AlphaZero is a computer program developed by artificial intelligence research company DeepMind to master the games of chess, shogi and go.
FactSnippet No. 845,768 |
AlphaZero is a computer program developed by artificial intelligence research company DeepMind to master the games of chess, shogi and go.
FactSnippet No. 845,768 |
DeepMind's paper on AlphaZero was published in the journal Science on 7 December 2018.
FactSnippet No. 845,769 |
AlphaZero is a more generalized variant of the AlphaGo Zero algorithm, and is able to play shogi and chess as well as Go.
FactSnippet No. 845,771 |
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.
FactSnippet No. 845,772 |
AlphaZero was trained on chess for a total of nine hours before the match.
FactSnippet No. 845,774 |
AlphaZero was trained on shogi for a total of two hours before the tournament.
FactSnippet No. 845,776 |
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 .
FactSnippet No. 845,777 |
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.
FactSnippet No. 845,778 |
AlphaZero inspired the computer chess community to develop Leela Chess Zero, using the same techniques as AlphaZero.
FactSnippet No. 845,779 |