{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T06:37:29Z","timestamp":1792651049476,"version":"4.5.0"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1005768","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2017,10,5]],"date-time":"2017-10-05T00:00:00Z","timestamp":1507161600000}}],"reference-count":116,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2017,9,25]],"date-time":"2017-09-25T00:00:00Z","timestamp":1506297600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000025","name":"National Institute of Mental Health (US)","doi-asserted-by":"crossref","award":["T32 MH019524"],"award-info":[{"award-number":["T32 MH019524"]}],"id":[{"id":"10.13039\/100000025","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["5R01MH109177-02"],"award-info":[{"award-number":["5R01MH109177-02"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000925","name":"John Templeton Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000925","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.1005768","type":"journal-article","created":{"date-parts":[[2017,9,25]],"date-time":"2017-09-25T13:24:36Z","timestamp":1506345876000},"page":"e1005768","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":271,"title":["Predictive representations can link model-based reinforcement learning to model-free mechanisms"],"prefix":"10.1371","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2929-6912","authenticated-orcid":true,"given":"Evan M.","family":"Russek","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ida","family":"Momennejad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew M.","family":"Botvinick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6546-3298","authenticated-orcid":true,"given":"Samuel J.","family":"Gershman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5029-1430","authenticated-orcid":true,"given":"Nathaniel D.","family":"Daw","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2017,9,25]]},"reference":[{"key":"ref1","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":"ref2","first-page":"249","article-title":"A model of how the basal ganglia generates and uses neural signals that predict reinforcement","author":"JC Houk","year":"1995","journal-title":"Model Inf Process Basal Ganglia"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.1523\/JNEUROSCI.16-05-01936.1996","article-title":"A framework for mesencephalic dopamine systems based on predictive Hebbian learning","volume":"16","author":"PR Montague","year":"1996","journal-title":"J Neurosci"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1940","DOI":"10.1126\/science.1102941","article-title":"By Carrot or by Stick: Cognitive Reinforcement Learning in Parkinsonism","volume":"306","author":"MJ Frank","year":"2004","journal-title":"Science"},{"key":"ref5","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":"ref6","first-page":"1204","article-title":"Model-based influences on humans\u2019 choices and striatal prediction errors","volume":"69","author":"ND Daw","year":"2011"},{"key":"ref7","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":"ref8","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1523\/JNEUROSCI.1901-15.2016","article-title":"Variability in Dopamine Genes Dissociates Model-Based and Model-Free Reinforcement Learning","volume":"36","author":"BB Doll","year":"2016","journal-title":"J Neurosci"},{"key":"ref9","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 U S A"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1093\/brain\/awv347","article-title":"Dopamine selectively remediates \u201cmodel-based\u201d reward learning: A computational approach","volume":"139","author":"ME Sharp","year":"2015","journal-title":"Brain"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.7554\/eLife.13665","article-title":"Midbrain dopamine neurons compute inferred and cached value prediction errors in a common framework","volume":"5","author":"BF Sadacca","year":"2016","journal-title":"Elife"},{"key":"ref12","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 Glascher","year":"2010","journal-title":"Neuron"},{"key":"ref13","first-page":"367","article-title":"Multiple Forms of Value Learning and the Function of Dopamine BT\u2014Neuroeconomics: Decision Making and the Brain","author":"BW Balleine","year":"2008","journal-title":"Neuroeconomics Decision Making and the Brain"},{"key":"ref14","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 Lond B Biol Sci"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1162\/neco.1993.5.4.613","article-title":"Improving Generalisation for Temporal Difference Learning: The Successor Representation","volume":"5","author":"P Dayan","year":"1993","journal-title":"Neural Comput"},{"key":"ref16","article-title":"Motivated Reinforcement Learning","author":"P