{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T20:47:19Z","timestamp":1776199639046,"version":"3.50.1"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"7587","license":[{"start":{"date-parts":[[2016,1,27]],"date-time":"2016-01-27T00:00:00Z","timestamp":1453852800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,27]],"date-time":"2016-01-27T00:00:00Z","timestamp":1453852800000},"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":[[2016,1,28]]},"DOI":"10.1038\/nature16961","type":"journal-article","created":{"date-parts":[[2016,1,26]],"date-time":"2016-01-26T12:44:19Z","timestamp":1453812259000},"page":"484-489","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11073,"title":["Mastering the game of Go with deep neural networks and tree search"],"prefix":"10.1038","volume":"529","author":[{"given":"David","family":"Silver","sequence":"first","affiliation":[]},{"given":"Aja","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Chris J.","family":"Maddison","sequence":"additional","affiliation":[]},{"given":"Arthur","family":"Guez","sequence":"additional","affiliation":[]},{"given":"Laurent","family":"Sifre","sequence":"additional","affiliation":[]},{"given":"George","family":"van den Driessche","sequence":"additional","affiliation":[]},{"given":"Julian","family":"Schrittwieser","sequence":"additional","affiliation":[]},{"given":"Ioannis","family":"Antonoglou","sequence":"additional","affiliation":[]},{"given":"Veda","family":"Panneershelvam","sequence":"additional","affiliation":[]},{"given":"Marc","family":"Lanctot","sequence":"additional","affiliation":[]},{"given":"Sander","family":"Dieleman","sequence":"additional","affiliation":[]},{"given":"Dominik","family":"Grewe","sequence":"additional","affiliation":[]},{"given":"John","family":"Nham","sequence":"additional","affiliation":[]},{"given":"Nal","family":"Kalchbrenner","sequence":"additional","affiliation":[]},{"given":"Ilya","family":"Sutskever","sequence":"additional","affiliation":[]},{"given":"Timothy","family":"Lillicrap","sequence":"additional","affiliation":[]},{"given":"Madeleine","family":"Leach","sequence":"additional","affiliation":[]},{"given":"Koray","family":"Kavukcuoglu","sequence":"additional","affiliation":[]},{"given":"Thore","family":"Graepel","sequence":"additional","affiliation":[]},{"given":"Demis","family":"Hassabis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,1,27]]},"reference":[{"key":"BFnature16961_CR1","unstructured":"Allis, L. V. Searching for Solutions in Games and Artificial Intelligence. PhD thesis, Univ. Limburg, Maastricht, The Netherlands (1994)"},{"key":"BFnature16961_CR2","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1016\/S0004-3702(01)00152-7","volume":"134","author":"H van den Herik","year":"2002","unstructured":"van den Herik, H., Uiterwijk, J. W. & van Rijswijck, J. Games solved: now and in the future. Artif. Intell. 134, 277\u2013311 (2002)","journal-title":"Artif. Intell."},{"key":"BFnature16961_CR3","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/S0065-2458(00)80019-4","volume":"52","author":"J Schaeffer","year":"2000","unstructured":"Schaeffer, J. The games computers (and people) play. Advances in Computers 52, 189\u2013266 (2000)","journal-title":"Advances in Computers"},{"key":"BFnature16961_CR4","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. & Hsu, F. Deep Blue. Artif. Intell. 134, 57\u201383 (2002)","journal-title":"Artif. Intell."},{"key":"BFnature16961_CR5","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1016\/0004-3702(92)90074-8","volume":"53","author":"J Schaeffer","year":"1992","unstructured":"Schaeffer, J. et al. A world championship caliber checkers program. Artif. Intell. 53, 273\u2013289 (1992)","journal-title":"Artif. Intell."