Alpha Zero

Chess world changed forever today 6th of December. The latest version of Deeplearning AI Google Alphago that called Alpha Zero learnt chess in 24 hours then won against strongest chess engine Stockfish.
They played 100 games with 50 white 50 black and 1 min thinking per move.

Results: Alpha Zero won the match with 28 wins,72 draws and 0 lose!!!!

This AI starting from random play, and given no knowledge except the game rules, AlphaZero achieved within 24 hours a superhuman level of play in the games of chess by deeplearning reinforcement algorithm. Matthew Lai also is Canadian chess player who recently joined google deep mind team was part of this project. He developped a chess AI who could learn chess in 4 days and play like IM. It named Giraffe and it is open source, you can find more information about his AI here

Full paper about Alphazero

I will publish some of the games with analyze in this froum soon. Keep in touch!

Categories: Computer Chess

Leave a Reply

Your email address will not be published. Required fields are marked *