Re: [Computer-go] KGS bot tournaments: structure

2016-05-11 Thread Nick Wedd
LeelaBot now has "Ranked Robot" status. It will still need to play some rated games to achieve a rank. I propose to run the June KGS bot tournament (9x9) in two divisions. One division will be McMahon, with entry restricted to programs that have "Ranked Robot" status *and* are able to beat GNU Go;

Re: [Computer-go] KGS bot tournaments: structure

2016-05-10 Thread Hideki Kato
Gian-Carlo Pascutto: <5731dc19.2020...@sjeng.org>: >On 10-05-16 11:23, Hideki Kato wrote: > >> CGOS is better place for those lower programs, isn't it? > >Not really, the pool of opponents is smaller and contains no humans. It >sort of depends on what the goal of the author is. Even if she's onl

Re: [Computer-go] KGS bot tournaments: structure

2016-05-10 Thread Gian-Carlo Pascutto
On 10-05-16 11:23, Hideki Kato wrote: > CGOS is better place for those lower programs, isn't it? Not really, the pool of opponents is smaller and contains no humans. It sort of depends on what the goal of the author is. Even if she's only interested in measuring vs other computer opponents, a K

Re: [Computer-go] KGS bot tournaments: structure

2016-05-10 Thread Petr Baudis
Hi! On Tue, May 10, 2016 at 08:15:16AM +0100, Nick Wedd wrote: > A problem with McMahon is that the scheduling software (a module of the KGS > server, which I have no control over) uses the ratings assigned by KGS, and > many bots do not have such ratings. I don't think it's reasonable to > requ

Re: [Computer-go] KGS bot tournaments: structure

2016-05-10 Thread Hideki Kato
CGOS is better place for those lower programs, isn't it? I'm not against creating lower division, just wonder if it's really necessary. Recently it's easier to implement "large patterns" which is necessary to beat GNU Go on 19x19 using DCNN than Remi's B-T model and so most programs could qu

Re: [Computer-go] KGS bot tournaments: structure

2016-05-10 Thread Gonçalo Mendes Ferreira
Knowing full well this adds nothing to the discussion -- I've been working on improvements of Matilda that have it with win rates of 95% against the version that played sunday. :) I'm very much looking forward to a rematch with Iomrascálaí. Gonçalo On 10/05/2016 08:45, Urban Hafner wrote: > That

Re: [Computer-go] KGS bot tournaments: structure

2016-05-10 Thread Urban Hafner
That sounds like a good compromise to me. And the lower devision would hopefully encourage other participants with weaker bots so that Iomrascálaí and matilda don’t feel so alone. ;) Urban On Tue, May 10, 2016 at 9:15 AM, Nick Wedd wrote: > At present, KGS bot tournaments are run as Swiss tourn