},{"key":"BFnature16961_CR6","doi-asserted-by":"crossref","unstructured":"Buro, M. From simple features to sophisticated evaluation functions. In 1st International Conference on Computers and Games, 126\u2013145 (1999)","DOI":"10.1007\/3-540-48957-6_8"},{"key":"BFnature16961_CR7","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/S0004-3702(01)00121-7","volume":"134","author":"M M\u00fcller","year":"2002","unstructured":"M\u00fcller, M. Computer Go. Artif. Intell. 134, 145\u2013179 (2002)","journal-title":"Artif. Intell."},{"key":"BFnature16961_CR8","unstructured":"Tesauro, G. & Galperin, G. On-line policy improvement using Monte-Carlo search. In Advances in Neural Information Processing, 1068\u20131074 (1996)"},{"key":"BFnature16961_CR9","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/S0004-3702(01)00166-7","volume":"134","author":"B Sheppard","year":"2002","unstructured":"Sheppard, B. World-championship-caliber Scrabble. Artif. Intell. 134, 241\u2013275 (2002)","journal-title":"Artif. Intell."},{"key":"BFnature16961_CR10","doi-asserted-by":"crossref","unstructured":"Bouzy, B. & Helmstetter, B. Monte-Carlo Go developments. In 10th International Conference on Advances in Computer Games, 159\u2013174 (2003)","DOI":"10.1007\/978-0-387-35706-5_11"},{"key":"BFnature16961_CR11","doi-asserted-by":"crossref","unstructured":"Coulom, R. Efficient selectivity and backup operators in Monte-Carlo tree search. In 5th International Conference on Computers and Games, 72\u201383 (2006)","DOI":"10.1007\/978-3-540-75538-8_7"},{"key":"BFnature16961_CR12","doi-asserted-by":"crossref","unstructured":"Kocsis, L. & Szepesv\u00e1ri, C. Bandit based Monte-Carlo planning. In 15th European Conference on Machine Learning, 282\u2013293 (2006)","DOI":"10.1007\/11871842_29"},{"key":"BFnature16961_CR13","doi-asserted-by":"publisher","first-page":"198","DOI":"10.3233\/ICG-2007-30403","volume":"30","author":"R Coulom","year":"2007","unstructured":"Coulom, R. Computing Elo ratings of move patterns in the game of Go. ICGA J. 30, 198\u2013208 (2007)","journal-title":"ICGA J."},{"key":"BFnature16961_CR14","doi-asserted-by":"crossref","unstructured":"Baudi\u0161, P. & Gailly, J.-L. Pachi: State of the art open source Go program. In Advances in Computer Games, 24\u201338 (Springer, 2012)","DOI":"10.1007\/978-3-642-31866-5_3"},{"key":"BFnature16961_CR15","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1109\/TCIAIG.2010.2083662","volume":"2","author":"M M\u00fcller","year":"2010","unstructured":"M\u00fcller, M., Enzenberger, M., Arneson, B. & Segal, R. Fuego \u2013 an open-source framework for board games and Go engine based on Monte-Carlo tree search. IEEE Trans. Comput. Intell. AI in Games 2, 259\u2013270 (2010)","journal-title":"IEEE Trans. Comput. Intell. AI in Games"},{"key":"BFnature16961_CR16","doi-asserted-by":"crossref","unstructured":"Gelly, S. & Silver, D. Combining online and offline learning in UCT. In 17th International Conference on Machine Learning, 273\u2013280 (2007)","DOI":"10.1145\/1273496.1273531"},{"key":"BFnature16961_CR17","unstructured":"Krizhevsky, A., Sutskever, I. & Hinton, G. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems, 1097\u20131105 (2012)"},{"key":"BFnature16961_CR18","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1109\/72.554195","volume":"8","author":"S Lawrence","year":"1997","unstructured":"Lawrence, S., Giles, C. L., Tsoi, A. C. & Back, A. D. Face recognition: a convolutional neural-network approach. IEEE Trans. Neural Netw. 8, 98\u2013113 (1997)","journal-title":"IEEE Trans. Neural Netw."},{"key":"BFnature16961_CR19","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)","journal-title":"Nature"},{"key":"BFnature16961_CR20","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436\u2013444 (2015)","journal-title":"Nature"},{"key":"BFnature16961_CR21","doi-asserted-by":"crossref","unstructured":"Stern, D., Herbrich, R. & Graepel, T. Bayesian pattern ranking for move prediction in the game of Go. In International Conference of Machine Learning, 873\u2013880 (2006)","DOI":"10.1145\/1143844.1143954"},{"key":"BFnature16961_CR22","doi-asserted-by":"crossref","unstructured":"Sutskever, I. & Nair, V. Mimicking Go experts with convolutional neural networks. In International Conference on Artificial Neural Networks, 101\u2013110 (2008)","DOI":"10.1007\/978-3-540-87559-8_11"},{"key":"BFnature16961_CR23","unstructured":"Maddison, C. J., Huang, A., Sutskever, I. & Silver, D. Move evaluation in Go using deep convolutional neural networks. 