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

Planning with a Model: AlphaZero

How deep can an alpha zero chess think? - Quora

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

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

AlphaZero really is that good

How did Google's AlphaZero beat the world's best chess computer?

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