12 Facts About AlphaZero

AlphaZero is a computer program developed by artificial intelligence research company DeepMind to master the games of chess, shogi and go.

DeepMind's paper on AlphaZero was published in the journal Science on 7 December 2018.

In 2019 DeepMind published a new paper detailing MuZero, a new algorithm able to generalise AlphaZero's work, playing both Atari and board games without knowledge of the rules or representations of the game.

AlphaZero is a more generalized variant of the AlphaGo Zero algorithm, and is able to play shogi and chess as well as Go.

In parallel, the in-training AlphaZero was periodically matched against its benchmark in brief one-second-per-move games to determine how well the training was progressing.

Related searches

DeepMind judged that AlphaZero's performance exceeded the benchmark after around four hours of training for Stockfish, two hours for elmo, and eight hours for AlphaGo Zero.

AlphaZero was trained on chess for a total of nine hours before the match.

In 100 games from the normal starting position, AlphaZero won 25 games as White, won 3 as Black, and drew the remaining 72.

AlphaZero was trained on shogi for a total of two hours before the tournament.

However, some grandmasters, such as Hikaru Nakamura and Komodo developer Larry Kaufman, downplayed AlphaZero's victory, arguing that the match would have been closer if the programs had access to an opening database .

Motohiro Isozaki, the author of YaneuraOu, noted that although AlphaZero did comprehensively beat elmo, the rating of AlphaZero in shogi stopped growing at a point which is at most 100~200 higher than elmo.

AlphaZero inspired the computer chess community to develop Leela Chess Zero, using the same techniques as AlphaZero.