AI AlphaGo Zero started from scratch to become best at Chess, Go and Japanese Chess within hours

The AlphaZero program developed by Google and DeepMind took four hours of playing against itself to create chess knowledge beyond any human or other computer

AlphaZero: The AI from Google which mastered Chess in 4 hours, by University of Toronto Machine Intelligence Team

AlphaZero AI beats champion chess program after teaching itself in four hours, DeepMind

DeepMind Achieves Holy Grail: An AI That Can Master Games Like Chess and Go Without Human Help - IEEE Spectrum

AI AlphaGo Zero started from scratch to become best at Chess, Go and Japanese Chess within hours

AlphaGo beating Lee Sedol at Go is another milestone in AI - Idea to Value

One Giant Step for a Chess-Playing Machine - The New York Times

Why Artificial Intelligence Like AlphaZero Has Trouble With the Real World

AI-Powered Apps That'll School You in the Ways of Chess and Go

Is there an Open Source version of AlphaZero? (specifically, the generic game-learning tool, distinct from AlphaGo) - Quora

Deep Blue and AlphaZero: Comparing Giants of Artificial Intelligence, by Hein de Haan

Reinforcement learning explained