DeepMind's AlphaZero algorithm taught itself to play Go, chess, and shogi with superhuman performance and then beat state-of-the-art programs specializing in each game. The ability of AlphaZero to adapt to various game rules is a notable step toward achieving a general game-playing system.

See the source article by following the link below:
DeepMind's AlphaZero algorithm taught itself to play Go, chess, and shogi with superhuman performance and then beat state-of-the-art programs specializing in each game. The ability of AlphaZero to adapt to various game rules is a notable step toward achieving a general game-playing system.