{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T06:37:50Z","timestamp":1793860670171,"version":"4.6.1"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2018,5,14]],"date-time":"2018-05-14T00:00:00Z","timestamp":1526256000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Neurosci"],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.1038\/s41593-018-0147-8","type":"journal-article","created":{"date-parts":[[2018,5,11]],"date-time":"2018-05-11T08:40:12Z","timestamp":1526028012000},"page":"860-868","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":579,"title":["Prefrontal cortex as a meta-reinforcement learning system"],"prefix":"10.1038","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1339-5040","authenticated-orcid":false,"given":"Jane X.","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeb","family":"Kurth-Nelson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dharshan","family":"Kumaran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhruva","family":"Tirumala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hubert","family":"Soyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joel Z.","family":"Leibo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Demis","family":"Hassabis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7758-6896","authenticated-orcid":false,"given":"Matthew","family":"Botvinick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,5,14]]},"reference":[{"key":"147_CR1","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R. S. & Barto, A. G. Reinforcement Learning: An Introduction (MIT Press, Cambridge, MA, USA, 1998)."},{"key":"147_CR2","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1523\/JNEUROSCI.16-05-01936.1996","volume":"16","author":"PR Montague","year":"1996","unstructured":"Montague, P. R., Dayan, P. & Sejnowski, T. J. A framework for mesencephalic dopamine systems based on predictive Hebbian learning. J. Neurosci. 16, 1936\u20131947 (1996).","journal-title":"J. Neurosci."},{"key":"147_CR3","unstructured":"Daw, N. D. & Tobler, P. N. Value learning through reinforcement: the basics of dopamine and reinforcement learning. Neuroeconomics: Decision Making and the Brain 2nd edn. (eds. Glimcher, P. W. & Fehr, E) 283\u2013298 (Academic, New York, 2014)."},{"key":"147_CR4","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1038\/nn2066","volume":"11","author":"MF Rushworth","year":"2008","unstructured":"Rushworth, M. F. & Behrens, T. E. Choice, uncertainty and value in prefrontal and cingulate cortex. Nat. Neurosci. 11, 389\u2013397 (2008).","journal-title":"Nat. Neurosci."},{"key":"147_CR5","doi-asserted-by":"publisher","first-page":"3845","DOI":"10.1098\/rstb.2008.0158","volume":"363","author":"H Seo","year":"2008","unstructured":"Seo, H. & Lee, D. Cortical mechanisms for reinforcement learning in competitive games. Phil. Trans. R. Soc. Lond. B 363, 3845\u20133857 (2008).","journal-title":"Phil. Trans. R. Soc. Lond. B"},{"key":"147_CR6","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1038\/nature04676","volume":"441","author":"C Padoa-Schioppa","year":"2006","unstructured":"Padoa-Schioppa, C. & Assad, J. A. Neurons in the orbitofrontal cortex encode economic value. Nature 441, 223\u2013226 (2006).","journal-title":"Nature"},{"key":"147_CR7","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms12554","volume":"7","author":"K Tsutsui","year":"2016","unstructured":"Tsutsui, K., Grabenhorst, F., Kobayashi, S. & Schultz, W. A dynamic code for economic object valuation in prefrontal cortex neurons. Nat. Commun. 7, 12554 (2016).","journal-title":"Nat. Commun."},{"key":"147_CR8","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1038\/5739","volume":"2","author":"JN Kim","year":"1999","unstructured":"Kim, J.-N. & Shadlen, M. N. Neural correlates of a decision in the dorsolateral prefrontal cortex of the macaque. Nat. Neurosci. 2, 176\u2013185 (1999).","journal-title":"Nat. Neurosci."