[Computer-go] CNN for winrate and territory

Álvaro Begué alvaro.begue at gmail.com
Sun Feb 8 02:43:41 PST 2015


What network architecture did you use? Can you give us some details?



On Sun, Feb 8, 2015 at 5:22 AM, Detlef Schmicker <ds2 at physik.de> wrote:

>  Hi,
>
> I am working on a CNN for winrate and territory:
>
> approach:
>  - input 2 layers for b and w stones
>  - 1. output: 1 layer territory (0.0 for owned by white, 1.0 for owned by
> black (because I missed TANH in the first place I used SIGMOID))
>  - 2. output: label for -60 to +60 territory leading by black
> the loss of both outputs is trained
>
> the idea is, that this way I do not have to put komi into input and make
> the winrate from the statistics of the trained label:
>
> e.g. komi 6.5: I sum the probabilites from +7 to +60 and get something
> like a winrate
>
> I trained with 800000 positions with territory information through 500
> playouts from oakfoam, which I symmetrized by the 8  transformation leading
> to >6000000 positions. (It is expensive to produce the positions due to the
> playouts....)
>
> The layers are the same as the large network from Christopher Clark
> <http://arxiv.org/find/cs/1/au:+Clark_C/0/1/0/all/0/1>, Amos Storkey
> <http://arxiv.org/find/cs/1/au:+Storkey_A/0/1/0/all/0/1> :
> http://arxiv.org/abs/1412.3409
>
>
> I get reasonable territory predictions from this network (compared to 500
> playouts of oakfoam), the winrates seems to be overestimated. But anyway,
> it looks as it is worth to do some more work on it.
>
> The idea is, I can do the equivalent of lets say 1000 playouts with a call
> to the CNN for the cost of 2 playouts some time...
>
>
> Now I try to do a soft turnover from conventional playouts to CNN
> predicted winrates within the framework of MC.
>
> I do have some ideas, but I am not happy with them.
>
> Maybe you have better ones :)
>
>
> Thanks a lot
>
> Detlef
>
>
> _______________________________________________
> 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/20150208/55cc5ecc/attachment.html>


More information about the Computer-go mailing list