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

How to Solve Board Games. AlphaZero is a generic algorithm that…, by Mark Saroufim

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

DeepMind's AlphaZero crushes chess

Simple Alpha Zero

AlphaZero Explained · On AI

PDF] Monte-Carlo Graph Search for AlphaZero

Towards Explainable AI for Chess - by Nate Solon

AlphaZero/Kramnik: More variants

Understanding AlphaZero Neural Network's SuperHuman Chess Ability - MarkTechPost

Does the neural net of AlphaZero only evaluate the score of a given chess position or does it do something else? - Quora

Win-Draw-Loss evaluation - Leela Chess Zero

AlphaZero vs the Drawn Evaluation

AlphaZero really is that good

AlphaZero and the Losing Future of Human Wisdom

Inside the (deep) mind of AlphaZero