3rd International Conference on Learning Representations (2015)"},{"key":"BFnature16961_CR24","unstructured":"Clark, C. & Storkey, A. J. Training deep convolutional neural networks to play go. In 32nd International Conference on Machine Learning, 1766\u20131774 (2015)"},{"key":"BFnature16961_CR25","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R. J. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"BFnature16961_CR26","unstructured":"Sutton, R., McAllester, D., Singh, S. & Mansour, Y. Policy gradient methods for reinforcement learning with function approximation. In Advances in Neural Information Processing Systems, 1057\u20131063 (2000)"},{"key":"BFnature16961_CR27","doi-asserted-by":"crossref","unstructured":"Sutton, R. & Barto, A. Reinforcement Learning: an Introduction (MIT Press, 1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"BFnature16961_CR28","first-page":"817","volume":"6","author":"NN Schraudolph","year":"1994","unstructured":"Schraudolph, N. N., Dayan, P. & Sejnowski, T. J. Temporal difference learning of position evaluation in the game of Go. Adv. Neural Inf. Process. Syst. 6, 817\u2013824 (1994)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"BFnature16961_CR29","doi-asserted-by":"crossref","unstructured":"Enzenberger, M. Evaluation in Go by a neural network using soft segmentation. In 10th Advances in Computer Games Conference, 97\u2013108 (2003). 267","DOI":"10.1007\/978-0-387-35706-5_7"},{"key":"BFnature16961_CR30","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s10994-012-5280-0","volume":"87","author":"D Silver","year":"2012","unstructured":"Silver, D., Sutton, R. & M\u00fcller, M. Temporal-difference search in computer Go. Mach. Learn. 87, 183\u2013219 (2012)","journal-title":"Mach. Learn."},{"key":"BFnature16961_CR31","unstructured":"Levinovitz, A. The mystery of Go, the ancient game that computers still can\u2019t win. Wired Magazine (2014)"},{"key":"BFnature16961_CR32","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1002\/j.2326-1951.1998.tb03356.x","volume":"38","author":"D Mechner","year":"1998","unstructured":"Mechner, D. All Systems Go. The Sciences 38, 32\u201337 (1998)","journal-title":"The Sciences"},{"key":"BFnature16961_CR33","doi-asserted-by":"crossref","unstructured":"Mandziuk, J. Computational intelligence in mind games. In Challenges for Computational Intelligence, 407\u2013442 (2007)","DOI":"10.1007\/978-3-540-71984-7_15"},{"key":"BFnature16961_CR34","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/S0004-3702(78)80012-5","volume":"10","author":"H Berliner","year":"1978","unstructured":"Berliner, H. A chronology of computer chess and its literature. Artif. Intell. 10, 201\u2013214 (1978)","journal-title":"Artif. Intell."},{"key":"BFnature16961_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCIAIG.2012.2186810","volume":"4","author":"C Browne","year":"2012","unstructured":"Browne, C. et al. A survey of Monte-Carlo tree search methods. IEEE Trans. Comput. Intell. AI in Games 4, 1\u201343 (2012)","journal-title":"IEEE Trans. Comput. Intell. AI in Games"},{"key":"BFnature16961_CR36","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. Commun. ACM 55, 106\u2013113 (2012)","journal-title":"Commun. ACM"},{"key":"BFnature16961_CR37","doi-asserted-by":"crossref","unstructured":"Coulom, R. Whole-history rating: A Bayesian rating system for players of time-varying strength. In International Conference on Computers and Games, 