DeepMind, Google Brain & World Chess Champion Explore How AlphaZero Learns Chess Knowledge

Deep neural networks are known to learn opaque, uninterpretable representations that lie beyond the grasp of human understanding. As such, from both scientific and practical viewpoints, it is intriguing to explore what is actually being learned and how in the case of superhuman self-taught neural network agents such as AlphaZero. In the new paper Acquisition

AI Taught Itself to Be the Best Chess Player in the World—What's Next? - The Ringer

Acquisition of chess knowledge in AlphaZero

Google AI teaches itself 'superhuman' chess skills in four hours – Sophos News

Google's New AI Is a Master of Games, but How Does It Compare to the Human Mind?, Innovation

Mastering the game of Go without human knowledge

What are the chances that AlphaZero will enter official competitions with other chess engines (e.g. TCEC)? - Quora

DeepMind's AlphaZero algorithm taught itself to play Go, chess, and shogi with superhuman performance and then beat state-of-the-art programs specializing in each game. The ability of AlphaZero to adapt to various game

AlphaZero Chess: How It Works, What Sets It Apart, and What It Can Tell Us, by Maxim Khovanskiy

DeepMind, Google Brain & World Chess Champion Explore How AlphaZero Learns Chess Knowledge

Acquisition of Chess Knowledge in AlphaZero – arXiv Vanity