AlphaZero vs the Drawn Evaluation

It has been clear for a while that AlphaZero is a chess program unlike any other. Armed only with the rules of the game, it played "millions of games against itself via a process of trial and error called reinforcement learning. At first, it plays completely randomly, but over time the system learns

Frontiers AlphaZe∗∗: AlphaZero-like baselines for imperfect information games are surprisingly strong

How to build your own AlphaZero AI using Python and Keras, by David Foster, Applied Data Science

AlphaZero on Carlsen-Caruana Games 9-12

Electronics, Free Full-Text

Centipawns Suck - by Nate Solon - Zwischenzug

AlphaZero really is that good

The future is here – AlphaZero learns chess

Reimagining Chess with AlphaZero, February 2022

AlphaZero - Wikipedia

AlphaZero vs the Drawn Evaluation

From-scratch implementation of AlphaZero for Connect4, by Wee Tee Soh

Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess

Watson Book Review: Sadler, Doknjas, and Modern Engines