113\u2013124 (2008)","DOI":"10.1007\/978-3-540-87608-3_11"},{"key":"BFnature16961_CR38","unstructured":"KGS. Rating system math. http:\/\/www.gokgs.com\/help\/rmath.html"},{"key":"BFnature16961_CR39","doi-asserted-by":"crossref","unstructured":"Littman, M. L. Markov games as a framework for multi-agent reinforcement learning. In 11th International Conference on Machine Learning, 157\u2013163 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"BFnature16961_CR40","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/0004-3702(75)90019-3","volume":"6","author":"DE Knuth","year":"1975","unstructured":"Knuth, D. E. & Moore, R. W. An analysis of alpha-beta pruning. Artif. Intell. 6, 293\u2013326 (1975)","journal-title":"Artif. Intell."},{"key":"BFnature16961_CR41","first-page":"9","volume":"3","author":"R Sutton","year":"1988","unstructured":"Sutton, R. Learning to predict by the method of temporal differences. Mach. Learn. 3, 9\u201344 (1988)","journal-title":"Mach. Learn."},{"key":"BFnature16961_CR42","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1023\/A:1007634325138","volume":"40","author":"J Baxter","year":"2000","unstructured":"Baxter, J., Tridgell, A. & Weaver, L. Learning to play chess using temporal differences. Mach. Learn. 40, 243\u2013263 (2000)","journal-title":"Mach. Learn."},{"key":"BFnature16961_CR43","unstructured":"Veness, J., Silver, D., Blair, A. & Uther, W. Bootstrapping from game tree search. In Advances in Neural Information Processing Systems (2009)"},{"key":"BFnature16961_CR44","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1147\/rd.116.0601","volume":"11","author":"AL Samuel","year":"1967","unstructured":"Samuel, A. L. Some studies in machine learning using the game of checkers II - recent progress. IBM J. Res. Develop. 11, 601\u2013617 (1967)","journal-title":"IBM J. Res. Develop."},{"key":"BFnature16961_CR45","unstructured":"Schaeffer, J., Hlynka, M. & Jussila, V. Temporal difference learning applied to a high-performance game-playing program. In 17th International Joint Conference on Artificial Intelligence, 529\u2013534 (2001)"},{"key":"BFnature16961_CR46","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)","journal-title":"Neural Comput."},{"key":"BFnature16961_CR47","unstructured":"Dahl, F. Honte, a Go-playing program using neural nets. In Machines that learn to play games, 205\u2013223 (Nova Science, 1999)"},{"key":"BFnature16961_CR48","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/s10472-011-9258-6","volume":"61","author":"CD Rosin","year":"2011","unstructured":"Rosin, C. D. Multi-armed bandits with episode context. Ann. Math. Artif. Intell. 61, 203\u2013230 (2011)","journal-title":"Ann. Math. Artif. Intell."},{"key":"BFnature16961_CR49","doi-asserted-by":"crossref","unstructured":"Lanctot, M., Winands, M. H. M., Pepels, T. & Sturtevant, N. R. Monte Carlo tree search with heuristic evaluations using implicit minimax backups. In IEEE Conference on Computational Intelligence and Games, 1\u20138 (2014)","DOI":"10.1109\/CIG.2014.6932903"},{"key":"BFnature16961_CR50","first-page":"INRIA","volume":"6062","author":"S Gelly","year":"2006","unstructured":"Gelly, S., Wang, Y., Munos, R. & Teytaud, O. Modification of UCT with patterns in Monte-Carlo Go. Tech. Rep. 6062, INRIA (2006)","journal-title":"Tech. Rep."},{"key":"BFnature16961_CR51","doi-asserted-by":"crossref","unstructured":"Silver, D. & Tesauro, G. Monte-Carlo simulation balancing. In 26th International Conference on Machine Learning, 119 (2009)","DOI":"10.1145\/1553374.1553495"},{"key":"BFnature16961_CR52","doi-asserted-by":"crossref","unstructured":"Huang, S.-C., Coulom, R. & Lin, S.