},{"key":"147_CR9","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1016\/j.neuron.2012.03.037","volume":"74","author":"M Seo","year":"2012","unstructured":"Seo, M., Lee, E. & Averbeck, B. B. Action selection and action value in frontal-striatal circuits. Neuron 74, 947\u2013960 (2012).","journal-title":"Neuron"},{"key":"147_CR10","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1038\/nn1209","volume":"7","author":"DJ Barraclough","year":"2004","unstructured":"Barraclough, D. J., Conroy, M. L. & Lee, D. Prefrontal cortex and decision making in a mixed-strategy game. Nat. Neurosci. 7, 404\u2013410 (2004).","journal-title":"Nat. Neurosci."},{"key":"147_CR11","doi-asserted-by":"publisher","first-page":"1704","DOI":"10.1038\/nn1560","volume":"8","author":"ND Daw","year":"2005","unstructured":"Daw, N. D., Niv, Y. & Dayan, P. Uncertainty-based competition between prefrontal and dorsolateral striatal systems for behavioral control. Nat. Neurosci. 8, 1704\u20131711 (2005).","journal-title":"Nat. Neurosci."},{"key":"147_CR12","doi-asserted-by":"publisher","first-page":"1068","DOI":"10.1152\/jn.00158.2010","volume":"104","author":"ES Bromberg-Martin","year":"2010","unstructured":"Bromberg-Martin, E. S., Matsumoto, M., Hong, S. & Hikosaka, O. A pallidus-habenula-dopamine pathway signals inferred stimulus values. J. Neurophysiol. 104, 1068\u20131076 (2010).","journal-title":"J. Neurophysiol."},{"key":"147_CR13","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.neures.2012.09.007","volume":"74","author":"H Nakahara","year":"2012","unstructured":"Nakahara, H. & Hikosaka, O. Learning to represent reward structure: a key to adapting to complex environments. Neurosci. Res. 74, 177\u2013183 (2012).","journal-title":"Neurosci. Res."},{"key":"147_CR14","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.13665","volume":"5","author":"BF Sadacca","year":"2016","unstructured":"Sadacca, B. F., Jones, J. L. & Schoenbaum, G. Midbrain dopamine neurons compute inferred and cached value prediction errors in a common framework. Elife 5, e13665 (2016).","journal-title":"Elife"},{"key":"147_CR15","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.1016\/j.neuron.2011.02.027","volume":"69","author":"ND Daw","year":"2011","unstructured":"Daw, N. D., Gershman, S. J., Seymour, B., Dayan, P. & Dolan, R. J. Model-based influences on humans\u2019 choices and striatal prediction errors. Neuron 69, 1204\u20131215 (2011).","journal-title":"Neuron"},{"key":"147_CR16","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1038\/nature12742","volume":"503","author":"V Mante","year":"2013","unstructured":"Mante, V., Sussillo, D., Shenoy, K. V. & Newsome, W. T. Context-dependent computation by recurrent dynamics in prefrontal cortex. Nature 503, 78\u201384 (2013).","journal-title":"Nature"},{"key":"147_CR17","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1162\/089976606775093909","volume":"18","author":"RC O\u2019Reilly","year":"2006","unstructured":"O\u2019Reilly, R. C. & Frank, M. J. Making working memory work: a computational model of learning in the prefrontal cortex and basal ganglia. Neural Comput. 18, 283\u2013328 (2006).","journal-title":"Neural Comput."},{"key":"147_CR18","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.21492","volume":"6","author":"HF Song","year":"2017","unstructured":"Song, H. F., Yang, G. R. & Wang, X.-J. Reward-based training of recurrent neural networks for cognitive and value-based tasks. Elife 6, e21492 (2017).","journal-title":"Elife"},{"key":"147_CR19","doi-asserted-by":"publisher","first-page":"784","DOI":"10.1037\/0033-295X.114.3.784","volume":"114","author":"AD Redish","year":"2007","unstructured":"Redish, A. D., Jensen, S., Johnson, A. & Kurth-Nelson, Z. Reconciling reinforcement learning models with behavioral extinction and renewal: implications for addiction, relapse, and problem gambling. Psychol. Rev. 114, 784\u2013805 (2007).","journal-title":"Psychol. Rev."