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

Simple Alpha Zero

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

Checkmate for Traditional Chess? - Nekst-Online

AlphaZero

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

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

AlphaZero really is that good

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

Planning with a Model: AlphaZero

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

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