«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».
«The paper introduces AlphaGo Zero, the latest evolution of AlphaGo, the first computer program to defeat a world champion at the ancient Chinese game of Go. Zero is even more powerful and is arguably the strongest Go player in history. Previous versions of AlphaGo initially trained on thousands of human amateur and professional games to learn how to play Go. AlphaGo Zero skips this step and learns to play simply by playing games against itself, starting from completely random play».
« The progress AI is making is far beyond our imagination. […]. I believe the future belongs to AI. But AlphaGo will always be a cold machine. Compared to human, I can’t feel its passion and love for Go. Well, its passion might only come from overheating with the CPU running too fast ». – Ke Jie
Gu Li, as quoted by Hassabis, was a lot more philosophical about his loss to the new version of AlphaGo: « Together, humans and AI will soon uncover the deeper mysteries of Go. » Gu Li is referring to the fact that AlphaGo plays Go quite differently from humans, placing stones that completely confound human players at first—but upon further analysis these strategies become a « divine move. » While there’s almost no chance that a human will ever beat AlphaGo again, human players can still learn a lot about the game itself by watching the AI play.