Dayan","year":"2002","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref17","first-page":"54","article-title":"The learning of world models by connectionist networks","author":"RS Sutton","year":"1985","journal-title":"Proceedings of the Seventh Annual Conference of the Cognitive Science Society"},{"key":"ref18","first-page":"1","article-title":"Design Principles of the Hippocampal Cognitive Map","author":"KL Stachenfeld","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1162\/NECO_a_00282","article-title":"The Successor Representation and Temporal Context","volume":"24","author":"SJ Gershman","year":"2012","journal-title":"Neural Comput"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/s002210100814","article-title":"Anticipatory responses of dopamine neurons and cortical neurons reproduced by internal model","volume":"140","author":"RE Suri","year":"2001","journal-title":"Exp Brain Res"},{"key":"ref21","unstructured":"Barreto A, Munos R, Schaul T, Silver D. Successor Features for Transfer in Reinforcement Learning. arXiv Prepr. 2016;1606."},{"key":"ref22","unstructured":"Lehnert L, Tellex S, Littman ML. Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning. arXiv. 2017; Available: <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/arxiv.org\/pdf\/1708.00102.pdf\" xlink:type=\"simple\">https:\/\/arxiv.org\/pdf\/1708.00102.pdf<\/ext-link>"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1037\/h0061626","article-title":"Cognitive maps in rats and men","volume":"55","author":"EC Tolman","year":"1948","journal-title":"Psychol Rev"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"5526","DOI":"10.1523\/JNEUROSCI.4647-10.2011","article-title":"Neural correlates of forward planning in a spatial decision task in humans","volume":"31","author":"DA Simon","year":"2011","journal-title":"J Neurosci"},{"key":"ref25","article-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2012"},{"key":"ref26","first-page":"283","article-title":"Neuroeconomics","author":"ND Daw","year":"2014"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1145\/122344.122377","article-title":"Dyna, an integrated architecture for learning, planning, and reacting","volume":"2","author":"RS Sutton","year":"1991","journal-title":"ACM SIGART Bull"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1037\/a0030844","article-title":"Retrospective revaluation in sequential decision making: a tale of two systems","volume":"143","author":"SJ Gershman","year":"2014","journal-title":"J Exp Psychol Gen"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1126\/science.1115270","article-title":"Representation of Action-Specific Reward Values in the Striatum","volume":"310","author":"K Samejima","year":"2005","journal-title":"Science"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1016\/j.neuron.2008.02.021","article-title":"Value Representations in the Primate Striatum during Matching Behavior","volume":"58","author":"B Lau","year":"2008","journal-title":"Neuron"},{"issue":"Suppl","key":"ref31","doi-asserted-by":"crossref","first-page":"15647","DOI":"10.1073\/pnas.1014269108","article-title":"Understanding dopamine and reinforcement learning: the dopamine reward prediction error hypothesis","volume":"108","author":"PW Glimcher","year":"2011","journal-title":"Proc Natl Acad Sci U S A"},{"key":"ref32","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":"ref33","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1016\/0166-2236(90)90107-L","article-title":"Functional architecture of basal ganglia circuits: neural substrated of parallel processing","volume":"13","author":"GE Alexander","year":"1990","journal-title":"Trends Neurosci"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1097\/00005053-191205000-00016","article-title":"Animal Intelligence. Experimental Studies","author":"EL Thorndike","year":"1912","journal-title":"The Journal of Nervous and Mental Disease"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1111\/1468-0262.00054","article-title":"Experience-Weighted Atttraction in Normal Form Games","volume":"67","author":"C Camerer","year":"1999","journal-title":"Econometrica"},{"key":"ref36","first-page":"497","article-title":"Steven\u2019s handbook of experimental psychology: Learning, motivation and emotion","author":"A Dickinson","year":"2002"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1126\/science.1223252","article-title":"Preference by association: how memory mechanisms in the hippocampus bias decisions","volume":"338","author":"GE Wimmer","year":"2012","journal-title":"Science"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1098\/rstb.1985.0010","article-title":"Actions and Habits: The Development of Behavioural Autonomy","author":"A Dickinson","year":"1985","journal-title":"Philosophical Transactions of the Royal Society B: Biological