{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T05:09:41Z","timestamp":1772082581973,"version":"3.50.1"},"reference-count":42,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2011,6,30]],"date-time":"2011-06-30T00:00:00Z","timestamp":1309392000000},"content-version":"unspecified","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.1002092","type":"journal-article","created":{"date-parts":[[2011,6,30]],"date-time":"2011-06-30T20:38:10Z","timestamp":1309466290000},"page":"e1002092","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":51,"title":["Spatio-Temporal Credit Assignment in Neuronal Population Learning"],"prefix":"10.1371","volume":"7","author":[{"given":"Johannes","family":"Friedrich","sequence":"first","affiliation":[]},{"given":"Robert","family":"Urbanczik","sequence":"additional","affiliation":[]},{"given":"Walter","family":"Senn","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2011,6,30]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1109\/TNN.1998.712192","article-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1126\/science.275.5297.213","article-title":"Regulation of synaptic efficacy by coincidence of postsynaptic APs and EPSPs.","volume":"275","author":"H Markram","year":"1997","journal-title":"Science"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"10464","DOI":"10.1523\/JNEUROSCI.18-24-10464.1998","article-title":"Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type.","volume":"18","author":"G Bi","year":"1998","journal-title":"J Neurosci"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1016\/S0896-6273(01)00451-2","article-title":"Cortical development and remapping through spike timing-dependent plasticity.","volume":"32","author":"S Song","year":"2001","journal-title":"Neuron"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"2245","DOI":"10.1162\/neco.2007.19.8.2245","article-title":"Reinforcement learning, spike-time-dependent plasticity, and the BCM rule.","volume":"19","author":"D Baras","year":"2007","journal-title":"Neural Comput"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1468","DOI":"10.1162\/neco.2007.19.6.1468","article-title":"Reinforcement learning through modulation of spike-timing-dependent synaptic plasticity.","volume":"19","author":"R Florian","year":"2007","journal-title":"Neural Comput"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"2443","DOI":"10.1093\/cercor\/bhl152","article-title":"Solving the distal reward problem through linkage of STDP and dopamine signaling.","volume":"17","author":"E Izhikevich","year":"2007","journal-title":"Cereb Cortex"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1162\/0899766054796888","article-title":"What can a neuron learn with spike-timing-dependent plasticity?","volume":"17","author":"R Legenstein","year":"2005","journal-title":"Neural Comput"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"2435","DOI":"10.1523\/JNEUROSCI.4402-07.2008","article-title":"Dopamine receptor activation is required for corticostriatal spiketiming-dependent plasticity.","volume":"28","author":"V Pawlak","year":"2008","journal-title":"J Neurosci"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"13028","DOI":"10.1073\/pnas.0900546106","article-title":"Gain in sensitivity and loss in temporal contrast of STDP by dopaminergic modulation of hippocampal synapses.","volume":"106","author":"J Zhang","year":"2009","journal-title":"Proc Natl Acad Sci USA"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"6826","DOI":"10.1073\/pnas.0901835106","article-title":"Learning reward timing in cortex through reward dependent expression of synaptic plasticity.","volume":"106","author":"JP Gavornik","year":"2009","journal-title":"Proc Natl Acad Sci USA"},{"key":"ref12","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":"ref13","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/j.conb.2008.08.003","article-title":"Reinforcement learning: the good, the bad and the ugly.","volume":"18","author":"P Dayan","year":"2008","journal-title":"Curr Opin Neurobiol"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"1318","DOI":"10.1162\/neco.2006.18.6.1318","article-title":"Optimal spike-timing-dependent plasticity for precise action potential firing in supervised learning.","volume":"18","author":"J Pfister","year":"2006","journal-title":"Neural Comput"},{"key":"ref15","first-page":"385","article-title":"Temporal difference based actor critic learning \u2013 convergence and neural implementation.","author":"D Castro","year":"2009"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1038\/nn.2264","article-title":"Reinforcement learning in populations of spiking neurons.","volume":"12","author":"R Urbanczik","year":"2009","journal-title":"Nat Neurosci"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"e1000586","DOI":"10.1371\/journal.pcbi.1000586","article-title":"Spike-based reinforcement learning in continuous state and action space: when policy gradient methods fail.","volume":"5","author":"E Vasilaki","year":"2009","journal-title":"PLoS Comput Biol"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1038\/nn.2479","article-title":"Connectivity reflects coding: a model of voltage-based STDP with homeostasis.","volume":"13","author":"C Clopath","year":"2010","journal-title":"Nat Neurosci"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1016\/S0896-6273(02)01092-9","article-title":"Probabilistic decision making by slow reverberation in cortical circuits.","volume":"36","author":"X Wang","year":"2002","journal-title":"Neuron"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1037\/h0087299","article-title":"Neuromodulation, development and synaptic plasticity.","volume":"53","author":"R Foehring","year":"1999","journal-title":"Can J Exp Psychol"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"4803","DOI":"10.1523\/JNEUROSCI.5312-05.2006","article-title":"The