Ok, I'm doing the komi study. I hope this data formats properly on your email clients.
I am not including the first day or two of games because I remember that I started out with 6.5 komi but I think that only lasted a few hours. I'm including ALL games unless they ended with an illegal move. I'm using bayeselo ratings. So each bot has only 1 rating over it's entire lifetime of games. I do not include games where either player played less than 20 games. 20 games does not give a very accurate rating, but I had to draw the line somewhere. However it's probably within 100 ELO of being correct. I require opponents to be within 100 ELO of each other. I ran this many times using different minimum ELO values. The data seems to indicate that white's winning percentage at 7.5 komi DECREASES with the strength of the players in general. HOWEVER, the 2500 ELO entry is intriguing. It shows a sudden jump with a sample of 3400 games. Does anyone have an explanation for that? Is this just sample error? Or are the programs finally strong enough to start seeing that white wins at 7.5 komi? Another interesting fact is that whites win percentage drops below 50% with some of these entries (stronger players.) DIFF MIN ELO WHITE TOTAL PERCENT ----- ------- ------- ------- ------- 100 0 74513 141579 52.630 100 100 74513 141579 52.630 100 200 74511 141577 52.629 100 300 74191 141054 52.598 100 400 73723 140308 52.544 100 500 73524 140009 52.514 100 600 73427 139874 52.495 100 700 72763 138921 52.377 100 800 72335 138212 52.336 100 900 71227 136490 52.185 100 1000 71192 136432 52.181 100 1100 71084 136231 52.179 100 1200 68862 132356 52.028 100 1300 67765 130428 51.956 100 1400 66562 128193 51.923 100 1500 64143 123672 51.865 100 1600 56458 108767 51.907 100 1700 53943 103828 51.954 100 1800 40790 78999 51.634 100 1900 18403 36247 50.771 100 2000 16859 33340 50.567 100 2100 13793 27399 50.341 100 2200 8986 18072 49.723 100 2300 8555 17266 49.548 100 2400 7686 15569 49.367 100 2500 1801 3400 52.971 100 2600 12 28 42.857 When I use a window of 200 ELO the data looks very similar. Here is the data when I require the difference to be 50 ELO or less: DIFF MIN ELO WHITE TOTAL PERCENT ----- ------- ------- ------- ------- 50 0 46184 87556 52.748 50 100 46184 87556 52.748 50 200 46183 87555 52.747 50 300 46031 87326 52.712 50 400 45890 87100 52.687 50 500 45815 86996 52.663 50 600 45813 86993 52.663 50 700 45376 86377 52.533 50 800 45108 85932 52.493 50 900 44050 84302 52.253 50 1000 44032 84277 52.247 50 1100 43969 84163 52.243 50 1200 42840 82193 52.121 50 1300 42361 81354 52.070 50 1400 41503 79735 52.051 50 1500 41003 78853 51.999 50 1600 37959 72933 52.046 50 1700 36280 69569 52.150 50 1800 28478 54845 51.925 50 1900 8535 16668 51.206 50 2000 7896 15433 51.163 50 2100 6823 13349 51.112 50 2200 4145 8120 51.047 50 2300 3917 7704 50.844 50 2400 3627 7166 50.614 50 2500 1497 2871 52.142 50 2600 12 28 42.857
signature.asc
Description: This is a digitally signed message part
_______________________________________________ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/