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

DeepMind's AlphaZero AI is the new champion in chess, shogi, and Go

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

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

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

When Alpha Zero is making seemingly bizarre moves in chess is it actually predicting what its opponent will do (calculating possibilities), or is it setting up its own attack/defense based on positional

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

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

Techmate: How AI rewrote the rules of chess

How AlphaZero Learns Chess

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

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