{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T11:27:50Z","timestamp":1791890870649,"version":"4.3.4"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"7553","license":[{"start":{"date-parts":[[2015,5,27]],"date-time":"2015-05-27T00:00:00Z","timestamp":1432684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2015,5,27]],"date-time":"2015-05-27T00:00:00Z","timestamp":1432684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nature"],"published-print":{"date-parts":[[2015,5,28]]},"DOI":"10.1038\/nature14540","type":"journal-article","created":{"date-parts":[[2015,5,26]],"date-time":"2015-05-26T12:10:15Z","timestamp":1432642215000},"page":"445-451","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":306,"title":["Reinforcement learning improves behaviour from evaluative feedback"],"prefix":"10.1038","volume":"521","author":[{"given":"Michael L.","family":"Littman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,5,27]]},"reference":[{"key":"BFnature14540_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, 1998). This book is the definitive reference on computational reinforcement learning."},{"key":"BFnature14540_CR2","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L. P., Littman, M. L. & Moore, A. W. Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237\u2013285 (1996).","journal-title":"J. Artif. Intell. Res."},{"key":"BFnature14540_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-015-3711-7","volume-title":"Bandit Problems: Sequential Allocation of Experiments","author":"DA Berry","year":"1985","unstructured":"Berry, D. A. & Fristedt, B. Bandit Problems: Sequential Allocation of Experiments (Chapman and Hall, 1985)."},{"key":"BFnature14540_CR4","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1038\/nrclinonc.2013.244","volume":"11","author":"J Shrager","year":"2014","unstructured":"Shrager, J. & Tenenbaum, J. M. Rapid learning for precision oncology. Nature Rev. Clin. Onco. 11, 109\u2013118 (2014).","journal-title":"Nature Rev. Clin. Onco."},{"key":"BFnature14540_CR5","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1023\/A:1013689704352","volume":"47","author":"P Auer","year":"2002","unstructured":"Auer, P., Cesa-Bianchi, N. & Fischer, P. Finite-time analysis of the multi-armed bandit problem. Mach. Learn. 47, 235\u2013256 (2002).","journal-title":"Mach. Learn."},{"key":"BFnature14540_CR6","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/4168.001.0001","volume-title":"Learning in Embedded Systems","author":"LP Kaelbling","year":"1993","unstructured":"Kaelbling, L. P. Learning in Embedded Systems (MIT Press, 1993)."},{"key":"BFnature14540_CR7","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1145\/1772690.1772758","volume-title":"Proc. 19th International World Wide Web Conference","author":"L Li","year":"2010","unstructured":"Li, L., Chu, W., Langford, J. & Schapire, R. E. A contextual-bandit approach to personalized news article recommendation. In Proc. 19th International World Wide Web Conference 661\u2013670 (2010)."},{"key":"BFnature14540_CR8","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1093\/biomet\/25.3-4.285","volume":"25","author":"WR Thompson","year":"1933","unstructured":"Thompson, W. R. On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika 25, 285\u2013294 (1933).","journal-title":"Biometrika"},{"key":"BFnature14540_CR9","doi-asserted-by":"publisher","first-page":"243","DOI":"10.3758\/BF03194383","volume":"31","author":"RF West","year":"2003","unstructured":"West, R. F. & Stanovich, K. E. Is probability matching smart? Associations between probabilistic choices and cognitive ability. Mem. Cognit. 31, 243\u2013251 (2003).","journal-title":"Mem. Cognit."},{"key":"BFnature14540_CR10","first-page":"2069","volume":"13","author":"BC May","year":"2012","unstructured":"May, B. C., Korda, N., Lee, A. & Leslie, D. S. Optimistic Bayesian sampling in contextual-bandit problems. J. Mach. Learn. Res. 13, 2069\u20132106 (2012).","journal-title":"J. Mach. Learn. Res."},{"key":"BFnature14540_CR11","first-page":"638","volume-title":"Proc. Advances in Neural Information Processing Systems","author":"S Bubeck","year":"2013","unstructured":"Bubeck, S. & Liu, C.-Y. Prior-free and prior-dependent regret bounds for Thompson sampling. In Proc. Advances in Neural Information Processing Systems 638\u2013646 (2013)."},{"key":"BFnature14540_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jmp.2011.08.004","volume":"56","author":"S Gershman","year":"2012","unstructured":"Gershman, S. & Blei, D. A tutorial on Bayesian nonparametric models. J. Math. Psychol. 