How Google DeepMind conquered the game of Go
Google’s AlphaGo is an extraordinary breakthrough for Artificial Intelligence. The game of 19×19 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 AI would be able to beat the best human players. So how did Google tackle this problem? What algorithms did they use and how do they work?
Roy van Rijn is a Software Craftsman at JPoint. He worked on miscellaneous projects and has given talks at Devoxx BE, Devoxx UK, Devoxx PL, Joy of Coding, J-Fall and J-Spring. He regularly gives trainings on various topics, including Spring, Software Architecture, Testing and Agile/Lean. He’s also a blogger (http://www.royvanrijn.com) and you can follow him on Twitter (@royvanrijn).