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

Planning with a Model: AlphaZero

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

AlphaZero paper peer-reviewed is available · Issue #2069 · leela-zero/leela-zero · GitHub

Planning with a Model: AlphaZero

AlphaZero

The future is here – AlphaZero learns chess

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

The future is here – AlphaZero learns chess

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

Checkmate for Traditional Chess? - Nekst-Online

A summary of the DeepMind's general reinforcement learning algorithm, AlphaZero, by Umer Hasan

The future is here – AlphaZero learns chess

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

AlphaGo/AlphaGoZero/AlphaZero/MuZero: Mastering games using progressively fewer priors