{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T17:21:55Z","timestamp":1774977715515,"version":"3.50.1"},"reference-count":55,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2015,12,11]],"date-time":"2015-12-11T00:00:00Z","timestamp":1449792000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"DOI":"10.1371\/journal.pcbi.1004648","type":"journal-article","created":{"date-parts":[[2015,12,14]],"date-time":"2015-12-14T12:57:54Z","timestamp":1450097874000},"page":"e1004648","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":129,"title":["Simple Plans or Sophisticated Habits? State, Transition and Learning Interactions in the Two-Step Task"],"prefix":"10.1371","volume":"11","author":[{"given":"Thomas","family":"Akam","sequence":"first","affiliation":[]},{"given":"Rui","family":"Costa","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Dayan","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2015,12,11]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1016\/S0028-3908(98)00033-1","article-title":"Goal-directed instrumental action: contingency and incentive learning and their cortical substrates","volume":"37","author":"BW Balleine","year":"1998","journal-title":"Neuropharmacology"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.neuron.2013.09.007","article-title":"Goals and Habits in the Brain","volume":"80","author":"RJ Dolan","year":"2013","journal-title":"Neuron"},{"key":"ref3","author":"RS Sutton","year":"1998"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1704","DOI":"10.1038\/nn1560","article-title":"Uncertainty-based competition between prefrontal and dorsolateral striatal systems for behavioral control","volume":"8","author":"ND Daw","year":"2005","journal-title":"Nat Neurosci"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1016\/j.neuron.2010.04.016","article-title":"States versus Rewards: Dissociable Neural Prediction Error Signals Underlying Model-Based and Model-Free Reinforcement Learning","volume":"66","author":"J Gl\u00e4scher","year":"2010","journal-title":"Neuron"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"e1002055","DOI":"10.1371\/journal.pcbi.1002055","article-title":"Speed\/accuracy trade-off between the habitual and the goal-directed processes","volume":"7","author":"M Keramati","year":"2011","journal-title":"PLoS Comput Biol"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1204","DOI":"10.1016\/j.neuron.2011.02.027","article-title":"Model-based influences on humans\u2019 choices and striatal prediction errors","volume":"69","author":"ND Daw","year":"2011","journal-title":"Neuron"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1016\/j.neuron.2012.03.042","article-title":"Dopamine Enhances Model-Based over Model-Free Choice Behavior","volume":"75","author":"K Wunderlich","year":"2012","journal-title":"Neuron"},{"key":"ref9","article-title":"Mapping value based planning and extensively trained choice in the human brain","author":"K Wunderlich","year":"2012","journal-title":"Nat Neurosci"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"e1002410","DOI":"10.1371\/journal.pcbi.1002410","article-title":"Bonsai trees in your head: how the Pavlovian system sculpts goal-directed choices by pruning decision trees","volume":"8","author":"QJM Huys","year":"2012","journal-title":"PLoS Comput Biol"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"751","DOI":"10.1177\/0956797612463080","article-title":"The Curse of Planning Dissecting Multiple Reinforcement-Learning Systems by Taxing the Central Executive","volume":"24","author":"AR Otto","year":"2013","journal-title":"Psychol Sci"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"e1003364","DOI":"10.1371\/journal.pcbi.1003364","article-title":"Actions, Action Sequences and Habits: Evidence That Goal-Directed and Habitual Action Control Are Hierarchically Organized","volume":"9","author":"A Dezfouli","year":"2013","journal-title":"PLoS Comput Biol"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.3389\/fpsyg.2013.00092","article-title":"The Mixed Instrumental Controller: Using Value of Information to Combine Habitual Choice and Mental Simulation","volume":"4","author":"G Pezzulo","year":"2013","journal-title":"Front Psychol"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"3098","DOI":"10.1073\/pnas.1414219112","article-title":"Interplay of approximate planning strategies","volume":"112","author":"QJ Huys","year":"2015","journal-title":"Proc Natl Acad Sci"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1080\/14640748108400816","article-title":"Instrumental responding following reinforcer devaluation","volume":"33","author":"CD Adams","year":"1981","journal-title":"Q J Exp Psychol Sect B"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1037\/0097-7403.11.1.120","article-title":"Postconditioning devaluation of a reinforcer affects instrumental responding","volume":"11","author":"RM Colwill","year":"1985","journal-title":"J Exp Psychol Anim Behav Process"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1098\/rstb.1985.0010","article-title":"Actions and habits: the development of behavioural autonomy","volume":"308","author":"A Dickinson","year":"1985","journal-title":"Philos Trans R Soc B Biol Sci"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1080\/14640748308400912","article-title":"The