{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/move-evaluation-in-go-using-deep","title":"Move Evaluation in Go Using Deep Convolutional Neural Networks","arxiv_id":"1412.6564","date":"2014-12-20","proceeding":null,"authors":["Chris J. Maddison","Aja Huang","Ilya Sutskever","David Silver"],"abstract":"The game of Go is more challenging than other board games, due to the\ndifficulty of constructing a position or move evaluation function. In this\npaper we investigate whether deep convolutional networks can be used to\ndirectly represent and learn this knowledge. We train a large 12-layer\nconvolutional neural network by supervised learning from a database of human\nprofessional games. The network correctly predicts the expert move in 55% of\npositions, equalling the accuracy of a 6 dan human player. When the trained\nconvolutional network was used directly to play games of Go, without any\nsearch, it beat the traditional search program GnuGo in 97% of games, and\nmatched the performance of a state-of-the-art Monte-Carlo tree search that\nsimulates a million positions per move.","url_abs":"http://arxiv.org/abs/1412.6564v2","url_pdf":"http://arxiv.org/pdf/1412.6564v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"move-evaluation-in-go-using-deep","repo_url":"https://github.com/jmgilmer/GoCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"board-games","task_name":"Board Games"},{"task_slug":"game-of-go","task_name":"Game of Go"},{"task_slug":null,"task_name":"Position"}],"methods":[{"method_slug":"monte-carlo-tree-search","method_name":"Monte-Carlo Tree Search"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1412.6564","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}