AlphaZero

Click the lanes or press Next change to see a moment.

Sources

1. ArticleMastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
2. ArticleA general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

built by:

• DeepMind

  Sources: Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm, A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

defeated:

• Stockfish5 Dec 2017

  100-game match: 28 wins, 72 draws.

  Sources: Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm, A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

Appears in3 items

• 
  Chess: From Chaturanga to AlphaZero3 items
  • The computer eraMar 1950
  • AlphaZero teaches itself chess5 Dec 2017
  • AlphaZero’s results appear in Science7 Dec 2018