David Doshay: <[email protected]>:
>I am unable to view those Google book pages. It says that either the page is
>unavailable for
>viewing or I have reached my viewing limit.
>
>Please include more info, and perhaps I can find the info in the Computer Go
>Newsletter. I
>subscribed way back when it was being published, although I lent a few out and
>they did not
>return.
--- The paragraph ---
Go is a deterministic game, but the large branching factor makes it
challeging. The key issues and carly literature in computer Go are
summerized by Bouzy and Cazenave (2001) and Mueller (2002). Up to 1997
there were no competent Go programs. Now the best programs play most
of their moves at the master level: the only problems is that over
the course of a game they usually make at least one serious blunder
that allows a strong opponent to win. Whereas alpha-beta search
reigns in most games, many recent Go programs have adopted Monte
Carlo method based on the UCT (upper confidence bounds on trees)
scheme (Kocsis and Szepesvari, 2006). The strongest Go program
as of 2009 is Gelly and Silver's MoGo (Wang and Gelly, 2007;
Gelly and Silver, 2008). In August 2008, MoGo scored a surprising
win against top professional Myungwan Kim, albeit with MoGo
receiving a handicap of nine stones (about the equivalent of a queen
handicap in chess). Kim estimated MoGo's strength at 2-3 dan, the
log end of advanced amateur. For this match, MoGo was run on an
800-processor 15 teraflop supercomputer (1000 times Deep Blue). A
few weeks later, MoGo, with only a five-stone handicap, won against
a 6-dan professional. In the 9 x 9 form of Go, MoGo is at
approximately the 1-dan professional level. Rapid advances are
likely as experimentation continues with new forms of Monte Carlo
search. The Computer Go Newsletter, published by the Computer Go
Association, describes current development.
--- end of quote ---
Notes: "challeging" in the second line is as of the original.
"Mueller" in the third line is M{\"u}ller (using an umlaut). Some
words are italic. Since the original is scaned picture, above quote
may have some errors, sigh :).
Hideki
>Cheers,
>David
>
>
>
>On 15, Feb 2011, at 12:45 AM, Hideki Kato wrote:
>
>> In a famous text book of AI, "Artificial Intelligence: A Modern
>> Approach (3rd ed.) by Stuart Russell and Perter Norvig", there is a
>> description about recent development in computer Go (the link
>> below).
>>
>http://books.google.co.jp/books?id=8jZBksh-bUMC&pg=PA194&lpg=PA194&dq=Artificial+Intelligence:+A+Modern+Approach+mogo&source=bl&ots=dohwAgm6t5&sig=qVQkna6YrH47mYngB6e3GgZU9C0&hl=en&ei=3TdaTb6kHIemuQOErfStDQ&sa=X&oi=book_result&ct=result&resnum=4&ved=0CC8Q6AEwAw#v=onepage&q&f=false
>>
>> At the end of the paragraph for "Go" (end of page 194 to the first
>> line of page 195),
>>> The Computer Go Newsletter, published by the Computer Go Association,
>>> describes current developments.
>>
>> I've Googled the newsletter and the association and found some old
>> issues (1986 - 1991) of the newsletter at <http://www.daogo.org/> but
>> nothing new. Does anyone know some about the newsletter and the
>> association, relevant to the description in the text book?
>>
>> Hideki
>> --
>> Hideki Kato <mailto:[email protected]>
>> _______________________________________________
>> Computer-go mailing list
>> [email protected]
>> http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
>
>_______________________________________________
>Computer-go mailing list
>[email protected]
>http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
--
Hideki Kato <mailto:[email protected]>
_______________________________________________
Computer-go mailing list
[email protected]
http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
