AlphaZero

DeepMind program that mastered chess, shogi, and Go from the rules alone — the foundation on which AlphaTensor and AlphaEvolve build.

Specifications & Metrics

A computer program developed by artificial intelligence research company DeepMind to master the games of chess, shogi, and go.
It is a more generalized variant of the AlphaGo Zero algorithm, able to play shogi and chess as well as Go.
Its combination of deep reinforcement learning with Monte Carlo tree search is the template for later discovery agents such as AlphaTensor.