Re: [Computer-go] Polygames: Improved Zero Learning

Yep, global pooling is also how KataGo already handles multiple board sizes with a single model. Convolution weights don't care about board size at all since the filter dimensions have no dependence on it, so the only issue is if you're using things like fully-connected layers, and those are often

[Computer-go] Polygames: Improved Zero Learning

Hi, I have just noticed this has recently been released: github: https://github.com/facebookincubator/polygames paper: https://arxiv.org/abs/2001.09832 Rémi ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinf