On Fri, Oct 09, 2015 at 12:22:36PM +0800, Cai Gengyang wrote:
> I just defeated Hirabot12(2d) by resignation. This bot is not very strong,
> prone to making huge calculation errors in life-and-death situations ..
Which bot isn't? :-)
Petr Baudis
2 Cents from a non-programmer;
>> 1. Limit on processor power?
From my computer chess background I can only recommend not to do
such a thing. The only consequence might be slower progress in computer
go in general. This would conflict with my longterm hopes:
* I want to see a bot win against a
Hi Nick,
I'd like no limit. Restriction will lose a chance of massive
computer's programming. But one thread limit tournament
once a year may be interesting.
I like (2), and (3) is nice, but I'm already happy with your reports!
Regards,
Hiroshi Yamashita
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Hi,
all the guys which are using caffe for DCNN:
If you want to see how bad a bot is playing in CPU mode: have a look
at the last results of NiceGo :)
Obviously the caffe library changed between December 2014 and August
2015 an now every thread
