Re: [Bug-gnubg] Snowie 4 vs. GNU 0.13

[Joern Thyssen]

On Mon, Jun 09, 2003 at 07:53:10AM -0700, Rod Roark wrote
> As I mentioned, I don't think standard deviation from a
> single run of any number of matches is an interesting
> number.

Right, now I see your point.

Still, I'm not convinced. I'm merely doing batches of one match each. 

I'm trying to reduce variance by including luck. Here are the first 9
matches:

1 1 .68190 .12913 .44723
2 1 .07097 -.43769 .49134
3 1 .24894 -.19362 .55744
4 0 -.26061 .16947 .43008
5 0 -.88839 -.30512 .58327
6 1 .14517 -.30066 .55417
7 0 -.41612 .38666 .80278
8 0 .19603 .19853 .00250
9 1 .36055 -.03610 .60335

The first column is the match number, column 2 is the actual result
(1=gnubg, 0=snowie), column 3 is gnubg's total luck, column 4 is
snowie's total luck, and column 5 is the luck-adjusted result.

The average of the luck adjustment values (for all 100 matches) is
0.500, i.e., the bots are equally good.

Jørn