2013
Search results
AlphaGo is a computer program that plays the board game Go. [1] It was developed by the London-based DeepMind Technologies, [2] an acquired subsidiary of Google. Subsequent versions of AlphaGo became increasingly powerful, including a version that competed under the name Master. [3]
AlphaGo is an AI system that learned to play Go, a complex board game of strategy and creativity, and defeated a human world champion. It combined deep neural networks with reinforcement learning and invented winning moves that challenged centuries of traditional wisdom.
Oct 19, 2017 · Recently, AlphaGo became the first program to defeat a world champion in the game of Go. The tree search in AlphaGo evaluated positions and selected moves using deep neural networks.
Oct 18, 2017 · AlphaGo Zero is a novel reinforcement learning algorithm that teaches itself to play Go from scratch, without any human input. It surpasses previous versions of AlphaGo and defeats the world champions by 100 games to 0.
AlphaGo - The Movie | Full award-winning documentary. With more board configurations than there are atoms in the universe, the ancient Chinese game of Go has long been considered a grand...
Explore how AlphaGo, the AI that beat human champions at Go, plays the game and improves its skills. Use the interactive board to see AlphaGo's predicted winrate for each move and compare it with human players' moves.
Jan 27, 2016 · AlphaGo is a machine learning system that combines neural networks and reinforcement learning to play Go, a complex and ancient board game. It has beaten human experts and professionals, and will challenge the world champion Lee Sedol in 2016.
