Hi everyone,
long time reader, sometimes poster.
I gave a talk last week at Full Stack Fest about Computer Go and the
advances that AlphaGo brought (but about MCTS as well of course). It's a
40mins presentation so I had to cut a lot. I think it's a good
introduction and the talk was well
Variations drawn from AlphaGo are usually indicated in the English
translation by phrases such as "AlphaGo believes...", or reactions such as
the pros' "approval" or "doubt" as mentioned by Steven. Some variations
were also created by Fan Hui, Gu Li, and Zhou Ruiyang in order to
investigate,
My interpretation is that all variations are from AlphaGo, whereas the
human pros are just weighing in on those. Hence you will see the pros
"approve of this variation" or "express doubts" about it.
On Thu, Sep 15, 2016 at 11:04 AM, Darren Cook wrote:
> > DeepMind published
> DeepMind published AlphaGo's selfplay 3 games with comment.
I've just been playing through the AlphaGo-Lee first game. When it shows
a variation, is this what AlphaGo was expecting, i.e. its prime
variation? Or is the follow-up "just" the opinion of the pro commentators?
(E.g. game 1, move 13,
Hi Paweł,
On Thu, Sep 15, 2016 at 9:12 AM, Paweł Morawiecki <
pawel.morawie...@gmail.com> wrote:
> 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
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