Sciences"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3758\/BF03199951","article-title":"Motivational control of goal-directed action.","volume":"22","author":"A Dickinson","year":"1994","journal-title":"Anim Learn Behav"},{"key":"ref40","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":"ref41","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":"M Keramati","year":"2011","journal-title":"PLoS Comput Biol"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"1","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":"ref43","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1037\/a0026435","article-title":"Goal-directed decision making as probabilistic inference: a computational framework and potential neural correlates","volume":"119","author":"A Solway","year":"2012","journal-title":"Psychol Rev"},{"key":"ref44","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"},{"key":"ref45","first-page":"367","article-title":"Neuroeconomics","author":"BW Balleine","year":"2009","journal-title":"Neuroeconomics"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"887","DOI":"10.1038\/nn1279","article-title":"Prediction of Immediate and Future Rewards Differentially Recruits Cortico-Basal Ganglia Loops","author":"SC Tanaka","year":"2004","journal-title":"Nature Neuroscience. Tokyo"},{"key":"ref47","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":"Eur J Neurosci"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/j.jchemneu.2003.10.003","article-title":"The primate basal ganglia: Parallel and integrative networks","volume":"26","author":"SN Haber","year":"2003","journal-title":"J Chem Neuroanat"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"2771","DOI":"10.1523\/JNEUROSCI.3894-04.2005","article-title":"Lesion to the Nigrostriatal Dopamine System Disrupts Stimulus\u2013Response Habit Formation","volume":"25","author":"A Faure","year":"2005","journal-title":"J Neurosci"},{"key":"ref50","author":"RS Sutton","year":"1998"},{"key":"ref51","first-page":"1","article-title":"What are the Computations of the Cerebellum, the Basal Gangila, and the Cerebral Cortex?","volume":"12","author":"K Doya","year":"1999","journal-title":"Sci Technol"},{"key":"ref52","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":"Proc Natl Acad Sci U S A"},{"key":"ref53","first-page":"6","article-title":"Expectancies in decision making, reinforcement learning, and ventral striatum","volume":"3","author":"MAA van der Meer","year":"2010","journal-title":"Front Neurosci"},{"key":"ref54","unstructured":"Ludvig EA, Mirian MS, Kehoe EJ, Sutton RS. Associative learning from replayed experience. bioRxiv. 2017; <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/doi.org\/10.1101\/100800\" xlink:type=\"simple\">https:\/\/doi.org\/10.1101\/100800<\/ext-link>"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"2221","DOI":"10.1162\/089976601750541787","article-title":"Spike-timing-dependent Hebbian plasticity as temporal difference learning","volume":"13","author":"RP Rao","year":"2001","journal-title":"Neural Comput"},{"key":"ref56","article-title":"Approximate Linear Successor Representation","author":"CA Gehring","year":"2015","journal-title":"Reinforcement Learning Decision Making"},{"key":"ref57","author":"EC Tolman","year":"1930"},{"key":"ref58","first-page":"397","article-title":"An optimization network for matrix inversion","author":"J Jang","year":"1988","journal-title":"Neural Inf Process Syst"},{"key":"ref59","doi-asserted-by":"crossref","first-page":"680","DOI":"10.1038\/s41562-017-0180-8","article-title":"The successor representation in human reinforcement learning","volume":"1","author":"I Momennejad","year":"2017","journal-title":"Nat Hum Behav"},{"key":"ref60","doi-asserted-by":"crossref","unstructured":"Wang T, Bowlingm M, Schuurmans D. Dual representations for dynamic programming and reinforcement learning. Proceedings of the 2007 IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning, ADPRL 2007. 2007. pp. 44\u201351. 10.1109\/ADPRL.2007.368168","DOI":"10.1109\/ADPRL.2007.368168"},{"key":"ref61","article-title":"Temporal Difference Learning: Eligibility Traces and the Successor Representation for Actions","author":"LM White","year":"1995"},{"key":"ref62","unstructured":"Blundell C, Uria B, Pritzel A, Li Y, Ruderman A, Leibo JZ, et al. Model-Free Episodic Control. arXiv:160604460v1 [statML]. 2016; 1\u201312."