},{"key":"147_CR20","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1016\/j.neuroscience.2014.10.008","volume":"282","author":"SN Haber","year":"2014","unstructured":"Haber, S. N. The place of dopamine in the cortico-basal ganglia circuit. Neuroscience 282, 248\u2013257 (2014).","journal-title":"Neuroscience"},{"key":"147_CR21","doi-asserted-by":"publisher","first-page":"1940","DOI":"10.1126\/science.1102941","volume":"306","author":"MJ Frank","year":"2004","unstructured":"Frank, M. J., Seeberger, L. C. & O\u2019Reilly, R. C. By carrot or by stick: cognitive reinforcement learning in parkinsonism. Science 306, 1940\u20131943 (2004).","journal-title":"Science"},{"key":"147_CR22","doi-asserted-by":"crossref","unstructured":"Houk, J. C., Adams, C. M. & Barto, A. G. A model of how the basal ganglia generate and use neural signals that predict reinforcement. in Models of Information Processing in the Basal Ganglia (eds. Houk, J.C. & Davis, D.G.) 249\u2013270 (MIT Press, Cambridge, MA, USA, 1995).","DOI":"10.7551\/mitpress\/4708.003.0020"},{"key":"147_CR23","doi-asserted-by":"publisher","first-page":"7338","DOI":"10.1073\/pnas.0502455102","volume":"102","author":"NP Rougier","year":"2005","unstructured":"Rougier, N. P., Noelle, D. C., Braver, T. S., Cohen, J. D. & O\u2019Reilly, R. C. Prefrontal cortex and flexible cognitive control: rules without symbols. Proc. Natl. Acad. Sci. USA 102, 7338\u20137343 (2005).","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"147_CR24","doi-asserted-by":"publisher","first-page":"e1001003","DOI":"10.1371\/journal.pcbi.1001003","volume":"6","author":"DE Acuna","year":"2010","unstructured":"Acuna, D. E. & Schrater, P. Structure learning in human sequential decision-making. PLoS Comput. Biol. 6, e1001003 (2010).","journal-title":"PLoS Comput. Biol."},{"key":"147_CR25","doi-asserted-by":"publisher","first-page":"1024","DOI":"10.1111\/j.1460-9568.2011.07980.x","volume":"35","author":"AG Collins","year":"2012","unstructured":"Collins, A. G. & Frank, M. J. How much of reinforcement learning is working memory, not reinforcement learning? A behavioral, computational, and neurogenetic analysis. Eur. J. Neurosci. 35, 1024\u20131035 (2012).","journal-title":"Eur. J. Neurosci."},{"key":"147_CR26","volume-title":"Learning to Learn","author":"S Thrun","year":"2012","unstructured":"Thrun, S. & Pratt, L. Learning to Learn (Springer Science & Business Media, New York, 2012)."},{"key":"147_CR27","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1016\/B978-0-444-62604-2.00022-8","volume":"202","author":"M Khamassi","year":"2013","unstructured":"Khamassi, M., Enel, P., Dominey, P. F. & Procyk, E. Medial prefrontal cortex and the adaptive regulation of reinforcement learning parameters. Prog. Brain Res. 202, 441\u2013464 (2013).","journal-title":"Prog. Brain Res."},{"key":"147_CR28","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1016\/S0893-6080(02)00056-4","volume":"15","author":"S Ishii","year":"2002","unstructured":"Ishii, S., Yoshida, W. & Yoshimoto, J. Control of exploitation-exploration meta-parameter in reinforcement learning. Neural Netw. 15, 665\u2013687 (2002).","journal-title":"Neural Netw."},{"key":"147_CR29","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/S0893-6080(02)00228-9","volume":"16","author":"N Schweighofer","year":"2003","unstructured":"Schweighofer, N. & Doya, K. Meta-learning in reinforcement learning. Neural Netw. 16, 5\u20139 (2003).","journal-title":"Neural Netw."},{"key":"147_CR30","unstructured":"Schmidhuber, J., Zhao, J. & Wiering, M. Simple principles of metalearning. IDSIA (Istituto Dalle Molle Di Studi Sull Intelligenza Artificiale) Technical Report 69-96, 1\u201323 (1996)."},{"key":"147_CR31","unstructured":"Wang, J.X. et al. Learning to reinforcement learn. Preprint at https:\/\/arxiv.org\/abs\/1611.05763 (2016)."},{"key":"147_CR32","unstructured":"Duan, Y. et al. RL2: fast reinforcement learning via slow reinforcement learning. Preprint at https:\/\/arxiv.org\/abs\/1611.02779 (2016)."},{"key":"147_CR33","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1901\/jeab.2005.110-04","volume":"84","author":"B Lau","year":"2005","unstructured":"Lau, B. & Glimcher, P. W. Dynamic response-by-response models of matching behavior in rhesus monkeys. J. Exp. Anal. Behav. 84, 555\u2013579 (2005).","journal-title":"J. Exp. Anal. Behav."