-S. Monte-Carlo simulation balancing in practice. In 7th International Conference on Computers and Games, 81\u201392 (Springer-Verlag, 2011)","DOI":"10.1007\/978-3-642-17928-0_8"},{"key":"BFnature16961_CR53","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1109\/TCIAIG.2010.2100396","volume":"2","author":"H Baier","year":"2010","unstructured":"Baier, H. & Drake, P. D. The power of forgetting: improving the last-good-reply policy in Monte Carlo Go. IEEE Trans. Comput. Intell. AI in Games 2, 303\u2013309 (2010)","journal-title":"IEEE Trans. Comput. Intell. AI in Games"},{"key":"BFnature16961_CR54","doi-asserted-by":"crossref","unstructured":"Huang, S. & M\u00fcller, M. Investigating the limits of Monte-Carlo tree search methods in computer Go. In 8th International Conference on Computers and Games, 39\u201348 (2013)","DOI":"10.1007\/978-3-319-09165-5_4"},{"key":"BFnature16961_CR55","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-642-17928-0_4","volume":"6515","author":"RB Segal","year":"2011","unstructured":"Segal, R. B. On the scalability of parallel UCT. Computers and Games 6515, 36\u201347 (2011)","journal-title":"Computers and Games"},{"key":"BFnature16961_CR56","doi-asserted-by":"crossref","unstructured":"Enzenberger, M. & M\u00fcller, M. A lock-free multithreaded Monte-Carlo tree search algorithm. In 12th Advances in Computer Games Conference, 14\u201320 (2009)","DOI":"10.1007\/978-3-642-12993-3_2"},{"key":"BFnature16961_CR57","doi-asserted-by":"crossref","unstructured":"Huang, S.-C., Coulom, R. & Lin, S.-S. Time management for Monte-Carlo tree search applied to the game of Go. In International Conference on Technologies and Applications of Artificial Intelligence, 462\u2013466 (2010)","DOI":"10.1109\/TAAI.2010.78"},{"key":"BFnature16961_CR58","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1016\/j.artint.2011.03.007","volume":"175","author":"S Gelly","year":"2011","unstructured":"Gelly, S. & Silver, D. Monte-Carlo tree search and rapid action value estimation in computer Go. Artif. Intell. 175, 1856\u20131875 (2011)","journal-title":"Artif. Intell."},{"key":"BFnature16961_CR59","doi-asserted-by":"publisher","first-page":"131","DOI":"10.3233\/ICG-2011-34302","volume":"34","author":"P Baudi\u0161","year":"2011","unstructured":"Baudi\u0161, P. Balancing MCTS by dynamically adjusting the komi value. ICGA J. 34, 131 (2011)","journal-title":"ICGA J."},{"key":"BFnature16961_CR60","unstructured":"Baier, H. & Winands, M. H. Active opening book application for Monte-Carlo tree search in 19\u00d719 Go. In Benelux Conference on Artificial Intelligence, 3\u201310 (2011)"},{"key":"BFnature16961_CR61","unstructured":"Dean, J. et al. Large scale distributed deep networks. In Advances in Neural Information Processing Systems, 1223\u20131231 (2012)"},{"key":"BFnature16961_CR62","unstructured":"Go ratings. http:\/\/www.goratings.org"}],"container-title":["Nature"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.nature.com\/articles\/nature16961.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/www.nature.com\/articles\/nature16961","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/www.nature.com\/articles\/nature16961.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,18]],"date-time":"2023-05-18T13:49:53Z","timestamp":1684417793000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/nature16961"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,1,27]]},"references-count":62,"journal-issue":{"issue":"7587","published-print":{"date-parts":[[2016,1,28]]}},"alternative-id":["BFnature16961"],"URL":"https:\/\/doi.org\/10.1038\/nature16961","relation":{"has-review":[{"id-type":"doi","id":"10.3410\/f.726105619.793525345","asserted-by":"object"}]},"ISSN":["0028-0836","1476-4687"],"issn-type":[{"value":"0028-0836","type":"print"},{"value":"1476-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,1,27]]},"assertion":[{"value":"11 November 2015","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2016","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 January 2016","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing financial interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}