{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T06:05:06Z","timestamp":1772172306613,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1005925","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2018,1,17]],"date-time":"2018-01-17T00:00:00Z","timestamp":1516147200000}}],"reference-count":59,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2018,1,4]],"date-time":"2018-01-04T00:00:00Z","timestamp":1515024000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["Hundreds of Talents Program"],"award-info":[{"award-number":["Hundreds of Talents Program"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["15JC1400104"],"award-info":[{"award-number":["15JC1400104"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Public Projects of Zhejiang Province","award":["2016C31G2020069"],"award-info":[{"award-number":["2016C31G2020069"]}]},{"name":"Zhejiang Province","award":["3rd Level in 151 talents project"],"award-info":[{"award-number":["3rd Level in 151 talents project"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"DOI":"10.1371\/journal.pcbi.1005925","type":"journal-article","created":{"date-parts":[[2018,1,4]],"date-time":"2018-01-04T13:34:36Z","timestamp":1515072876000},"page":"e1005925","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":33,"title":["A neural network model for the orbitofrontal cortex and task space acquisition during reinforcement learning"],"prefix":"10.1371","volume":"14","author":[{"given":"Zhewei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2185-7006","authenticated-orcid":true,"given":"Zhenbo","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongqiao","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chechang","family":"Nie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6976-9246","authenticated-orcid":true,"given":"Tianming","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2018,1,4]]},"reference":[{"key":"ref1","first-page":"64","article-title":"Classical conditioning II: Current research and theory","author":"RA Rescorla","year":"1972"},{"issue":"32","key":"ref2","doi-asserted-by":"crossref","first-page":"8368","DOI":"10.1523\/JNEUROSCI.0271-06.2006","article-title":"Reward-related cortical inputs define a large striatal region in primates that interface with associative cortical connections, providing a substrate for incentive-based learning","volume":"26","author":"SN Haber","year":"2006","journal-title":"J Neurosci"},{"issue":"5306","key":"ref3","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":"12","key":"ref4","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.1038\/nn.2961","article-title":"Double dissociation of value computations in orbitofrontal and anterior cingulate neurons","volume":"14","author":"SW Kennerley","year":"2011","journal-title":"Nat Neurosci"},{"issue":"6","key":"ref5","doi-asserted-by":"crossref","first-page":"1204","DOI":"10.1016\/j.neuron.2011.02.027","article-title":"Model-Based Influences on Humans' Choices and Striatal Prediction Errors","volume":"69","author":"ND Daw","year":"2011","journal-title":"Neuron"},{"issue":"4","key":"ref6","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"},{"issue":"2","key":"ref7","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"},{"issue":"3","key":"ref8","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1162\/089892904322926791","article-title":"Reward-related reversal learning after surgical excisions in orbito-frontal or dorsolateral prefrontal cortex in humans","volume":"16","author":"J Hornak","year":"2004","journal-title":"J Cogn Neurosci"},{"issue":"34","key":"ref9","doi-asserted-by":"crossref","first-page":"7540","DOI":"10.1523\/JNEUROSCI.1921-04.2004","article-title":"Bilateral orbital prefrontal cortex lesions in rhesus monkeys disrupt choices guided by both reward value and reward contingency","volume":"24","author":"A Izquierdo","year":"2004","journal-title":"J Neurosci"},{"issue":"12","key":"ref10","doi-asserted-by":"crossref","first-page":"1590","DOI":"10.1038\/nn.2957","article-title":"Expectancy-related changes in firing of dopamine neurons depend on orbitofrontal cortex","volume":"14","author":"YK Takahashi","year":"2011","journal-title":"Nat Neurosci"},{"issue":"7090","key":"ref11","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1038\/nature04676","article-title":"Neurons in the orbitofrontal cortex encode economic value","volume":"441","author":"C Padoa-Schioppa","year":"2006","journal-title":"Nature"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1146\/annurev-neuro-061010-113648","article-title":"Neurobiology