Re: [computer-go] Computer Go tournament at EGF

[steve uurtamo <apoxonpoo@xxxxxxxxx>]

> Just for perspective, physics simulations I have
> done in the past
> took a month of 24x7 run time to generate their data
> and another
> month of 24x7 run time to reduce that data down to a
> single
> number. I seem to spend my efforts out at the edge
> of what people
> are willing to wait for computers to do.

just for perspective, if those simulations could have
been done by someone else (and generated functionally
equivalent data) in 2 days, the 2 day solution would
likely be considered preferable.

computer go tournaments are for the computer 
programmers who enter them, and their patience is
what matters.  at this early stage in computer go
development, you'd likely need to show a *very large*
improvement over existing programs in order to get
many people to be willing to wait a significantly
longer period of time for a game to finish.

if you want to find out how well your code does
against actual *humans*, of course, you'll need to
use time constraints that the actual humans playing
against your code will be likely to play within.

code that already does this has the additional
advantage of having its strength more easily
measured (on kgs, for instance.).

s.


		
__________________________________ 
Do you Yahoo!? 
Yahoo! Mail - now with 250MB free storage. Learn more.
http://info.mail.yahoo.com/mail_250
_______________________________________________
computer-go mailing list
computer-go@xxxxxxxxxxxxxxxxx
http://www.computer-go.org/mailman/listinfo/computer-go/