Hacker News Reader

Is AlphaGo Zero the first Go program without special code to read ladders? I'm curious how a pure neural net can read them, given how non-local they are.

View on HN

The concept of locality is nothing but a human weakness in Go, the best AI must read the whole board with every move.

EDIT: From the paper: "Surprisingly, shicho (“ladder” capture sequences that may span the whole board) – one of the first elements of Go knowledge learned by humans – were only understood by AlphaGo Zero much later in training" I'm surprised by the author's use of the word "Surprisingly" here.

>Surprisingly, shicho (‘ladder’ capture sequences that may span the whole board)—one of the first elements of Go knowledge learned by humans—were only understood by AlphaGo Zero much later in training. [0]

[0] https://www.nature.com/nature/journal/v550/n7676/full/nature...

AlphaGo is still based around layers of 3×3 local convolutions.

That represents a strong assumption about locality in the network design. I would expect AlphaGo to perform poorly on the game "Go with the vertices randomly permuted".

Well they didn't use inception. If their inception units have, say, a 7x7 conv, then ladders will probably be found much earlier.

Reply on news.ycombinator.com