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

Training AlphaZero for 700,000 steps. Elo ratings were computed from

Simple Alpha Zero

AlphaZero vs Stockfish 8: A Landmark Battle of Human and Artificial Intelligence in Chess, by David Georgyan

Stockfish (Computer) vs AlphaZero (Computer) (2018)

AlphaZero - Notes on AI

AlphaZero/Kramnik: More variants

AlphaZero vs the Drawn Evaluation

AlphaZero really is that good

AlphaZero vs AlphaZero

DeepMind's AlphaZero crushes chess

Google's AlphaZero Destroys Stockfish In 100-Game Match

Acquisition of chess knowledge in AlphaZero

Win-Draw-Loss evaluation - Leela Chess Zero