},{"key":"147_CR34","doi-asserted-by":"publisher","first-page":"1214","DOI":"10.1038\/nn1954","volume":"10","author":"TEJ Behrens","year":"2007","unstructured":"Behrens, T. E. J., Woolrich, M. W., Walton, M. E. & Rushworth, M. F. S. Learning the value of information in an uncertain world. Nat. Neurosci. 10, 1214\u20131221 (2007).","journal-title":"Nat. Neurosci."},{"key":"147_CR35","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.18073","volume":"5","author":"K Iigaya","year":"2016","unstructured":"Iigaya, K. Adaptive learning and decision-making under uncertainty by metaplastic synapses guided by a surprise detection system. Elife 5, e18073 (2016).","journal-title":"Elife"},{"key":"147_CR36","doi-asserted-by":"publisher","first-page":"1402","DOI":"10.1016\/j.neuron.2016.08.019","volume":"91","author":"NW Schuck","year":"2016","unstructured":"Schuck, N. W., Cai, M. B., Wilson, R. C. & Niv, Y. Human orbitofrontal cortex represents a cognitive map of state space. Neuron 91, 1402\u20131412 (2016).","journal-title":"Neuron"},{"key":"147_CR37","doi-asserted-by":"publisher","first-page":"7817","DOI":"10.1523\/JNEUROSCI.0659-16.2016","volume":"36","author":"SC Chan","year":"2016","unstructured":"Chan, S. C., Niv, Y. & Norman, K. A. A probability distribution over latent causes, in the orbitofrontal cortex. J. Neurosci. 36, 7817\u20137828 (2016).","journal-title":"J. Neurosci."},{"key":"147_CR38","doi-asserted-by":"publisher","first-page":"8360","DOI":"10.1523\/JNEUROSCI.1010-06.2006","volume":"26","author":"AN Hampton","year":"2006","unstructured":"Hampton, A. N., Bossaerts, P. & O\u2019Doherty, J. P. The role of the ventromedial prefrontal cortex in abstract state-based inference during decision making in humans. J. Neurosci. 26, 8360\u20138367 (2006).","journal-title":"J. Neurosci."},{"key":"147_CR39","doi-asserted-by":"publisher","first-page":"1269","DOI":"10.1038\/nn.4613","volume":"20","author":"KJ Miller","year":"2017","unstructured":"Miller, K. J., Botvinick, M. M. & Brody, C. D. Dorsal hippocampus contributes to model-based planning. Nat. Neurosci. 20, 1269\u20131276 (2017).","journal-title":"Nat. Neurosci."},{"key":"147_CR40","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1037\/h0062474","volume":"56","author":"HF Harlow","year":"1949","unstructured":"Harlow, H. F. The formation of learning sets. Psychol. Rev. 56, 51\u201365 (1949).","journal-title":"Psychol. Rev."},{"key":"147_CR41","unstructured":"Trujillo-Pisanty, I., Solis, P., Conover, K., Dayan, P. & Shizgal, P. On the forms of learning supported by rewarding optical stimulation of dopamine neurons. Soc. Neurosci. Annu. Meet. 66.06, http:\/\/www.abstractsonline.com\/pp8\/#!\/4071\/presentation\/29633 (2016)."},{"key":"147_CR42","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0033612","volume":"7","author":"KM Kim","year":"2012","unstructured":"Kim, K. M. et al. Optogenetic mimicry of the transient activation of dopamine neurons by natural reward is sufficient for operant reinforcement. PLoS One 7, e33612 (2012).","journal-title":"PLoS One"},{"key":"147_CR43","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1038\/nn.4191","volume":"19","author":"CY Chang","year":"2016","unstructured":"Chang, C. Y. et al. Brief optogenetic inhibition of dopamine neurons mimics endogenous negative reward prediction errors. Nat. Neurosci. 19, 111\u2013116 (2016).","journal-title":"Nat. Neurosci."},{"key":"147_CR44","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.neuron.2014.08.033","volume":"84","author":"CM Stopper","year":"2014","unstructured":"Stopper, C. M., Tse, M. T. L., Montes, D. R., Wiedman, C. R. & Floresco, S. B. Overriding phasic dopamine signals redirects action selection during risk\/reward decision making. Neuron 84, 177\u2013189 (2014).","journal-title":"Neuron"},{"key":"147_CR45","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1016\/S0166-2236(00)01868-3","volume":"24","author":"XJ Wang","year":"2001","unstructured":"Wang, X.-J. Synaptic reverberation underlying mnemonic persistent activity. Trends Neurosci. 24, 455\u2013463 (2001).","journal-title":"Trends Neurosci."