Using "Many" plies early in the game gets you results that don't have
much use at all.

If you think about it -- say you're choosing between opening with A or
with B.  And so you open with A, and then assign random racks to the
end of the game to see who wins, and then you do the same with B...
and repeat this.  Well, there's so much randomness in the whole
remainder of the game, that it will take millions and millions of
iterations before you have a meaningful sample of the possible
combinations between here and the end of the game.  Whereas, if you go
two or three moves out, there are many fewer combinations, and you can
draw a meaningful conclusion about the state of the game in a couple
moves' time with hundreds or thousands of iterations, not millions.

Interesting side question -- has anyone calculated how many iterations
you would need for a "Many" sim on the opening move to be
statistically meaningful to whatever given degree?  Has anyone run
sims for that long?

Chris Lipe

On Mon, Nov 24, 2008 at 11:29 AM, Phil Robertshaw
<[EMAIL PROTECTED]> wrote:
> I don't sim games as often as I should. I've been experimenting with 4-
> ply sims, between 500 and 1000 iterations. Wondering, though, if I
> should use 'many' plies, which takes considerably longer. What is the
> general combination of plies and iterations which most people use? I
> find 4 plies generally gives a pretty good indication of the best
> moves, but often disagree with the results.
>
> Phil R
>
> 

Reply via email to