56, 1\u201312 (2012).","journal-title":"J. Math. Psychol."},{"key":"BFnature14540_CR13","first-page":"9","volume":"3","author":"RS Sutton","year":"1988","unstructured":"Sutton, R. S. Learning to predict by the method of temporal differences. Mach. Learn. 3, 9\u201344 (1988).","journal-title":"Mach. Learn."},{"key":"BFnature14540_CR14","first-page":"369","volume-title":"Proc. Advances in Neural Information Processing Systems","author":"JA Boyan","year":"1995","unstructured":"Boyan, J. A. & Moore, A. W. Generalization in reinforcement learning: safely approximating the value function. In Proc. Advances in Neural Information Processing Systems 369\u2013376 (1995)."},{"key":"BFnature14540_CR15","first-page":"30","volume-title":"Proc. 12th International Conference on Machine Learning","author":"L Baird","year":"1995","unstructured":"Baird, L. Residual algorithms: reinforcement learning with function approximation. In Proc. 12th International Conference on Machine Learning (eds Prieditis, A. & Russell, S.) 30\u201337 (Morgan Kaufmann, 1995)."},{"key":"BFnature14540_CR16","doi-asserted-by":"crossref","first-page":"993","DOI":"10.1145\/1553374.1553501","volume-title":"Proc. 26th Annual International Conference on Machine Learning","author":"RS Sutton","year":"2009","unstructured":"Sutton, R. S. et al. Fast gradient-descent methods for temporal-difference learning with linear function approximation. In Proc. 26th Annual International Conference on Machine Learning 993\u20131000 (2009)."},{"key":"BFnature14540_CR17","first-page":"1609","volume-title":"Proc. Advances in Neural Information Processing Systems","author":"RS Sutton","year":"2009","unstructured":"Sutton, R. S., Maei, H. R. & Szepesv\u00e1ri, C. A convergent O(n) temporal-difference algorithm for off-policy learning with linear function approximation. In Proc. Advances in Neural Information Processing Systems 1609\u20131616 (2009)."},{"key":"BFnature14540_CR18","first-page":"1204","volume-title":"Proc. Advances in Neural Information Processing Systems","author":"HR Maei","year":"2009","unstructured":"Maei, H. R. et al. Convergent temporal-difference learning with arbitrary smooth function approximation. In Proc. Advances in Neural Information Processing Systems 1204\u20131212 (2009)."},{"key":"BFnature14540_CR19","first-page":"719","volume-title":"Proc. 27th International Conference on Machine Learning","author":"HR Maei","year":"2010","unstructured":"Maei, H. R., Szepesv\u00e1ri, C., Bhatnagar, S. & Sutton, R. S. Toward off-policy learning control with function approximation. In Proc. 27th International Conference on Machine Learning 719\u2013726 (2010)."},{"key":"BFnature14540_CR20","first-page":"324","volume-title":"Proc. 30th Conference on Uncertainty in Artificial Intelligence","author":"H van Hasselt","year":"2014","unstructured":"van Hasselt, H., Mahmood, A. R. & Sutton, R. S. Off-policy TD(\u03bb) with a true online equivalence. In Proc. 30th Conference on Uncertainty in Artificial Intelligence 324 (2014)."},{"key":"BFnature14540_CR21","volume-title":"Artificial Intelligence: A Modern Approach","author":"SJ Russell","year":"1994","unstructured":"Russell, S. J. & Norvig, P. Artificial Intelligence: A Modern Approach (Prentice\u2013Hall, 1994)."},{"key":"BFnature14540_CR22","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/S0004-3702(01)00129-1","volume":"134","author":"M Campbell","year":"2002","unstructured":"Campbell, M., Hoane, A. J. & Hsu, F. H. Deep blue. Artif. Intell. 134, 57\u201383 (2002).","journal-title":"Artif. Intell."},{"key":"BFnature14540_CR23","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1147\/rd.33.0210","volume":"3","author":"AL Samuel","year":"1959","unstructured":"Samuel, A. L. Some studies in machine learning using the game of checkers. IBM J. Res. Develop. 3, 211\u2013229 (1959).","journal-title":"IBM J. Res. Develop."},{"key":"BFnature14540_CR24","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1162\/neco.1994.6.2.215","volume":"6","author":"G Tesauro","year":"1994","unstructured":"Tesauro, G. TD-Gammon, a self-teaching backgammon program, achieves master-level play. Neural Comput. 6, 215\u2013219 (1994). This article describes the first reinforcement-learning system to solve a truly non-trivial task.","journal-title":"Neural Comput."