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

Mastering the game of Go without human knowledge

Science Magazine - December 7, 2018 - A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

PDF) Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

How deep can an alpha zero chess think? - Quora

Planning with a Model: AlphaZero

Mastering the game of Go without human knowledge

Science Magazine - December 7, 2018 - A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

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

How deep can an alpha zero chess think? - Quora

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