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

Monte-Carlo Graph Search for AlphaZero – arXiv Vanity

Google's AlphaZero Destroys Stockfish In 100-Game Match

AlphaZero vs AlphaZero

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

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

AlphaZero/Kramnik: More variants

Understanding AlphaZero Neural Network's SuperHuman Chess Ability - MarkTechPost

AlphaZero SpringerLink

AlphaZero

Acquisition of chess knowledge in AlphaZero

Mastering chess and shogi by self-play with a general reinforcement learning algorithm

AlphaZero paper discussion (Mastering Go, Chess, and Shogi) • Life In 19x19

Lessons From AlphaZero (part 4): Improving the Training Target, by Vish (Ishaya) Abrams, Oracle Developers

Are Self-Learning Game Players Truly Intelligent?, by Dave Whipp