effect of the instrumental training contingency on susceptibility to reinforcer devaluation","volume":"35","author":"A Dickinson","year":"1983","journal-title":"Q J Exp Psychol"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1523\/JNEUROSCI.23-02-00666.2003","article-title":"The Effect of Lesions of the Basolateral Amygdala on Instrumental Conditioning","volume":"23","author":"BW Balleine","year":"2003","journal-title":"J Neurosci"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.bbr.2003.09.023","article-title":"The role of prelimbic cortex in instrumental conditioning","volume":"146","author":"LH Corbit","year":"2003","journal-title":"Behav Brain Res"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1093\/cercor\/13.4.400","article-title":"Coordination of Actions and Habits in the Medial Prefrontal Cortex of Rats","volume":"13","author":"S Killcross","year":"2003","journal-title":"Cereb Cortex"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.bbr.2003.09.025","article-title":"Inactivation of the infralimbic prefrontal cortex reinstates goal-directed responding in overtrained rats","volume":"146","author":"E Coutureau","year":"2003","journal-title":"Behav Brain Res"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1111\/j.1460-9568.2004.03095.x","article-title":"Lesions of dorsolateral striatum preserve outcome expectancy but disrupt habit formation in instrumental learning","volume":"19","author":"HH Yin","year":"2004","journal-title":"Eur J Neurosci"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1111\/j.1460-9568.2005.04219.x","article-title":"Blockade of NMDA receptors in the dorsomedial striatum prevents action\u2013outcome learning in instrumental conditioning","volume":"22","author":"HH Yin","year":"2005","journal-title":"Eur J Neurosci"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1111\/j.1460-9568.2005.04218.x","article-title":"The role of the dorsomedial striatum in instrumental conditioning","volume":"22","author":"HH Yin","year":"2005","journal-title":"Eur J Neurosci"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.bbr.2005.07.012","article-title":"Inactivation of dorsolateral striatum enhances sensitivity to changes in the action-outcome contingency in instrumental conditioning","volume":"166","author":"HH Yin","year":"2006","journal-title":"Behav Brain Res"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"7763","DOI":"10.1523\/JNEUROSCI.1921-05.2005","article-title":"Lesions of medial prefrontal cortex disrupt the acquisition but not the expression of goal-directed learning","volume":"25","author":"SB Ostlund","year":"2005","journal-title":"J Neurosci"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.1111\/j.1460-9568.2012.08073.x","article-title":"Different dorsal striatum circuits mediate action discrimination and action generalization","volume":"35","author":"M Hilario","year":"2012","journal-title":"Eur J Neurosci"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1038\/ncomms3264","article-title":"Orbitofrontal and striatal circuits dynamically encode the shift between goal-directed and habitual actions","volume":"4","author":"CM Gremel","year":"2013","journal-title":"Nat Commun"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.3389\/fncom.2013.00110","article-title":"Premotor cortex is critical for goal-directed actions","volume":"7","author":"CM Gremel","year":"2013","journal-title":"Front Comput Neurosci"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"20941","DOI":"10.1073\/pnas.1312011110","article-title":"Working-memory capacity protects model-based learning from stress","volume":"110","author":"AR Otto","year":"2013","journal-title":"Proc Natl Acad Sci"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.3389\/fnhum.2013.00525","article-title":"Extraversion differentiates between model-based and model-free strategies in a reinforcement learning task","volume":"7","author":"A Skatova","year":"2013","journal-title":"Front Hum Neurosci"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2013.00253","article-title":"Of goals and habits: age-related and individual differences in goal-directed decision-making","volume":"7","author":"B Eppinger","year":"2013","journal-title":"Front Neurosci"},{"key":"ref34","article-title":"Disruption of Dorsolateral Prefrontal Cortex Decreases Model-Based in Favor of Model-free Control in Humans","author":"P Smittenaar","year":"2013","journal-title":"Neuron"},{"key":"ref35","article-title":"Cognitive control predicts use of model-based reinforcement learning","author":"AR Otto","year":"2014","journal-title":"J Cogn Neurosci"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1159\/000362840","article-title":"Model-Based and Model-Free Decisions in Alcohol Dependence","volume":"70","author":"M Sebold","year":"2014","journal-title":"Neuropsychobiology"},{"key":"ref37","article-title":"Transcranial Direct Current Stimulation of Right Dorsolateral Prefrontal Cortex Does Not Affect Model-Based or Model-Free Reinforcement Learning in Humans","author":"P Smittenaar","year":"2014","journal-title":"PLoS ONE"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.3389\/fpsyg.2014.01450","article-title":"Processing speed enhances model-based