},{"key":"ref63","doi-asserted-by":"crossref","DOI":"10.1126\/science.8036517","article-title":"Reactivation of hippocampal ensemble memories during sleep","volume":"265","author":"M Wilson","year":"1994","journal-title":"Science"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"4090","DOI":"10.1523\/JNEUROSCI.19-10-04090.1999","article-title":"Reactivation of hippocampal cell assemblies: effects of behavioral state, experience, and EEG dynamics","volume":"19","author":"HS Kudrimoti","year":"1999","journal-title":"J Neurosci"},{"key":"ref65","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1037\/0033-295X.102.3.419","article-title":"Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory","volume":"102","author":"JL McClelland","year":"1995","journal-title":"Psychol Rev"},{"key":"ref66","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1016\/0306-4522(89)90423-5","article-title":"Two-stage model of memory trace formation: A role for \u201cnoisy\u201d brain states","volume":"31","author":"G Buzs\u00e1ki","year":"1989","journal-title":"Neuroscience"},{"key":"ref67","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1007\/BF00993104","article-title":"Prioritized Sweeping: Reinforcement Learning with Less Data and Less Time","volume":"13","author":"AW Moore","year":"1993","journal-title":"Mach Learn"},{"key":"ref68","doi-asserted-by":"crossref","article-title":"Dissociable contribution of prefrontal and striatal dopaminergic genes to learning in economic games","author":"E Set","DOI":"10.1073\/pnas.1316259111"},{"key":"ref69","doi-asserted-by":"crossref","first-page":"1184","DOI":"10.1038\/81460","article-title":"Neurocomputational models of working memory","volume":"3","author":"D Durstewitz","year":"2000","journal-title":"Nat Neurosci"},{"key":"ref70","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1007\/s00213-006-0502-4","article-title":"Tonic dopamine: Opportunity costs and the control of response vigor","volume":"191","author":"Y Niv","year":"2007","journal-title":"Psychopharmacology (Berl)"},{"key":"ref71","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1016\/j.tics.2015.08.013","article-title":"Deciding How To Decide: Self-Control and Meta-Decision Making","volume":"19","author":"YL Boureau","year":"2015","journal-title":"Trends Cogn Sci"},{"key":"ref72","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":"Proc Natl Acad Sci U S A"},{"key":"ref73","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/j.conb.2014.01.001","article-title":"Multiplexing signals in reinforcement learning with internal models and dopamine","volume":"25","author":"N Hiroyuki","year":"2014","journal-title":"Curr Opin Neurobiol"},{"key":"ref74","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pcbi.1004648","article-title":"Simple Plans or Sophisticated Habits? State, Transition and Learning Interactions in the Two-Step Task","volume":"11","author":"T Akam","year":"2015","journal-title":"PLoS Comput Biol"},{"key":"ref75","article-title":"TD Models: Modeling the world at a mixture of time scales","author":"RS Sutton","year":"1995","journal-title":"Proceedings of the 12th Int Conf on Machine Learning"},{"key":"ref76","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cobeha.2015.06.001","article-title":"Hierarchical control of goal-directed action in the cortical\u2013basal ganglia network","volume":"5","author":"BW Balleine","year":"2015","journal-title":"Curr Opin Behav Sci"},{"key":"ref77","doi-asserted-by":"crossref","first-page":"1492","DOI":"10.1038\/nn.3515","article-title":"Online evaluation of novel choices by simultaneous representation of multiple memories","volume":"16","author":"HC Barron","year":"2013","journal-title":"Nat Neurosci"},{"key":"ref78","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1016\/j.neuron.2016.10.028","article-title":"Interplay between Hippocampal Sharp-Wave-Ripple Events and Vicarious Trial and Error Behaviors in Report Interplay between Hippocampal Sharp-Wave-Ripple Events and Vicarious Trial and Error Behaviors in Decision Making","volume":"92","author":"AE Papale","year":"2016","journal-title":"Neuron"},{"key":"ref79","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1016\/j.neuron.2013.11.028","article-title":"Neural Computations Underlying Arbitration between Model-Based and Model-free Learning","volume":"81","author":"SW Lee","year":"2014","journal-title":"Neuron"},{"key":"ref80","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1016\/j.neuron.2010.01.034","article-title":"Hippocampal Replay Is Not a Simple Function of Experience","volume":"65","author":"AS Gupta","year":"2010","journal-title":"Neuron"},{"key":"ref81","first-page":"461","article-title":"Tolman and Honzik (1930) revisited: or The mazes of psychology (1930\u20131980)","volume":"41","author":"F Ciancia","year":"1991","journal-title":"Psychol Rec"},{"key":"ref82","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1016\/S0003-3472(83)80083-9","article-title":"Route planning in cats, in relation to the visibility of the goal","volume":"31","author":"B Poucet","year":"1983","journal-title":"Anim Behav"},{"key":"ref83","doi-asserted-by":"crossref","first-page":"1350","DOI":"10.1002\/hipo.20721","article-title":"An investigation of