AlphaZero AI Learns Chess in Four Hours to Beat World’s Best Chess Program

Chess Set

AlphaZero, a game playing Artificial Intelligence created by Google’s DeepMind, has beaten Stockfish 8, that was until now the world’s best chess-playing computer program.

Here is the abstract from the none-peer-reviewed scientific research paper published on Cornell University Library’s arXiv.

The game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination of sophisticated search techniques, domain-specific adaptations, and handcrafted evaluation functions that have been refined by human experts over several decades. In contrast, the AlphaGo Zero program recently achieved superhuman performance in the game of Go, by tabula rasa reinforcement learning from games of self-play. In this paper, we generalise this approach into a single AlphaZero algorithm that can achieve, tabula rasa, superhuman performance in many challenging domains. Starting from random play, and given no domain knowledge except the game rules, AlphaZero achieved within 24 hours a superhuman level of play in the games of chess and shogi (Japanese chess) as well as Go, and convincingly defeated a world-champion program in each case.

– Your Joyful Benefactor
 Image Source: Alan Light  CC BY-SA 3.0

Leave a Reply

Your email address will not be published.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