[Computer-go] 25x25 experiment

Aja Huang ajahuang at google.com
Tue Apr 28 09:26:45 PDT 2015


On Mon, Apr 27, 2015 at 2:12 PM, Detlef Schmicker <ds2 at physik.de> wrote:
>
> I did not do any playing tests without MC! On CGOS 13x13 I have two
> players (NiceGo) with 50 and 1k playouts running at the moment...


Maybe you can play your CNN of 44% prediction rate on KGS and compare it
with DCNNigo which is solid KGS 5k at the moment. Our 12-layer CNN
described in the paper is 600 Elo stronger than GnuGo, about 2k on KGS.

Aja
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://computer-go.org/pipermail/computer-go/attachments/20150428/2e416b4f/attachment.html>


More information about the Computer-go mailing list