[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-43476-en":3,"doc-seo-43476-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},43476,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","Mastering the Game of Go with Deep Neural Networks and Tree Search","The document presents a computer-Go approach that integrates deep neural networks with tree search. It uses value networks to evaluate board positions and policy networks to select moves, trained via supervised learning from human expert games and reinforcement learning from self-play. Without lookahead, the networks reach state-of-the-art performance comparable to strong Monte-Carlo tree search. A new search algorithm combining Monte-Carlo simulation with the learned networks enables AlphaGo to achieve a 99.8% win rate against other programs and defeat a European champion 5–0.","Mastering the Game of Go with Deep Neural Networks and Tree Search  \nDavid Silver1 *, Aja Huang 1 *, Chris J. Maddison 1 , Arthur Guez 1 , Laurent Sifre 1 , George van den Driessche 1 , Julian Schrittwieser1 , Ioannis Antonoglou 1 , Veda Panneershelvam 1 , Marc Lanctot 1 , Sander Dieleman 1 , Dominik Grewe 1 , John Nham2 , Nal Kalchbrenner1 , Ilya Sutskever2 , Timothy Lillicrap 1 , Madeleine Leach 1 , Koray Kavukcuoglu 1 , Thore Graepel 1 , Demis Hassabis 1.  \n1 Google DeepMind, 5 New Street Square, London EC4A 3TW.  \n2 Google, 1600 Amphitheatre Parkway, Mountain View CA 94043 .  \n*These authors contributed equally to this work.  \nCorrespondence should be addressed to either David Silver ([davidsilver@google.com](davidsilver@google.com)) or Demis Hassabis ([demishassabis@google.com](demishassabis@google.com)).  \nThe game of Go has long been viewed as the most challenging of classic games for artificial intelligence due to its enormous search space and the difficulty of evaluating board positions and moves. We introduce a new approach to computer Go that uses value networks to evaluate board positions and policy networks to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of state-of-the-art Monte-Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte-Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.  \nAll games of perfect information have an optimal value function, v 􀀃 (s), which determines the outcome of the game, from every board position or state s, under perfect play by all players. These games may be solved by recursively computing the optimal value function in a search tree containing approximately bd possible sequences of moves, where b is the game's breadth (number  \nof legal moves per position) and d is its depth (game length) . In large games, such as chess (b 􀀙 35; d 􀀙 80) 1 and especially Go (b 􀀙 250; d 􀀙 150) 1 , exhaustive search is infeasible 2, 3 , but the effective search space can be reduced by two general principles. First, the depth of the search may be reduced by position evaluation: truncating the search tree at state s and replacing the subtree below s by an approximate value function v(s) 􀀙 v􀀃 (s) that predicts the outcome from state s. This approach has led to super-human performance in chess 4 , checkers 5 and othello 6 , but it was believed to be intractable in Go due to the complexity of the game 7. Second, the breadth of the search may be reduced by sampling actions from a policy p(ajs) that is a probability distribution over possible moves a in position s. For example, Monte-Carlo rollouts 8 search to maximum depth without branching at all, by sampling long sequences of actions for both players from a policy p. Averaging over such rollouts can provide an effective position evaluation, achieving super-human performance in backgammon 8 and Scrabble 9 , and weak amateur level play in Go 10.  \nMonte-Carlo tree search (MCTS) 11, 12 uses Monte-Carlo rollouts to estimate the value of each state in a search tree. As more simulations are executed, the search tree grows larger and the relevant values become more accurate. The policy used to select actions during search is also improved over time, by selecting children with higher values. Asymptotically, this policy converges to optimal play, and the evaluations converge to the optimal value function 12. The strongest current Go programs are based on MCT","cbCaiuvANE4yEbgI","https://ap.wps.com/l/cbCaiuvANE4yEbgI","pdf",1630106,3,1,37,"English","en",105,"# Overview of the approach\n# Optimal value functions and search complexity\n# Monte-Carlo tree search and prior policy/value methods\n# Deep neural network architecture for Go positions\n# Training pipeline: supervised learning, reinforcement learning, and value learning","[{\"question\":\"How does the approach evaluate Go positions and choose moves?\",\"answer\":\"It uses a value network to evaluate board positions and a policy network to select moves, guiding the search and action sampling.\"},{\"question\":\"How are the neural networks trained?\",\"answer\":\"Training combines supervised learning from human expert games with reinforcement learning from self-play, followed by value network training to predict outcomes against itself.\"},{\"question\":\"What role does Monte-Carlo tree search play in the system?\",\"answer\":\"Monte-Carlo simulations estimate state values, while the combined search algorithm uses the value and policy networks to improve move selection and reduce effective search depth and breadth.\"}]",1783381667,93,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"mastering-the-game-of-go-with-deep-neural-networks-and-tree-search","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/mastering-the-game-of-go-with-deep-neural-networks-and-tree-search/43476/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-13","2026-07-06",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How does the approach evaluate Go positions and choose moves?","Question",{"text":75,"@type":76},"It uses a value network to evaluate board positions and a policy network to select moves, guiding the search and action sampling.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are the neural networks trained?",{"text":80,"@type":76},"Training combines supervised learning from human expert games with reinforcement learning from self-play, followed by value network training to predict outcomes against itself.",{"name":82,"@type":73,"acceptedAnswer":83},"What role does Monte-Carlo tree search play in the system?",{"text":84,"@type":76},"Monte-Carlo simulations estimate state values, while the combined search algorithm uses the value and policy networks to improve move selection and reduce effective search depth and breadth.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]