Hello Tony,
I'm just speaking for myself here, but I suspect you may not get the answers
you are looking for, because you're not asking the right questions.
I get the impression that the situation is similar to this scenario:
A young guy with a surf board and a hawai shirt turns up at
basecamp on mount Everest and says:
"Hey dudes, what's up!
This morning I had this wonderful idea: I wanna climb the mount
Everest!
So here I am, and I even brought my hiking shoes!
But can anyone give me directions to the nearest McDonalds, cuz
I'm starving."
Everybody in the tent stares at him speechlessy.
I may be wrong, but that's my impression.
I'm not even sure whether if I myself should be here at basecamp, even though I
am a 4d in Go and even though I have 25 years of programming experience in a
couple of different languages (including the last 8 years as a fulltime
professional developer.)
It's only logical that ever since I've learned Go 20 years ago I've had a
special interest in computer-go and I spent some time over the years attempting
to build a strong go playing program myself (although not nearly as much time
as some others here).
I'm a mountaineer, but climbing the mount Everest is something else. I feel a
bit like a rooky between all the seasoned mountaineers hanging around here at
the Everest basecamp. Most of the time I keep my mouth shut when one of them is
talking, because I'm a bit apprehensive that I might say something that is
utterly obvious to the others or even outright stupid.
And then this guy turns up in his hawai shirt.
I hope you don't feel offended. Indeed you took up a wonderful endeavour, but I
sense that you're not quite ready to go for the summit today.
Best Regards,
Dave
________________________________
Van: [EMAIL PROTECTED] namens tony tang
Verzonden: do 13-11-2008 22:03
Aan: go mailing list
Onderwerp: RE: [computer-go] Monte carlo play
Thanks Darren,
After reading a couple of interesting papers on this field I am applying
pattern matching to limit the number of possibilities of the monte carlo tree
(on 19x19 it appears to take a day to play).
I was wondering if you could comment on weather my following concept is right
on the evalution part.
The possible patterns for the current situation are passed to a class where
self play begins. Each different pattern runs on a instance, and at the end the
results are written into a file. The game tree will be constructed using the
stats from the file.
Thanks again
Tony
> Date: Wed, 12 Nov 2008 10:34:21 +0900
> From: [EMAIL PROTECTED]
> To: [email protected]
> Subject: Re: [computer-go] Monte carlo play
>
> > I am new to programming go, could some one explain to me how a monte
> > carlo based evalution manages to play random games by itself? ie:
> > who/what is the oppoent which supplies the opposing moves which
> > allows another move to be randomly played after making the initial
>
> It is self-play, so both players are random.
>
> I'm not aware of any programs that use different playout strategies for
> black/white, though it has been briefly mentioned before on this list,
> and I personally think it might be interesting as a way of discovering
> and more accurately evaluating the imbalances present in most go
> positions (i.e. usually one side has more strength and one side has more
> territory, and so to correctly understand the position one side has to
> play aggressive moves and the other has to play defensive moves).
>
> > move at the root. I am implementing in java, is there a
> > package/framework which allows me to train my software.
>
> This page, recently started by Eric Marchand, might be a good starting
> place:
> http://ricoh51.free.fr/go/engineeng.htm
>
> Darren
>
>
> --
> Darren Cook, Software Researcher/Developer
> http://dcook.org/mlsn/ (English-Japanese-German-Chinese-Arabic
> open source dictionary/semantic network)
> http://dcook.org/work/ (About me and my work)
> http://dcook.org/blogs.html (My blogs and articles)
> _______________________________________________
> computer-go mailing list
> [email protected]
> http://www.computer-go.org/mailman/listinfo/computer-go/
________________________________
Get the best wallpapers on the Web - FREE. Click here!
<http://wallpapers.msn.com/?ocid=[B001MSN42A0716B]>
_______________________________________________
computer-go mailing list
[email protected]
http://www.computer-go.org/mailman/listinfo/computer-go/