over model-free reinforcement learning in the presence of high working memory functioning","volume":"5","author":"DJ Schad","year":"2014","journal-title":"Front Psychol"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1038\/mp.2014.44","article-title":"Disorders of compulsivity: a common bias towards learning habits","volume":"20","author":"V Voon","year":"2015","journal-title":"Mol Psychiatry"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1016\/j.psyneuen.2014.12.017","article-title":"The interaction of acute and chronic stress impairs model-based behavioral control","volume":"53","author":"C Radenbach","year":"2015","journal-title":"Psychoneuroendocrinology"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"1595","DOI":"10.1073\/pnas.1417219112","article-title":"Ventral striatal dopamine reflects behavioral and neural signatures of model-based control during sequential decision making","volume":"112","author":"L Deserno","year":"2015","journal-title":"Proc Natl Acad Sci"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"e1004463","DOI":"10.1371\/journal.pcbi.1004463","article-title":"Model-Based Reasoning in Humans Becomes Automatic with Training","volume":"11","author":"M Economides","year":"2015","journal-title":"PLoS Comput Biol"},{"key":"ref43","article-title":"Valence-dependent influence of serotonin depletion on model-based choice strategy","author":"Y Worbe","year":"2015","journal-title":"Mol Psychiatry"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1038\/346174a0","article-title":"Cortical microstimulation influences perceptual judgements of motion direction","volume":"346","author":"CD Salzman","year":"1990","journal-title":"Nature"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1038\/nn1142","article-title":"Speed and accuracy of olfactory discrimination in the rat","volume":"6","author":"N Uchida","year":"2003","journal-title":"Nat Neurosci"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1126\/science.1233912","article-title":"Rats and humans can optimally accumulate evidence for decision-making","volume":"340","author":"BW Brunton","year":"2013","journal-title":"Science"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1038\/nature12077","article-title":"Corticostriatal neurons in auditory cortex drive decisions during auditory discrimination","volume":"497","author":"P Znamenskiy","year":"2013","journal-title":"Nature"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"8360","DOI":"10.1523\/JNEUROSCI.1010-06.2006","article-title":"The Role of the Ventromedial Prefrontal Cortex in Abstract State-Based Inference during Decision Making in Humans","volume":"26","author":"AN Hampton","year":"2006","journal-title":"J Neurosci"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"2407","DOI":"10.1523\/JNEUROSCI.1989-14.2015","article-title":"Reversal Learning and Dopamine: A Bayesian Perspective","volume":"35","author":"VD Costa","year":"2015","journal-title":"J Neurosci"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1162\/neco.1993.5.4.613","article-title":"Improving generalization for temporal difference learning: The successor representation","volume":"5","author":"P Dayan","year":"1993","journal-title":"Neural Comput"},{"key":"ref51","doi-asserted-by":"crossref","first-page":"20130478","DOI":"10.1098\/rstb.2013.0478","article-title":"The algorithmic anatomy of model-based evaluation","volume":"369","author":"ND Daw","year":"2014","journal-title":"Philos Trans R Soc B Biol Sci"},{"key":"ref52","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.cognition.2008.08.011","article-title":"Hierarchically organized behavior and its neural foundations: A reinforcement learning perspective","volume":"113","author":"MM Botvinick","year":"2009","journal-title":"Cognition"},{"key":"ref53","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.conb.2010.02.008","article-title":"Learning latent structure: carving nature at its joints","volume":"20","author":"SJ Gershman","year":"2010","journal-title":"Curr Opin Neurobiol"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1016\/j.neuron.2013.11.005","article-title":"Orbitofrontal Cortex as a Cognitive Map of Task Space","volume":"81","author":"RC Wilson","year":"2014","journal-title":"Neuron"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1093\/comjnl\/7.2.155","article-title":"An efficient method for finding the minimum of a function of several variables without calculating derivatives","volume":"7","author":"MJ Powell","year":"1964","journal-title":"Comput J"}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1004648","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,8]],"date-time":"2020-05-08T18:42:00Z","timestamp":1588963320000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1004648"}},"subtitle":[],"editor":[{"given":"Jean","family":"Daunizeau","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2015,12,11]]},"references-count":55,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2015,12,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1004648","relation":{"has-review":[{"id-type":"doi","id":"10.3410\/f.726009281.793588458","asserted-by":"object"}],"has-preprint":[{"id-type":"doi","id":"10.1101\/021428","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,12,11]]}}}