[Computer-go] Creating the playout NN

Stefan Kaitschick skaitschick at gmail.com
Mon Jun 13 05:58:49 PDT 2016


>
> BTW, by improvement, I don't mean higher Go playing skill...I mean
> appearing close to the same level of Go playing skill _per_ _move_ with far
> less computational cost. It's the total game outcomes that will fall.
>
>
 For the playouts, you always need a relatively inexpensive computation.
Because for every invocation of the main NN in the tree, you need several
hundred cheaper calls in the playout.
So it will have to be orders of magnitude faster. Surely, replacing a crude
fast NN with a slightly less crude fast NN would be beneficial.
I don't know if other bots besides AlphaGo are already utilizing the
selfplay improvement. But when they do, it will be helpful there too.
Because the added knowledge of the main NN can be transferred down to the
playout NN.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://computer-go.org/pipermail/computer-go/attachments/20160613/dd167c9c/attachment.html>


More information about the Computer-go mailing list