I have no idea what you're talking about. I meant to respond to Don's email, not yours. Sorry for the confusion.
On Sat, Jun 18, 2011 at 1:23 AM, "Ingo Althöfer" <[email protected]>wrote: > > Datum: Fri, 17 Jun 2011 18:22:32 -0400 > > Von: Michael Williams <[email protected]> > > > > If we are only looking for the shape of the curve, then maybe each > > datapoint does not need to be as precise as +/- 10 ELO. > > > Sorry, but your comment missed the point. > My strange result ( MC(4) performs clearly better against MC(1) > than expected after knowing the quota for MC(4)-vs-(MC(2) and > MC(2)-vs-MC(1) ) is NOT due to fluctuations of small sample size. > > IT IS A PHENOMENON. > > Ingo. > > > > > I am not a go programmer, but in experiments with very > > > simple model games I found the following phenomenon, > > > when looking at the "basic" Monte Carlo algorithm in > > > 3 levels: MC(1), MC(2), MC(4). > > > [Here MC(k) is the version which makes k random games for each > candidate > > > move.] > > > > > > I found several cases (more than 30 % of the games analysed this way) > > > with the following phenomenon: > > > Elo difference between MC(1) and MC(2) = k(1,2) > > > Elo difference between MC(2) and MC(4) = k(2,4). > > > Elo difference between MC(1) and MC(4) > k(1,2) + k(2,4) > > > > > > The games under investigation were so simple that I was able to run > > > 100,000 matches in selfplay (or even more), and the inequality above > > > ( k(1,4) > k(1,2) + k(2,4) ) was statistically significant. > > > > > > Ingo > > > -- > NEU: FreePhone - kostenlos mobil telefonieren! > Jetzt informieren: http://www.gmx.net/de/go/freephone > _______________________________________________ > 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
