AlphaZero reached superhuman chess in 24 hours

According to the AlphaZero paper, “Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm,” the system started from random play with no domain knowledge except the rules of the game and achieved a superhuman level of play in chess and shogi within 24 hours, going on to defeat a world-champion program in each game.

Sources

Last verified June 6, 2026