From Tic Tac Toe to AlphaGo: Playing games with AI by Roy van Rijn

Google DeepMind’s AlphaGo was an extraordinary breakthrough for Artificial Intelligence. The game of Go has 1.74×10^172 unique positions and is about a ‘googol’ times harder to calculate than chess. Experts thought it would take at least another decade before A.I. would be able to beat the best human players. So how did DeepMind tackle this problem? What algorithms did they usage and how do they piece of work?
During this talk we’ll explore several algorithms that can be used to make a program play games, we’ll start simple (Tic Tac Toe) and as the games get harder, the A.I.’s need to become smarter.

About Roy
Roy van Rijn is director at OpenValue Rotterdam and a Java Champion. He worked on numerous projects all over the Netherlands as developer, architect and agile coach. You can read more at his blog (http://www.royvanrijn.com) or follow him on Twitter (@royvanrijn).