\/s00422-013-0571-5","relation":{},"ISSN":["0340-1200","1432-0770"],"issn-type":[{"value":"0340-1200","type":"print"},{"value":"1432-0770","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,10,2]]}}}