presence of background dopamine signal converts longterm synaptic depression to potentiation in rat prefrontal cortex.","volume":"26","author":"Y Matsuda","year":"2006","journal-title":"J Neurosci"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1016\/j.neuron.2007.08.013","article-title":"Neuromodulators control the polarity of spike-timing-dependent synaptic plasticity.","volume":"55","author":"G Seol","year":"2007","journal-title":"Neuron"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.conb.2006.03.006","article-title":"The computational neurobiology of learning and reward.","volume":"16","author":"ND Daw","year":"2006","journal-title":"Curr Opin Neurobiol"},{"key":"ref24","article-title":"Learning and Behavior","author":"J Mazur","year":"2002"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1901\/jeab.1999.71-75","article-title":"Optimality And Concurrent Variable-interval Variable-ratio Schedules.","volume":"71","author":"W Baum","year":"1999","journal-title":"J Exp Anal Behav"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1038\/78829","article-title":"Competitive Hebbian learning through spike-timing dependent synaptic plasticity.","volume":"3","author":"S Song","year":"2000","journal-title":"Nat Neurosci"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1152\/physrev.00014.2003","article-title":"Long-term potentiation and memory.","volume":"84","author":"MA Lynch","year":"2004","journal-title":"Physiol Rev"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"11001","DOI":"10.1523\/JNEUROSCI.1749-06.2006","article-title":"Spine Ca<sup>2+<\/sup> signaling in spike-timing-dependent plasticity.","volume":"26","author":"T Nevian","year":"2006","journal-title":"J Neurosci"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1038\/nrn2356","article-title":"Metaplasticity: tuning synapses and networks for plasticity.","volume":"9","author":"W Abraham","year":"2008","journal-title":"Nat Neurosci"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1038\/nrn1722","article-title":"Astrocytes, from brain glue to communication elements: the revolution continues.","volume":"6","author":"A Volterra","year":"2005","journal-title":"Nat Rev Neurosci"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1038\/nature08673","article-title":"Long-term potentiation depends on release of D-serine from astrocytes.","volume":"463","author":"C Henneberger","year":"2010","journal-title":"Nature"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/S0079-6123(07)00007-6","article-title":"\u2018Synaptic tagging\u2019 and \u2018cross-tagging\u2019 and related associative reinforcement processes of functional plasticity as the cellular basis for memory formation.","volume":"169","author":"S Frey","year":"2008","journal-title":"Prog Brain Res"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"1546","DOI":"10.1016\/j.neuroscience.2009.11.068","article-title":"Differential effects of electrical stimulation patterns, motivational-behavioral stimuli and their order of application on functional plasticity processes within one input in the dentate gyrus of freely moving rats in vivo.","volume":"165","author":"W Almaguer-Melian","year":"2010","journal-title":"Neuroscience"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"1698","DOI":"10.1162\/neco.2010.05-09-1010","article-title":"Learning spike-based population codes by reward and population feedback.","volume":"22","author":"J Friedrich","year":"2010","journal-title":"Neural Comput"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning.","volume":"8","author":"R Williams","year":"1992","journal-title":"Mach Learn"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","article-title":"Infinite-horizon policy-gradient estimation.","volume":"15","author":"J Baxter","year":"2001","journal-title":"J Artif Intell Res"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1613\/jair.807","article-title":"Experiments with infinite-horizon, policy-gradient estimation.","volume":"15","author":"J Baxter","year":"2001","journal-title":"J Artif Intell Res"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"e1000180","DOI":"10.1371\/journal.pcbi.1000180","article-title":"A learning theory for reward-modulated spike-timingdependent plasticity with application to biofeedback.","volume":"4","author":"R Legenstein","year":"2008","journal-title":"PLoS Comput Biol"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1152\/jn.1973.36.2.179","article-title":"Operantly conditioned patterns on precentral unit activity and correlated responses in adjacent cells and contralateral muscles.","volume":"36","author":"EE Fetz","year":"1973","journal-title":"J Neurophysiol"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1038\/35039062","article-title":"Information processing with population codes.","volume":"1","author":"A Pouget","year":"2000","journal-title":"Nat Rev Neurosci"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1038\/nrn1888","article-title":"Neural correlations, population coding and computation.","volume":"7","author":"B Averbeck","year":"2006","journal-title":"Nat Rev Neurosci"},{"key":"ref42","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation.","author":"R Sutton","year":"2002"}],"container-title":["PLoS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1002092","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,12]],"date-time":"2019-06-12T15:51:21Z","timestamp":1560354681000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1002092"}},"subtitle":[],"editor":[{"given":"Boris S.","family":"Gutkin","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2011,6,30]]},"references-count":42,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2011,6,30]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1002092","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,6,30]]}}}