},{"key":"BFnature14540_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1147\/JRD.2012.2188931","volume":"56","author":"G Tesauro","year":"2012","unstructured":"Tesauro, G., Gondek, D., Lenchner, J., Fan, J. & Prager, J. M. Simulation, learning, and optimization techniques in Watson's game strategies. IBM J. Res. Develop. 56, 1\u201311 (2012).","journal-title":"IBM J. Res. Develop."},{"key":"BFnature14540_CR26","first-page":"282","volume-title":"Proc. 17th European Conference on Machine Learning","author":"L Kocsis","year":"2006","unstructured":"Kocsis, L. & Szepesv\u00e1ri, C. Bandit based Monte-Carlo planning. In Proc. 17th European Conference on Machine Learning 282\u2013293 (2006). This article introduces UCT, the decision-making algorithm that revolutionized gameplay in Go."},{"key":"BFnature14540_CR27","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1145\/2093548.2093574","volume":"55","author":"S Gelly","year":"2012","unstructured":"Gelly, S. et al. The grand challenge of computer Go: Monte Carlo tree search and extensions. Communications of the ACM 55, 106\u2013113 (2012).","journal-title":"Communications of the ACM"},{"key":"BFnature14540_CR28","first-page":"39","volume-title":"Proc. 35th International Symposium on Computer Architecture","author":"E \u0130pek","year":"2008","unstructured":"\u0130pek. E., Mutlu, O., Mart\u00ednez, J. F. & Caruana, R. Self-optimizing memory controllers: a reinforcement learning approach. In Proc. 35th International Symposium on Computer Architecture 39\u201350 (2008)."},{"key":"BFnature14540_CR29","volume-title":"Proc. Advances in Neural Information Processing Systems","author":"AY Ng","year":"2003","unstructured":"Ng, A. Y., Kim, H. J., Jordan, M. I. & Sastry, S. Autonomous helicopter flight via reinforcement learning. In Proc. Advances in Neural Information Processing Systems http:\/\/papers.nips.cc\/paper\/2455-autonomous-helicopter-flight-via-reinforcement-learning (2003)."},{"key":"BFnature14540_CR30","first-page":"216","volume-title":"Proc. 7th International Conference on Machine Learning","author":"RS Sutton","year":"1990","unstructured":"Sutton, R. S. Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In Proc. 7th International Conference on Machine Learning 216\u2013224 (Morgan Kaufmann, 1990)."},{"key":"BFnature14540_CR31","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1023\/A:1017984413808","volume":"49","author":"MJ Kearns","year":"2002","unstructured":"Kearns, M. J. & Singh, S. P. Near-optimal reinforcement learning in polynomial time. Mach. Learn. 49, 209\u2013232 (2002). This article provides the first algorithm and analysis that shows that reinforcement-learning tasks can be solved approximately optimally with a relatively small amount of experience.","journal-title":"Mach. Learn."},{"key":"BFnature14540_CR32","first-page":"213","volume":"3","author":"RI Brafman","year":"2002","unstructured":"Brafman, R. I. & Tennenholtz, M. R-MAX \u2014 a general polynomial time algorithm for near-optimal reinforcement learning. J. Mach. Learn. Res. 3, 213\u2013231 (2002).","journal-title":"J. Mach. Learn. Res."},{"key":"BFnature14540_CR33","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1007\/s10994-010-5225-4","volume":"82","author":"L Li","year":"2011","unstructured":"Li, L., Littman, M. L., Walsh, T. J. & Strehl, A. L. Knows what it knows: a framework for self-aware learning. Mach. Learn. 82, 399\u2013443 (2011).","journal-title":"Mach. Learn."},{"key":"BFnature14540_CR34","first-page":"5","volume":"3","author":"P Langley","year":"1988","unstructured":"Langley, P. Machine learning as an experimental science. Mach. Learn. 3, 5\u20138 (1988).","journal-title":"Mach. Learn."},{"key":"BFnature14540_CR35","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M. G., Naddaf, Y., Veness, J. & Bowling, M. The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013).","journal-title":"J. Artif. Intell. Res."},{"key":"BFnature14540_CR36","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015). This article describes the application of deep learning in a reinforcement-learning setting to address the challenging task of decision making in an arcade environment.","journal-title":"Nature"},{"key":"BFnature14540_CR37","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1002\/sim.2022","volume":"24","author":"SA Murphy","year":"2005","unstructured":"Murphy, S. A. An experimental design for the development of adaptive treatment strategies. Stat. Med. 24, 1455\u20131481 (2005).","journal-title":"Stat. Med."