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

AI - Last Year Progress (2018-2019)

Mastering the game of Go without human knowledge

AlphaGo Zero Explained

Are there any ways to calculate the rating difference between AlphaGo Zero and Leela Zero? · Issue #2576 · leela-zero/leela-zero · GitHub

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

Planning with a Model: AlphaZero

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

The future is here – AlphaZero learns chess

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

Figure 1 from Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm – arXiv Vanity

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

Mastering the game of Go without human knowledge