On Wed, Mar 16, 2011 at 08:41:41AM +0900, Darren Cook wrote:
> On 2011-02-20 06:58, Petr Baudis wrote:
> > Another factor is time per game. Some people advise for very fast
> > games and/or limitation by playout. I do not think either is good
> > idea. Your idea is no good if the program beats gnugo in 5% more
> > cases, but takes 20% longer per move. ...
>
> That depends on your goal. If it only takes 20% longer to improve 5%
> against your reference opponent, and all your other ways (such as dumb
> scaling) require doubling the time to get the same improvement, then
> your idea can be thought of as Very Good.
You are right, I wrote it the wrong way - I meant a rather more common
situation, where the program beats gnugo in 5% cases with 20% extra
time, but performs worse with the same time allotment. RAVE scales very
well in itself, so in general only fast or rather significant
improvements seem to beat plain RAVE scaling.
--
Petr "Pasky" Baudis
Computer science education cannot make an expert programmer any more
than studying brushes and pigment can make an expert painter. --esr
_______________________________________________
Computer-go mailing list
[email protected]
http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
