[Computer-go] Testing against a started game

Don Dailey dailey.don at gmail.com
Mon Sep 3 10:18:46 PDT 2012


I wonder if it would come down to simply whether the bot can find the right
first move?

On Mon, Sep 3, 2012 at 1:17 PM, Nick Wedd <nick at maproom.co.uk> wrote:

> On 03/09/2012 17:45, Xavier Combelle wrote:
>
>> It seems that all the computer go experiments are made in comparing
>> win/rates from an empty board. Would make sense to start from a game
>> position especially the ones which are difficult for the current bots ?
>>
>
> Ɓukasz Lew was discussing the same thing yesterday.  I guess you
> already know this - but if you don't, I suggest you talk to him
> about it.
>
> Nick
>
>> ______________________________**_________________
>> Computer-go mailing list
>> Computer-go at dvandva.org
>> http://dvandva.org/cgi-bin/**mailman/listinfo/computer-go<http://dvandva.org/cgi-bin/mailman/listinfo/computer-go>
>>
>>
>
> --
> Nick Wedd
> nick at maproom.co.uk
> ______________________________**_________________
> Computer-go mailing list
> Computer-go at dvandva.org
> http://dvandva.org/cgi-bin/**mailman/listinfo/computer-go<http://dvandva.org/cgi-bin/mailman/listinfo/computer-go>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://computer-go.org/pipermail/computer-go/attachments/20120903/4fc9b9f0/attachment.html>


More information about the Computer-go mailing list