},{"key":"147_CR46","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.cobeha.2014.08.001","volume":"1","author":"CH Chatham","year":"2015","unstructured":"Chatham, C. H. & Badre, D. Multiple gates on working memory. Curr. Opin. Behav. Sci. 1, 23\u201331 (2015).","journal-title":"Curr. Opin. Behav. Sci."},{"key":"147_CR47","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1523\/JNEUROSCI.2422-12.2013","volume":"33","author":"H Kim","year":"2013","unstructured":"Kim, H., Lee, D. & Jung, M. W. Signals for previous goal choice persist in the dorsomedial, but not dorsolateral striatum of rats. J. Neurosci. 33, 52\u201363 (2013).","journal-title":"J. Neurosci."},{"key":"147_CR48","doi-asserted-by":"publisher","first-page":"1590","DOI":"10.1038\/nn.2957","volume":"14","author":"YK Takahashi","year":"2011","unstructured":"Takahashi, Y. K. et al. Expectancy-related changes in firing of dopamine neurons depend on orbitofrontal cortex. Nat. Neurosci. 14, 1590\u20131597 (2011).","journal-title":"Nat. Neurosci."},{"key":"147_CR49","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/j.cognition.2016.04.002","volume":"152","author":"AGE Collins","year":"2016","unstructured":"Collins, A. G. E. & Frank, M. J. Neural signature of hierarchically structured expectations predicts clustering and transfer of rule sets in reinforcement learning. Cognition 152, 160\u2013169 (2016).","journal-title":"Cognition"},{"key":"147_CR50","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1146\/annurev-psych-122414-033625","volume":"68","author":"SJ Gershman","year":"2017","unstructured":"Gershman, S. J. & Daw, N. D. Reinforcement learning and episodic memory in humans and animals: An integrative framework. Annu. Rev. Psychol. 68, 101\u2013128 (2017).","journal-title":"Annu. Rev. Psychol."},{"key":"147_CR51","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997).","journal-title":"Neural Comput."},{"key":"147_CR52","unstructured":"Mnih, V. et al. Asynchronous methods for deep reinforcement learning. in Proc. 33rd Intl. Conf. Machine Learning 48, 1928\u20131937 (JMLR, New York, 2016)."},{"key":"147_CR53","doi-asserted-by":"crossref","unstructured":"Graves, A., Jaitly, N. & Mohamed, A.-r. Hybrid speech recognition with deep bidirectional LSTM. in IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) 2013 273\u2013278 (IEEE, 2013).","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"147_CR55","unstructured":"Leibo, J. Z. et al. Psychlab: a psychology laboratory for deep reinforcement learning agents. Preprint at https:\/\/arxiv.org\/abs\/1801.08116 (2018)."},{"key":"147_CR54","doi-asserted-by":"crossref","unstructured":"Deng, J. et al. ImageNet: a large-scale hierarchical image database. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 248\u2013255 (IEEE, 2009).","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["Nature Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.nature.com\/articles\/s41593-018-0147-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/www.nature.com\/articles\/s41593-018-0147-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/www.nature.com\/articles\/s41593-018-0147-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T14:13:07Z","timestamp":1720275187000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41593-018-0147-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,14]]},"references-count":55,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2018,6]]}},"alternative-id":["147"],"URL":"https:\/\/doi.org\/10.1038\/s41593-018-0147-8","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/295964","asserted-by":"object"}],"has-review":[{"id-type":"doi","id":"10.3410\/f.733230343.793547713","asserted-by":"object"}]},"ISSN":["1097-6256","1546-1726"],"issn-type":[{"value":"1097-6256","type":"print"},{"value":"1546-1726","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,5,14]]},"assertion":[{"value":"13 December 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 April 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 May 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors are employed by DeepMind Technologies Limited.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}