of economic choice: a good-based model","volume":"34","author":"C Padoa-Schioppa","year":"2011","journal-title":"Annu Rev Neurosci"},{"issue":"7","key":"ref13","doi-asserted-by":"crossref","first-page":"2069","DOI":"10.1046\/j.1460-9568.2003.02922.x","article-title":"Neuronal activity in primate dorsolateral and orbital prefrontal cortex during performance of a reward preference task","volume":"18","author":"JD Wallis","year":"2003","journal-title":"The European journal of neuroscience"},{"issue":"6109","key":"ref14","doi-asserted-by":"crossref","first-page":"953","DOI":"10.1126\/science.1227489","article-title":"Orbitofrontal cortex supports behavior and learning using inferred but not cached values","volume":"338","author":"JL Jones","year":"2012","journal-title":"Science"},{"issue":"6","key":"ref15","doi-asserted-by":"crossref","first-page":"1519","DOI":"10.1016\/j.neuron.2013.09.036","article-title":"Effects of amygdala lesions on reward-value coding in orbital and medial prefrontal cortex","volume":"80","author":"PH Rudebeck","year":"2013","journal-title":"Neuron"},{"issue":"10","key":"ref16","doi-asserted-by":"crossref","first-page":"2061","DOI":"10.1111\/j.1460-9568.2009.06743.x","article-title":"Evaluating choices by single neurons in the frontal lobe: outcome value encoded across multiple decision variables","volume":"29","author":"SW Kennerley","year":"2009","journal-title":"Eur J Neurosci"},{"issue":"1\u20133","key":"ref17","first-page":"70","article-title":"Economic risk coding by single neurons in the orbitofrontal cortex","volume":"109","author":"M O'Neill","year":"2015","journal-title":"J Physiol Paris"},{"issue":"3","key":"ref18","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neuron.2014.12.050","article-title":"Orbitofrontal cortex uses distinct codes for different choice attributes in decisions motivated by curiosity","volume":"85","author":"TC Blanchard","year":"2015","journal-title":"Neuron"},{"issue":"6840","key":"ref19","doi-asserted-by":"crossref","first-page":"953","DOI":"10.1038\/35082081","article-title":"Single neurons in prefrontal cortex encode abstract rules","volume":"411","author":"JD Wallis","year":"2001","journal-title":"Nature"},{"issue":"12","key":"ref20","doi-asserted-by":"crossref","first-page":"4583","DOI":"10.1523\/JNEUROSCI.5816-10.2011","article-title":"Comparison of strategy signals in the dorsolateral and orbital prefrontal cortex","volume":"31","author":"S Tsujimoto","year":"2011","journal-title":"J Neurosci"},{"issue":"2","key":"ref21","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1038\/nrn2558","article-title":"State-dependent computations: spatiotemporal processing in cortical networks","volume":"10","author":"DV Buonomano","year":"2009","journal-title":"Nat Rev Neurosci"},{"issue":"7","key":"ref22","doi-asserted-by":"crossref","first-page":"925","DOI":"10.1038\/nn.3405","article-title":"Robust timing and motor patterns by taming chaos in recurrent neural networks","volume":"16","author":"R Laje","year":"2013","journal-title":"Nat Neurosci"},{"issue":"11","key":"ref23","doi-asserted-by":"crossref","first-page":"2531","DOI":"10.1162\/089976602760407955","article-title":"Real-time computing without stable states: a new framework for neural computation based on perturbations","volume":"14","author":"W Maass","year":"2002","journal-title":"Neural Comput"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1016\/j.pneurobio.2013.02.002","article-title":"From fixed points to chaos: three models of delayed discrimination","volume":"103","author":"O Barak","year":"2013","journal-title":"Prog Neurobiol"},{"issue":"6","key":"ref25","doi-asserted-by":"crossref","first-page":"3296","DOI":"10.1152\/jn.00378.2015","article-title":"Efficient reinforcement learning of a reservoir network model of parametric working memory achieved with a cluster population winner-take-all readout mechanism","volume":"114","author":"Z Cheng","year":"2015","journal-title":"J Neurophysiol"},{"issue":"6","key":"ref26","doi-asserted-by":"crossref","first-page":"e1004967","DOI":"10.1371\/journal.pcbi.1004967","article-title":"Reservoir Computing Properties of Neural Dynamics in Prefrontal Cortex","volume":"12","author":"P Enel","year":"2016","journal-title":"PLoS Comput Biol"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1007\/11840817_86","article-title":"Reinforcement Learning with Echo State Networks","author":"I Szita","year":"2006"},{"issue":"2","key":"ref28","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1016\/0014-4886(72)90030-1","article-title":"Limbic