alphagoteach.deepmind.comAlphaGo Teach: Discover new and creative ways of playing Go

AlphaGo Teach Home About About WGo.js Player 2.0 About DeepMind AlphaGo Credits 6,000 opening sequences in total, harvested from over 230,000 human games: 65,000 pro games (1980-2017) from Go4Go 36,000 pro games (1960-1990) from GoBase 130,000 9-dan games (2013-2016) from foxwq 75 AlphaGo games (using moves 1-30) with human players: 5 games against Fan Hui by AlphaGo Fan 5 games against Lee Sedol at the Google DeepMind Challenge Match by AlphaGo Lee 60 online games by AlphaGo Master 5 games at the Future of Go Summit by AlphaGo Master AlphaGo Teaching Tool developed by: Aja Huang, Fan Hui and Lucas Baker EN EN 简体中文 繁體中文 日本語 한국어 Let the AlphaGo Teaching Tool help you find new and creative ways of playing Go. Read More Read Less This tool provides analysis of 6,000 of the most popular opening sequences from the recent history of Go, using data from 231,000 human games and 75 games AlphaGo played against human players. Explore the board and learn how AlphaGo’s moves compare to those of professional and amateur players. Show Move Order Hide Move Order Overlay: None AlphaGo Value Rank Occurrences Key Moves AlphaGo would play Moves human players would play 46.8 AlphaGo’s evaluation of the move for black’s winrate Last move played How to Use The Tool Use the coloured circles or the controls to navigate the board, explore different opening sequences, and find out AlphaGo’s estimate of black winning for each move played. The number in each circle is that move’s % winrate from black’s perspective, based on AlphaGo’s predictions. When it is black’s move, values closer to 100 are considered better, and when it is white’s move, values closer to 0 are considered better. 50 means the game is considered equal. Understanding Alphago’s predicted winrate AlphaGo’s preferred move does not always have the highest value. This is because each move’s winning probability was computed by running an independent search of 10 million simulations from that position. AlphaGo has some randomness in this search, meaning it might pick different but similar value moves if we run the search again. For more information on how AlphaGo works, read the original paper published in Nature . Follow Research Applied BlogCareers Press Terms and Conditions Privacy Policy Alphabet Inc. © 2017 DeepMind Technologies Limited © 2017 DeepMind Technologies...