How AlphaGo Zero works
By Alvin Alexander. Last updated: December 12 2017
Tim Wheeler has a good tutorial on How AlphaGo Zero works.
alphago
AlphaZero generalized to learn more games by itself
By Alvin Alexander. Last updated: December 11 2017
From this Cornell University page, Google’s AlphaZero algorithm has been generalized to learn new games given only the game rules: “In this paper, we generalise this approach into a single AlphaZero algorithm that can achieve, tabula rasa, superhuman performance in many challenging domains.
AlphaGo Zero hardware configuration
By Alvin Alexander. Last updated: October 23 2017
I was curious what kind of hardware AlphaGo Zero uses, and I found this table on this Wikipedia page. The “TPU” references in that table refer to Tensor processing units.
The story of AlphaGo Zero
By Alvin Alexander. Last updated: October 23 2017
deepmind.com has a great new article titled, “AlphaGo Zero: Learning from scratch.”
AlphaGo Zero whips AlphaGo, 100-0
By Alvin Alexander. Last updated: October 18 2017
NPR reports that a new version of Google’s AlphaGo Zero software became a Go master by learning to play the game only by playing itself, i.e., only by using reinforcement learning (as opposed to supervised learning). Per the report in Nature.com, “AlphaGo Zero achieved superhuman performance, winning 100–0 against the previously published, champion-defeating AlphaGo.”
AlphaGo, and managing risk
By Alvin Alexander. Last updated: June 3 2016
With all the interest in AI, AlphaGo, the game of Go, and the human (Lee Sedol), I thought this image was a good description of AlphaGo’s strategy. It comes from this gogameguru.com page.