Yamato: <4a8d2cc8.29578c0a.3f87.6...@mx.google.com>: >steve uurtamo wrote: >>zen wins many more of its "even" games with no handicap than it does >>with even, say, an even 2 stone handicap as either black or white. i >>haven't compiled numbers for it (i'm not zen's maintainer), but i >>watched it happen over the course of about 50 games one day. it was >>pretty consistently worse with any kind of handicap on the board, the >>more handicap the worse. fix the handicap problem and it would likely >>rise a stone in strength. > >I have done some experiments in dynamic komi on Zen, and it didn't work. >My experiments might not be enough, but I feel this kind of idea is not >a solution for the handicap problem. Did anyone succeed with it?
Were the experiments Zen vs (maybe weakened) Zen or other bots? If Zen, it is possible that the error of the model of the opponent is small (i.e. the averages of the score are the same while the variances are different) and the idea doesn't work well. In other words, how did you measure the effectiveness of the idea, by some hundreds of self-playing games? I believe that since the improvement of the idea could be a few tens Elo (logically, depends on the correctness of the model), thousands of games are necessary to detect it. Hideki -- g...@nue.ci.i.u-tokyo.ac.jp (Kato) _______________________________________________ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
