On 9/14/07, Jason House <[EMAIL PROTECTED]> wrote:

>       // Note that variance of the estimate increases by (0.5 * fractional
> game)^2


I should say that the variance of "wins" increases by that amount.  The
estimate of winning percentage will be computed as wins / sims.  The
variance for that is (variance of wins variable) / sims^2.  In normal monte
carlo, each sim causes the variance of wins to increase by 0.5^2 for a total
of 0.5^2 * sims.  The final result is a variance of 0.5^2/sims.  Of course,
final computations typically use the standard deviation (the square root of
variance).  This gives the classical result of 0.25 / sqrt(sims)...  For the
same MCBR, the result is less for the same value of sims...
_______________________________________________
computer-go mailing list
[email protected]
http://www.computer-go.org/mailman/listinfo/computer-go/

Reply via email to