the effects of hippocampal lesions in rats on pre- and postoperatively acquired spatial memory in a complex environment","volume":"20","author":"G Winocur","year":"2010","journal-title":"Hippocampus"},{"key":"ref84","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.bbr.2011.02.035","article-title":"Horizontal biases in rats\u2019 use of three-dimensional space","volume":"222","author":"A Jovalekic","year":"2011","journal-title":"Behav Brain Res"},{"key":"ref85","doi-asserted-by":"crossref","first-page":"174","DOI":"10.3758\/BF03204960","article-title":"The role of exploratory experience in a shortcut task by golden hamsters (&amp;lt;i&amp;gt;Mesocricetus auratus&amp;lt;\/i&amp;gt;)","volume":"15","author":"N Chapuis","year":"1987","journal-title":"Learn Behav"},{"key":"ref86","doi-asserted-by":"crossref","first-page":"7324","DOI":"10.1523\/JNEUROSCI.1909-08.2008","article-title":"Different CA1 and CA3 representations of novel routes in a shortcut situation","volume":"28","author":"A Alvernhe","year":"2008","journal-title":"J Neurosci"},{"key":"ref87","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fnhum.2015.00125","article-title":"Solving the detour problem in navigation: a model of prefrontal and hippocampal interactions","volume":"9","author":"HJ Spiers","year":"2015","journal-title":"Front Hum Neurosci"},{"key":"ref88","doi-asserted-by":"crossref","first-page":"10976","DOI":"10.1523\/JNEUROSCI.22-24-10976.2002","article-title":"Sensitivity to instrumental contingency degradation is mediated by the entorhinal cortex and its efferents via the dorsal hippocampus","volume":"22","author":"LH Corbit","year":"2002","journal-title":"J Neurosci"},{"key":"ref89","doi-asserted-by":"crossref","first-page":"1222","DOI":"10.1038\/nn.2384","article-title":"Selective suppression of hippocampal ripples impairs spatial memory","volume":"12","author":"G Girardeau","year":"2009","journal-title":"Nat Neurosci"},{"key":"ref90","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/hipo.20707","article-title":"Disruption of ripple-associated hippocampal activity during rest impairs spatial learning in the rat","volume":"20","author":"V Ego-Stengel","year":"2010","journal-title":"Hippocampus"},{"key":"ref91","doi-asserted-by":"crossref","DOI":"10.1126\/science.1217230","article-title":"Awake Hippocampal Sharp-Wave Ripples Support Spatial Memory","volume":"336","author":"SP Jadhav","year":"2012","journal-title":"Science"},{"key":"ref92","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fnbeh.2012.00079","article-title":"Integrating cortico-limbic-basal ganglia architectures for learning model-based and model-free navigation strategies","volume":"6","author":"M Khamassi","year":"2012","journal-title":"Front Behav Neurosci"},{"key":"ref93","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":"ref94","doi-asserted-by":"crossref","first-page":"10692","DOI":"10.1523\/JNEUROSCI.4828-09.2010","article-title":"Temporally extended dopamine responses to perceptually demanding reward-predictive stimuli","volume":"30","author":"K Nomoto","year":"2010","journal-title":"J Neurosci"},{"key":"ref95","doi-asserted-by":"crossref","first-page":"429","DOI":"10.3758\/CABN.8.4.429","article-title":"Decision theory, reinforcement learning, and the brain","volume":"8","author":"P Dayan","year":"2008","journal-title":"Cogn Affect Behav Neurosci"},{"key":"ref96","first-page":"1555","article-title":"Predictive Representations of State","volume":"14","author":"ML Littman","year":"2001","journal-title":"Neural Inf Process Syst"},{"key":"ref97","unstructured":"Schlegel M, White A, White M. Stable predictive representations with general value functions for continual learning. Continual Learning and Deep Networks workshop at the Neural Information Processing System Conference. 2017. Available: <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/sites.ualberta.ca\/~amw8\/cldl.pdf\" xlink:type=\"simple\">https:\/\/sites.ualberta.ca\/~amw8\/cldl.pdf<\/ext-link>"},{"key":"ref98","doi-asserted-by":"crossref","first-page":"31378","DOI":"10.1038\/srep31378","article-title":"Model-based action planning involves cortico-cerebellar and basal ganglia networks","volume":"6","author":"ASR Fermin","year":"2016","journal-title":"Sci Rep"},{"key":"ref99","unstructured":"Stachenfeld KL, Botvinick MM, Gershman SJ. The hippocampus as a predictive map. biorRxiv. 