},{"key":"BFnature14540_CR38","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1145\/1935826.1935878","volume-title":"Proc. 4th ACM International Conference on Web Search and Data Mining","author":"L Li","year":"2011","unstructured":"Li, L., Chu, W., Langford, J. & Wang, X. Unbiased offline evaluation of contextual-bandit-based news article recommendation algorithms. In Proc. 4th ACM International Conference on Web Search and Data Mining 297\u2013306 (2011)."},{"key":"BFnature14540_CR39","volume-title":"Proc. Multidisciplinary Symposium on Reinforcement Learning","author":"A Nouri","year":"2009","unstructured":"Nouri, A. et al. A novel benchmark methodology and data repository for real-life reinforcement learning. In Proc. Multidisciplinary Symposium on Reinforcement Learning, Poster (2009)."},{"key":"BFnature14540_CR40","volume-title":"Proc. Machine Learning for Clinical Data Analysis and Healthcare NIPS Workshop","author":"VN Marivate","year":"2013","unstructured":"Marivate, V. N., Chemali, J., Littman, M. & Brunskill, E. Discovering multi-modal characteristics in observational clinical data. In Proc. Machine Learning for Clinical Data Analysis and Healthcare NIPS Workshop http:\/\/paul.rutgers.edu\/\u223cvukosi\/papers\/nips2013workshop.pdf (2013)."},{"key":"BFnature14540_CR41","first-page":"278","volume-title":"Proc. 16th International Conference on Machine Learning","author":"AY Ng","year":"1999","unstructured":"Ng, A. Y., Harada, D. & Russell, S. Policy invariance under reward transformations: theory and application to reward shaping. In Proc. 16th International Conference on Machine Learning 278\u2013287 (1999)."},{"key":"BFnature14540_CR42","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1016\/j.artint.2007.09.009","volume":"172","author":"AL Thomaz","year":"2008","unstructured":"Thomaz, A. L. & Breazeal, C. Teachable robots: understanding human teaching behaviour to build more effective robot learners. Artif. Intell. 172, 716\u2013737 (2008).","journal-title":"Artif. Intell."},{"key":"BFnature14540_CR43","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1145\/1597735.1597738","volume-title":"Proc. 5th International Conference on Knowledge Capture","author":"WB Knox","year":"2009","unstructured":"Knox, W. B. & Stone, P. Interactively shaping agents via human reinforcement: The TAMER framework. In Proc. 5th International Conference on Knowledge Capture 9\u201316 (2009)."},{"key":"BFnature14540_CR44","volume-title":"Proc. 28th Association for the Advancement of Artificial Intelligence Conference","author":"R Loftin","year":"2014","unstructured":"Loftin, R. et al. A strategy-aware technique for learning behaviors from discrete human feedback. In Proc. 28th Association for the Advancement of Artificial Intelligence Conference https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI14\/paper\/view\/8579 (2014)."},{"key":"BFnature14540_CR45","first-page":"663","volume-title":"Proc. International Conference on Machine Learning","author":"AY Ng","year":"2000","unstructured":"Ng, A. Y. & Russell, S. Algorithms for inverse reinforcement learning. In Proc. International Conference on Machine Learning 663\u2013670 (2000)."},{"key":"BFnature14540_CR46","first-page":"897","volume-title":"Proc. International Conference on Machine Learning","author":"M Babes","year":"2011","unstructured":"Babes, M., Marivate, V. N., Littman, M. L. & Subramanian, K. Apprenticeship learning about multiple intentions. In Proc. International Conference on Machine Learning 897\u2013904 (2011)."},{"key":"BFnature14540_CR47","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/TAMD.2010.2051031","volume":"2","author":"S Singh","year":"2010","unstructured":"Singh, S., Lewis, R.L., Barto, A.G. & Sorg, J. Intrinsically motivated reinforcement learning: an evolutionary perspective. IEEE Trans. Auto. Mental Dev. 2, 70\u201382 (2010).","journal-title":"IEEE Trans. Auto. Mental Dev."},{"key":"BFnature14540_CR48","doi-asserted-by":"crossref","unstructured":"Newell, A. The chess machine: an example of dealing with a complex task by adaptation. In Proc. Western Joint Computer Conference 101\u2013108 (1955).","DOI":"10.1145\/1455292.1455312"},{"key":"BFnature14540_CR49","first-page":"24","volume-title":"Proc. Symposium on the Mechanization of Thought Processes","author":"ML Minsky","year":"1958","unstructured":"Minsky, M. L. Some methods of artificial intelligence and heuristic programming. In Proc. Symposium on the Mechanization of Thought Processes 24\u201327 (1958)."