[Computer-go] Creating the playout NN

Petri Pitkanen petri.t.pitkanen at gmail.com
Sun Jun 12 00:51:37 PDT 2016

Would the expected improvement be reduced training time or improved

2016-06-11 23:06 GMT+03:00 Stefan Kaitschick <stefan.kaitschick at hamburg.de>:

> If I understood it right, the playout NN in AlphaGo was created by using
> the same training set as the one used for the large NN that is used in the
> tree. There would be an alternative though. I don't know if this is the
> best source, but here is one example: https://arxiv.org/pdf/1312.6184.pdf
> The idea is to teach a shallow NN to mimic the outputs of a deeper net.
> For one thing, this seems to give better results than direct training on
> the same set. But also, more importantly, this could be done after the
> large NN has been improved with selfplay.
> And after that, the selfplay could be restarted with the new playout NN.
> So it seems to me, there is real room for improvement here.
> Stefan
> _______________________________________________
> Computer-go mailing list
> Computer-go at computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://computer-go.org/pipermail/computer-go/attachments/20160612/cb5f1c95/attachment.html>

More information about the Computer-go mailing list