lesions and the problem of stimulus\u2014reinforcement associations","volume":"36","author":"B Jones","year":"1972","journal-title":"Exp Neurol"},{"issue":"8","key":"ref29","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1038\/nn.3440","article-title":"Prefrontal mechanisms of behavioral flexibility, emotion regulation and value updating","volume":"16","author":"PH Rudebeck","year":"2013","journal-title":"Nat Neurosci"},{"issue":"4","key":"ref30","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1002\/cne.903630409","article-title":"Sensory and premotor connections of the orbital and medial prefrontal cortex of macaque monkeys","volume":"363","author":"ST Carmichael","year":"1995","journal-title":"The Journal of comparative neurology"},{"issue":"4","key":"ref31","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1002\/cne.903630408","article-title":"Limbic connections of the orbital and medial prefrontal cortex in macaque monkeys","volume":"363","author":"ST Carmichael","year":"1995","journal-title":"The Journal of comparative neurology"},{"issue":"9","key":"ref32","doi-asserted-by":"crossref","first-page":"5999","DOI":"10.1523\/JNEUROSCI.15-09-05999.1995","article-title":"Highly restricted origin of prefrontal cortical inputs to striosomes in the macaque monkey","volume":"15","author":"F Eblen","year":"1995","journal-title":"J Neurosci"},{"issue":"5","key":"ref33","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1038\/nn.3068","article-title":"Mapping value based planning and extensively trained choice in the human brain","volume":"15","author":"K Wunderlich","year":"2012","journal-title":"Nat Neurosci"},{"issue":"3","key":"ref34","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"},{"issue":"4","key":"ref35","doi-asserted-by":"crossref","first-page":"914","DOI":"10.1016\/j.neuron.2013.08.009","article-title":"Disruption of dorsolateral prefrontal cortex decreases model-based in favor of model-free control in humans","volume":"80","author":"P Smittenaar","year":"2013","journal-title":"Neuron"},{"issue":"12","key":"ref36","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"},{"issue":"12","key":"ref37","doi-asserted-by":"crossref","first-page":"e1004648","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"},{"issue":"5","key":"ref38","doi-asserted-by":"crossref","first-page":"1322","DOI":"10.1016\/j.neuron.2013.09.013","article-title":"Neuronal origins of choice variability in economic decisions","volume":"80","author":"C Padoa-Schioppa","year":"2013","journal-title":"Neuron"},{"issue":"5","key":"ref39","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1016\/j.neuron.2014.01.008","article-title":"Contributions of orbitofrontal and lateral prefrontal cortices to economic choice and the good-to-action transformation","volume":"81","author":"X Cai","year":"2014","journal-title":"Neuron"},{"issue":"3","key":"ref40","doi-asserted-by":"crossref","first-page":"1382","DOI":"10.1152\/jn.00184.2015","article-title":"A neuro-computational model of economic decisions","volume":"114","author":"A Rustichini","year":"2015","journal-title":"J Neurophysiol"},{"issue":"4","key":"ref41","doi-asserted-by":"crossref","first-page":"847","DOI":"10.1016\/j.neuron.2015.01.006","article-title":"Spatial patterns of persistent neural activity vary with the behavioral context of short-term memory","volume":"85","author":"K Daie","year":"2015","journal-title":"Neuron"},{"key":"ref42","first-page":"235","volume":"xii","author":"JAK Suykens","year":"1996"},{"issue":"9","key":"ref43","doi-asserted-by":"crossref","first-page":"2093","DOI":"10.1162\/089976601750399326","article-title":"Simple recurrent networks learn context-free and context-sensitive languages by counting","volume":"13","author":"P Rodriguez","year":"2001","journal-title":"Neural Comput"},{"issue":"9","key":"ref44","doi-asserted-by":"crossref","first-page":"3844","DOI":"10.1523\/JNEUROSCI.2753-12.2013","article-title":"The sparseness of mixed selectivity neurons controls the generalization-discrimination trade-off","volume":"33","author":"O Barak","year":"2013","journal-title":"J Neurosci"},{"issue":"7451","key":"ref45","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1038\/nature12160","article-title":"The importance of mixed selectivity in complex cognitive tasks","volume":"497","author":"M Rigotti","year":"2013","journal-title":"Nature"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"24","DOI":"10.3389\/fncom.2010.00024","article-title":"Internal representation of task rules by recurrent dynamics: the importance of the diversity of neural responses","volume":"4","author":"M Rigotti","year":"2010","journal-title":"Front Comput Neurosci"},{"issue":"4","key":"ref47","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1016\/j.neuron.2009.07.018","article-title":"Generating coherent patterns of activity from chaotic neural networks","volume":"63","author":"D Sussillo","year":"2009","journal-title":"Neuron"},{"issue":"5","key":"ref48","doi-asserted-by":"crossref","first-page":"1970","DOI":"10.1152\/jn.1996.75.5.1970","article-title":"Orbitofrontal cortex neurons: role in olfactory and visual association learning","volume":"75","author":"ET Rolls","year":"1996","journal-title":"J Neurophysiol"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1196\/annals.1401.001","article-title":"Reconciling the roles of orbitofrontal cortex in reversal learning and the encoding of outcome expectancies","volume":"1121","author":"G Schoenbaum","year":"2007","journal-title":"Ann N Y Acad Sci"},{"key":"ref50","article-title":"Reward-based training of recurrent neural networks for cognitive and value-based tasks","volume":"6","author":"HF Song","year":"2017","journal-title":"Elife"},{"issue":"1","key":"ref51","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/BF00235545","article-title":"The orbitofrontal cortex: neuronal activity in the behaving monkey","volume":"49","author":"SJ Thorpe","year":"1983","journal-title":"Exp Brain Res"},{"issue":"6","key":"ref52","doi-asserted-by":"crossref","first-page":"927","DOI":"10.1016\/j.neuron.2010.02.027","article-title":"Separable learning systems in the macaque brain and the role of orbitofrontal cortex in contingent learning","volume":"65","author":"ME Walton","year":"2010","journal-title":"Neuron"},{"issue":"7","key":"ref53","doi-asserted-by":"crossref","first-page":"2700","DOI":"10.1523\/JNEUROSCI.5499-10.2011","article-title":"Ventral striatum and orbitofrontal cortex are both required for model-based, but not model-free, reinforcement learning","volume":"31","author":"MA McDannald","year":"2011","journal-title":"J Neurosci"},{"key":"ref54","article-title":"Hebbian Learning in a Random Network Captures Selectivity Properties of Prefrontal Cortex","author":"GW Lindsay","year":"2017","journal-title":"J Neurosci"},{"key":"ref55","first-page":"1412","article-title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","author":"J Chung","year":"2014","journal-title":"ArXiv e-prints"},{"issue":"46","key":"ref56","doi-asserted-by":"crossref","first-page":"16402","DOI":"10.1523\/JNEUROSCI.0776-12.2012","article-title":"Reward stability determines the contribution of orbitofrontal cortex to adaptive behavior","volume":"32","author":"JS Riceberg","year":"2012","journal-title":"J Neurosci"},{"issue":"5","key":"ref57","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1038\/nn.2304","article-title":"Reinforcement learning can account for associative and perceptual learning on a visual-decision task","volume":"12","author":"CT Law","year":"2009","journal-title":"Nature neuroscience"},{"issue":"6","key":"ref58","doi-asserted-by":"crossref","first-page":"1063","DOI":"10.1016\/S0896-6273(03)00761-X","article-title":"Learning in spiking neural networks by reinforcement of stochastic synaptic transmission","volume":"40","author":"HS Seung","year":"2003","journal-title":"Neuron"},{"issue":"6931","key":"ref59","doi-asserted-by":"crossref","first-page":"518","DOI":"10.1038\/nature01530","article-title":"Conservation of total synaptic weight through balanced synaptic depression and potentiation","volume":"422","author":"S Royer","year":"2003","journal-title":"Nature"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1005925","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2018,1,17]],"date-time":"2018-01-17T00:00:00Z","timestamp":1516147200000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1005925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,8]],"date-time":"2019-10-08T21:23:19Z","timestamp":1570569799000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1005925"}},"subtitle":[],"editor":[{"given":"Samuel J.","family":"Gershman","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2018,1,4]]},"references-count":59,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2018,1,4]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1005925","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/116608","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,1,4]]}}}