},{"key":"BFnature14540_CR50","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1037\/0033-295X.88.2.135","volume":"88","author":"RS Sutton","year":"1981","unstructured":"Sutton, R. S. & Barto, A. G. Toward a modern theory of adaptive networks: expectation and prediction. Psychol. Rev. 88, 135\u2013170 (1981).","journal-title":"Psychol. Rev."},{"key":"BFnature14540_CR51","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.1126\/science.275.5306.1593","volume":"275","author":"W Schultz","year":"1997","unstructured":"Schultz, W., Dayan, P. & Montague, P. R. A neural substrate of prediction and reward. Science 275, 1593\u20131599 (1997).","journal-title":"Science"},{"key":"BFnature14540_CR52","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.conb.2008.08.003","volume":"18","author":"P Dayan","year":"2008","unstructured":"Dayan, P. & Niv, Y. Reinforcement learning and the brain: the good, the bad and the ugly. Curr. Opin. Neurobiol. 18, 185\u2013196 (2008).","journal-title":"Curr. Opin. Neurobiol."},{"key":"BFnature14540_CR53","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/500533a","volume":"500","author":"Y Niv","year":"2013","unstructured":"Niv, Y. Neuroscience: dopamine ramps up. Nature 500, 533\u2013535 (2013).","journal-title":"Nature"},{"key":"BFnature14540_CR54","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1177\/1088868313495594","volume":"17","author":"F Cushman","year":"2013","unstructured":"Cushman, F. Action, outcome, and value a dual-system framework for morality. Pers. Soc. Psychol. Rev. 17, 273\u2013292 (2013).","journal-title":"Pers. Soc. Psychol. Rev."},{"key":"BFnature14540_CR55","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1073\/pnas.39.10.1095","volume":"39","author":"L Shapley","year":"1953","unstructured":"Shapley, L. Stochastic games. Proc. Natl Acad. Sci. USA 39, 1095\u20131100 (1953).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"BFnature14540_CR56","volume-title":"Dynamic Programming","author":"R Bellman","year":"1957","unstructured":"Bellman, R. Dynamic Programming (Princeton Univ. Press, 1957)."},{"key":"BFnature14540_CR57","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1177\/0278364913495721","volume":"32","author":"J Kober","year":"2013","unstructured":"Kober, J., Bagnell, J. A. & Peters, J. Reinforcement learning in robotics: a survey. Int. J. Rob. Res. 32, 1238\u20131274 (2013).","journal-title":"Int. J. Rob. Res."},{"key":"BFnature14540_CR58","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C. J. C. H. & Dayan, P. Q-learning. Mach. Learn. 8, 279\u2013292 (1992). This article introduces the first provably correct approach to reinforcement learning for both prediction and decision making.","journal-title":"Mach. Learn."},{"key":"BFnature14540_CR59","first-page":"703","volume-title":"Advances in Neural Information Processing Systems","author":"T Jaakkola","year":"1994","unstructured":"Jaakkola, T., Jordan, M. I. & Singh, S. P. Convergence of stochastic iterative dynamic programming algorithms. In Advances in Neural Information Processing Systems 6, 703\u2013710 (Morgan Kaufmann, 1994)."},{"key":"BFnature14540_CR60","first-page":"32","volume-title":"Proc. 26th International Conference on Machine Learning","author":"C Diuk","year":"2009","unstructured":"Diuk, C., Li, L. & Leffner, B. R. The adaptive k-meteorologists problem and its application to structure learning and feature selection in reinforcement learning. In Proc. 26th International Conference on Machine Learning 32\u201340 (2009)."}],"container-title":["Nature"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/nature14540.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/nature14540","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/nature14540.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,10]],"date-time":"2023-08-10T18:11:36Z","timestamp":1691691096000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/nature14540"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5,27]]},"references-count":60,"journal-issue":{"issue":"7553","published-print":{"date-parts":[[2015,5,28]]}},"alternative-id":["BFnature14540"],"URL":"https:\/\/doi.org\/10.1038\/nature14540","relation":{},"ISSN":["0028-0836","1476-4687"],"issn-type":[{"value":"0028-0836","type":"print"},{"value":"1476-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,5,27]]},"assertion":[{"value":"11 January 2015","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 April 2015","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 May 2015","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The author declares no competing financial interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}