28 January 2016

Google Research Blog: “AlphaGo: Mastering the ancient game of Go with Machine Learning”

But as simple as the rules are, Go is a game of profound complexity. The search space in Go is vast – more than a googol times larger than chess (a number greater than there are atoms in the universe!). As a result, traditional “brute force” AI methods – which construct a search tree over all possible sequences of moves – don’t have a chance in Go. To date, computers have played Go only as well as amateurs. Experts predicted it would be at least another 10 years until a computer could beat one of the world’s elite group of Go professionals.

We saw this as an irresistible challenge! We started building a system, AlphaGo, described in a paper in Nature this week, that would overcome these barriers. The key to AlphaGo is reducing the enormous search space to something more manageable. To do this, it combines a state-of-the-art tree search with two deep neural networks, each of which contains many layers with millions of neuron-like connections. One neural network, the “policy network”, predicts the next move, and is used to narrow the search to consider only the moves most likely to lead to a win. The other neural network, the “value network”, is then used to reduce the depth of the search tree – estimating the winner in each position in place of searching all the way to the end of the game.

David Silver and Demis Hassabis

Fascinating – and rather unexpected – development in the field of artificial intelligence: an algorithm that can consistently best human players at Go, the only remaining deterministic game where humans have (had?) the upper hand. I must admit, I am starting to understand why important people are getting worried that AI research is moving too fast and that the world is ill prepared for the rapid changes it will bring…

Google DeepMind: Ground-breaking AlphaGo masters the game of Go

Amusingly, only a day earlier Mark Zuckerberg posted an update about the progress of Facebook’s AI Research team on the very same problem. As exciting as a human-against-machine game sounds, I am rather looking forward to a match of AlphaGo against FaceGo – and I think there’s a good chance it could happen before the end of the year!

The ancient Chinese game of Go is one of the last games where the best human players can still beat the best artificial...

Posted by Mark Zuckerberg on Tuesday, January 26, 2016

Post a Comment