2017; <comment>doi: <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/doi.org\/10.1101\/097170\" xlink:type=\"simple\">http:\/\/dx.doi.org\/10.1101\/097170<\/ext-link><\/comment>"},{"key":"ref100","doi-asserted-by":"crossref","first-page":"486","DOI":"10.1038\/nn.3331","article-title":"Neural representations of events arise from temporal community structure","volume":"16","author":"AC Schapiro","year":"2013","journal-title":"Nat Neurosci"},{"key":"ref101","doi-asserted-by":"crossref","first-page":"1","DOI":"10.7554\/eLife.17086","article-title":"A map of abstract relational knowledge in the human hippocampal\u2013entorhinal cortex","volume":"6","author":"MM Garvert","year":"2017","journal-title":"Elife"},{"key":"ref102","article-title":"The hippocampus as a cognitive map","author":"J O\u2019Keefe","year":"1978"},{"key":"ref103","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1007\/s004220100269","article-title":"From view cells and place cells to cognitive map learning: processing stages of the hippocampal system","volume":"86","author":"P Gaussier","year":"2002","journal-title":"Biol Cybern"},{"key":"ref104","doi-asserted-by":"crossref","first-page":"e1002235","DOI":"10.1371\/journal.pcbi.1002235","article-title":"Grid Cells, Place Cells, and Geodesic Generalization for Spatial Reinforcement Learning","volume":"7","author":"NJ Gustafson","year":"2011","journal-title":"PLoS Comput Biol"},{"key":"ref105","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1038\/nrn.2016.56","article-title":"Over the river, through the woods: cognitive maps in the hippocampus and orbitofrontal cortex","volume":"17","author":"AM Wikenheiser","year":"2016","journal-title":"Nat Rev Neurosci"},{"key":"ref106","doi-asserted-by":"crossref","first-page":"1402","DOI":"10.1016\/j.neuron.2016.08.019","article-title":"Human Orbitofrontal Cortex Represents a Cognitive Map of State Space","volume":"91","author":"NW Schuck","year":"2016","journal-title":"Neuron"},{"key":"ref107","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.neuroimage.2012.02.079","article-title":"Human anterior prefrontal cortex encodes the \u201cwhat\u201d and \u201cwhen\u201d of future intentions","volume":"61","author":"I Momennejad","year":"2012","journal-title":"Neuroimage"},{"key":"ref108","doi-asserted-by":"crossref","first-page":"17342","DOI":"10.1523\/JNEUROSCI.0492-13.2013","article-title":"Encoding of Prospective Tasks in the Human Prefrontal Cortex under Varying Task Loads","volume":"33","author":"I Momennejad","year":"2013","journal-title":"J Neurosci"},{"key":"ref109","doi-asserted-by":"crossref","unstructured":"Miller EK, Cohen JD. A N I NTEGRATIVE T HEORY OF P REFRONTAL C ORTEX F UNCTION. 2001; 167\u2013202.","DOI":"10.1146\/annurev.neuro.24.1.167"},{"key":"ref110","doi-asserted-by":"crossref","first-page":"1197","DOI":"10.1016\/j.neuron.2017.08.003","article-title":"Suppression of Ventral Hippocampal Output Impairs Integrated Orbitofrontal Encoding of Task Structure","volume":"95","author":"AM Wikenheiser","year":"2017","journal-title":"Neuron"},{"key":"ref111","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":"ref112","doi-asserted-by":"crossref","first-page":"20130480","DOI":"10.1098\/rstb.2013.0480","article-title":"Model-based hierarchical reinforcement learning and human action control","volume":"369","author":"M Botvinick","year":"2014","journal-title":"Philos Trans R Soc Lond B Biol Sci"},{"key":"ref113","article-title":"Neural representations of events arise from temporal community structure","volume":"16","author":"AC Schapiro","year":"2013","journal-title":"Nat Publ Gr"},{"key":"ref114","doi-asserted-by":"crossref","first-page":"1343","DOI":"10.1016\/j.neuron.2016.02.014","article-title":"Two Anatomically and Computationally Distinct Learning Signals Predict Changes to Stimulus-Outcome Associations in Hippocampus","volume":"89","author":"ED Boorman","year":"2016","journal-title":"Neuron"},{"key":"ref115","doi-asserted-by":"crossref","first-page":"767","DOI":"10.1038\/nn.3981","article-title":"Model-based choices involve prospective neural activity","volume":"18","author":"BB Doll","year":"2015","journal-title":"Nat Neurosci"},{"key":"ref116","doi-asserted-by":"crossref","DOI":"10.1038\/nn.4287","article-title":"Reward and choice encoding in terminals of midbrain dopamine neurons depends on striatal target","volume":"19","author":"NF Parker","year":"2016","journal-title":"Nat Neurosci"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1005768","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2017,10,5]],"date-time":"2017-10-05T00:00:00Z","timestamp":1507161600000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1005768","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T03:01:11Z","timestamp":1719457271000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1005768"}},"subtitle":[],"editor":[{"given":"Jean","family":"Daunizeau","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2017,9,25]]},"references-count":116,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2017,9,25]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1005768","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/083857","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,9,25]]}}}