kferg.dev

[ go ]

In chapter 7 of my (+ Max’s) book, Deep Learning and the Game of Go, there is an example that collects a sample of human go game records, encodes them, and trains a small neural network. This is followed by a sample output showing it achieving over 90% training set accuracy. Several readers have reported that they could not reproduce this. You’re not crazy! There is a mismatch between the code listing in the book and the results listing.
I wrote a book! (Please buy it) I’ve been interested in game AI ever since I was a kid, and I’ve played go off-and-on since I was a teenager. So when the AlphaGo news hit, I was obsessed; I stayed up late to watch the games against Lee Sedol, scrutinized the game records, and pored over all the papers. It was my pal Max’s idea to turn our hobby projects into a book.
BadukEllington is my go AI, which you can play on the Online Go Server. At fast settings, it plays at a strong kyu level. At one point, it was among the top 10 most popular bots on OGS! (Maybe it still is; there are more bots on OGS these days though) Did I mention I wrote an entire book about how this works? (Please buy my book) Go? What?