Abstract
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.

https://arxiv.org/pdf/1712.01815.pdf
AlphaGo: Beats top human players in the world at Go, a feat most leading AI researchers still thought 10 years away
AlphaGo Zero: Beats AlphaGo at Go without ever learning from a human during training; 100% self-taught
Alpha Zero: Beats AlphaGo Zero at Go, leading chess software at chess, etc.

Whoa.