{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T12:20:27Z","timestamp":1776687627873,"version":"3.51.2"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1006827","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2019,3,29]],"date-time":"2019-03-29T00:00:00Z","timestamp":1553817600000}}],"reference-count":30,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2019,3,12]],"date-time":"2019-03-12T00:00:00Z","timestamp":1552348800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP150104878"],"award-info":[{"award-number":["DP150104878"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000324","name":"Gatsby Charitable Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000324","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"DOI":"10.1371\/journal.pcbi.1006827","type":"journal-article","created":{"date-parts":[[2019,3,12]],"date-time":"2019-03-12T17:35:48Z","timestamp":1552412148000},"page":"e1006827","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":24,"title":["Optimizing the depth and the direction of prospective planning using information values"],"prefix":"10.1371","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9661-2519","authenticated-orcid":true,"given":"Can Eren","family":"Sezener","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amir","family":"Dezfouli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehdi","family":"Keramati","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2019,3,12]]},"reference":[{"key":"ref1","article-title":"Meditations","author":"M Aurelius","year":"2014"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1109\/TNN.1998.712192","article-title":"Introduction to Reinforcement Learning","author":"RS Sutton","year":"1998"},{"key":"ref3","article-title":"Artificial Intelligence: A Modern Approach","author":"SJ Russell","year":"2002"},{"key":"ref4","article-title":"Studies in limited rationality","author":"S Russell","year":"1991"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1593","DOI":"10.1126\/science.275.5306.1593","article-title":"A Neural Substrate of Prediction and Reward","volume":"275","author":"W Schultz","year":"1997","journal-title":"Science"},{"issue":"6","key":"ref6","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"},{"issue":"9","key":"ref7","first-page":"1","article-title":"Flexibility to contingency changes distinguishes habitual and goal-directed strategies in humans","volume":"13","author":"JJ Lee","year":"2017","journal-title":"PLOS Computational Biology"},{"issue":"1","key":"ref8","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1038\/npp.2009.131","article-title":"Human and Rodent Homologies in Action Control: Corticostriatal Determinants of Goal-Directed and Habitual Action","volume":"35","author":"BW Balleine","year":"2010","journal-title":"Neuropsychopharmacology"},{"key":"ref9","article-title":"Steven\u2019s Handbook of Experimental Psychology: Learning, Motivation, and Emotion","volume":"Vol.3","author":"A Dickinson","year":"2002"},{"issue":"7587","key":"ref10","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"D Silver","year":"2016","journal-title":"Nature"},{"issue":"45","key":"ref11","doi-asserted-by":"crossref","first-page":"12868","DOI":"10.1073\/pnas.1609094113","article-title":"Adaptive integration of habits into depth-limited planning defines a habitual-goal?directed spectrum","volume":"113","author":"M Keramati","year":"2016","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"3","key":"ref12","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 Computational Biology"},{"issue":"10","key":"ref13","doi-asserted-by":"crossref","first-page":"3098","DOI":"10.1073\/pnas.1414219112","article-title":"Interplay of approximate planning strategies","volume":"112","author":"QJM Huys","year":"2015","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"2","key":"ref14","doi-asserted-by":"crossref","first-page":"197","DOI":"10.3758\/BF03199935","article-title":"Motivational control after extended instrumental training","volume":"23","author":"A Dickinson","year":"1995","journal-title":"Animal Learning & Behavior"},{"issue":"2","key":"ref15","first-page":"104","article-title":"Relations Between Pavlovian-Instrumental Transfer and Reinforcer Devaluation","volume":"30","author":"PC Holland","year":"2004","journal-title":"Journal of Experimental Psychology: Animal Behavior Processes"},{"issue":"4","key":"ref16","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":"Cerebral Cortex"},{"issue":"1","key":"ref17","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":"European