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

Acquisition of chess knowledge in AlphaZero

Techmate: How AI rewrote the rules of chess

Top dog: AlphaZero / AlphaStar. AlphaZero and AlphaStar are two AIs…, by Lois Rosenbloom

How AlphaZero Learns Chess?. DeepMind and Google Brain researchers…, by Gayan Samuditha, Expo-MAS

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

Checkmate, humans? Google's AI programme takes just 4 hours to master chess - Hindustan Times

Electronics, Free Full-Text

DeepMind's AlphaZero beats state-of-the-art chess and shogi game engines

The Case for AlphaZero: Openings and Pawn Progression — The Yale Logos

How the Artificial Intelligence Program AlphaZero Mastered Its Games