DeepMind's AlphaGo mastered chess in its spare time
by Volker Weber
What makes DeepMind’s latest accomplishment is noteworthy is the fact that it conquered three games with very different rule sets using a single AI. AlphaGo Zero, the latest version of AlphaGo, began “tabula rasa” without any prior knowledge or understanding of Go, shogi or chess, but the AI managed to achieve “superhuman performance” in all three games with stunning speed. IBM spent more than 10 years perfecting Deep Blue before it successfully mastered chess. AlphaGo Zero did it in just 24 hours.
Now put all of that into a computer the size of a smartphone and we are toast.
Comments
A rack with four Google 2nd gen TPUs is about 150x110x100 mm, so this won't take too long, if Murphy's Law still applies - just assuming the initial training of the neural network can be done in advance.
Axel von Dielingen, 2017-12-08