Hideki,
> An important difference from actual game is
> the search tree, which is very big in real, long-time setting
> game. One possible interpretation is, Zen read in deep and
> found the (wrong) seki, which would lead W a sure win and so,
> played R18 toward this (again wrong!) winning
>
>
> RATHER OFTEN the outcome was a score where both sides thought
> to have won. In the 5.5/7.5 komi example from Go this means that
> outcomes with +6 or +7 points for Black on the board would occur
> often.
>
>
It looks like this issue is serious again was a factor in today's game
against
Hideki,
Using this for Japanese and 6.5, there will be some
>> error in close games. We knew this issue and thought such
>> chances would be so small that postponed correcting (not so
>> easy).
>>
>
But how would you fix it? Isn't that you'd need to retrain your value
network from the scratch?
ells you a winning percentage for a green player. Does it
make sense?
Best,
Paweł
> I would be afraid to invest an enormous amount of time just to learn,
> that you have to open differently in reverse komi games :)
>
>
> Detlef
>
> Am 05.01.2017 um 10:50 schrieb Paweł Mor
2017-01-04 21:07 GMT+01:00 David Ongaro :
>
> [...]So my question is: is it possible to have reverse Komi games by
> feeding the value network with reverse colors?
>
In the paper from Nature (subsection "Features for policy/value network"),
authors state:
*the stone
Ingo,
> So, do you want to say that "Master" might be AlphaGo?
> From the disucssion I thought that "Master" was a chinese bot.
>
> I'd put all my money it's AlphaGo. They were certified by Korean Baduk
Association, hence a Korean flag when playing on Tygem. My personal belief
is that these
>
> Hi,
>
> The grey box shows the list of 30 games played by
> the "Master bot. All these games were won by the bot!
>
>
There have been another 8 games on Foxwq server:
Game 31: black2012 = Li Qincheng
Game 32: 星宿老仙 = Gu Li
Game 33: 星宿老仙 = Gu Li
Game 34: 我想静静了 = Dang Yifei
Game 35: 若水云寒 =
Dear Aja,
On the _official_ website of Korean Baduk Association, specifically on
their schedule (http://www.baduk.or.kr/info/schedule.asp), they announce
what is called "Google event match(es) in October. Looks like 3 matches, 3
rounds per match. Dates are as follows:
10/03 1st match 1st Round
2016-05-27 22:10 GMT+02:00 daniel rich :
> Anyone have any idea how well crazy stone does in Wine? Or if Mac/Linux
> support will happen?
>
On Mac it works pretty well with Crossover 15 (https://www.codeweavers.com)
Not everything is displayed properly (buttons are black)
Hi,
> It's fun to hear the pro making comments as she goes. I had hoped for a
> better game, though.
> Any comments from the CS camp?
>
> I'm not from CrazyStone Team but a happy user of CS Deep Learning.
I analyzed the game (30 000 playouts per move) with the version
commercially available and
Hi,
Here are some thoughts (translated into English), given by Lee Sedol on all
five matches: http://badukinkorea.tumblr.com
Dear Aja/Deepmind, would we see something similar from your point of view?
It's been a month since the match, i think many people really waiting for
any news/plans for
Hi,
>
> Final result
> 1st Zen
> 2nd darkforest
> 3rd CrazyStone
> 4th Aya
>
>
Are there any games available? (SGFs)?
Regards,
Paweł
>
> - Original Message - From: ""Ingo Althöfer"" <3-hirn-ver...@gmx.de
> >
> To:
> Sent: Sunday, March 20, 2016 4:04 PM
>
12 matches
Mail list logo