Journal of Neuroscience"},{"key":"ref18","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":"Nature Neuroscience"},{"issue":"5","key":"ref19","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1002055","article-title":"Speed\/Accuracy Trade-Off between the Habitual and the Goal-Directed Processes","volume":"7","author":"MM Keramati","year":"2011","journal-title":"PLoS Computational Biology"},{"key":"ref20","unstructured":"Kocsis L, Szepesv\u00e1ri C. Bandit Based Monte-carlo Planning. In: Proceedings of the 17th European Conference on Machine Learning. ECML\u201906. Berlin, Heidelberg: Springer-Verlag; 2006. p. 282\u2013293. Available from: <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/dx.doi.org\/10.1007\/11871842_29\" xlink:type=\"simple\">http:\/\/dx.doi.org\/10.1007\/11871842_29<\/ext-link>."},{"key":"ref21","unstructured":"Tolpin D, Shimony SE. MCTS Based on Simple Regret. In: Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, July 22-26, 2012, Toronto, Ontario, Canada.; 2012. Available from: <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI12\/paper\/view\/4798\" xlink:type=\"simple\">http:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI12\/paper\/view\/4798<\/ext-link>."},{"key":"ref22","unstructured":"Hay N, Russell S, Tolpin D, Shimony SE. Selecting Computations: Theory and Applications. In: Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence. UAI\u201912. Arlington, Virginia, United States: AUAI Press; 2012. p. 346\u2013355. Available from: <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/dl.acm.org\/citation.cfm?id=3020652.3020691\" xlink:type=\"simple\">http:\/\/dl.acm.org\/citation.cfm?id=3020652.3020691<\/ext-link>."},{"issue":"7","key":"ref23","doi-asserted-by":"crossref","first-page":"1036","DOI":"10.1111\/j.1460-9568.2012.08050.x","article-title":"Habits, action sequences and reinforcement learning","volume":"35","author":"A Dezfouli","year":"2012","journal-title":"European Journal of Neuroscience"},{"issue":"2","key":"ref24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pcbi.0040004","article-title":"Serotonin, Inhibition, and Negative Mood","volume":"4","author":"P Dayan","year":"2008","journal-title":"PLOS Computational Biology"},{"issue":"1","key":"ref25","first-page":"483","article-title":"Kalman Temporal Differences","volume":"39","author":"M Geist","year":"2010","journal-title":"J Artif Int Res"},{"key":"ref26","unstructured":"Dearden R, Friedman N, Russell S. Bayesian Q-learning. In: Proceedings of the Fifteenth National\/Tenth Conference on Artificial Intelligence\/Innovative Applications of Artificial Intelligence. AAAI\u201998\/IAAI\u201998. Menlo Park, CA, USA: American Association for Artificial Intelligence; 1998. p. 761\u2013768."},{"issue":"2","key":"ref27","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1037\/h0043158","article-title":"The Magical Number Seven, Plus or Minus Two: Some Limits on Our Capacity for Processing Information","volume":"63","author":"GA Miller","year":"1956","journal-title":"The Psychological Review"},{"issue":"1","key":"ref28","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1017\/S0140525X01003922","article-title":"The Magical Number 4 in Short-term Memory: A Reconsideration of Mental Storage Capacity","volume":"24","author":"N Cowan","year":"2001","journal-title":"Behavioral and Brain Sciences"},{"issue":"3","key":"ref29","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1038\/nn.3655","article-title":"Changing concepts of working memory","volume":"17","author":"WJ Ma","year":"2014","journal-title":"Nat Neurosci"},{"key":"ref30","article-title":"Budgeted Learning, Part I: The Multi-Armed Bandit Case","author":"O Madani","year":"2003"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1006827","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2019,3,29]],"date-time":"2019-03-29T00:00:00Z","timestamp":1553817600000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1006827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,9]],"date-time":"2020-05-09T09:12:11Z","timestamp":1589015531000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1006827"}},"subtitle":[],"editor":[{"given":"Marcelo Gomes","family":"Mattar","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2019,3,12]]},"references-count":30,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2019,3,12]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1006827","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1006827","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3,12]]}}}