Christoph Birk wrote: > On Sun, 2 Mar 2008, Don Dailey wrote: >> My feeling is that in lost positions, the only thing we are trying to >> accomplish is to make the moves more cosmetically appealing (normal) and >> at best improve the programs chances of winning against weak players. >> After all, if the program is in bad shape, then to be completely >> realistic it's probably going to lose to the player that put it in this >> bad shape. > > I think you are wrong here. > If there are two lines of play from the viewpoint of the MC program: > a) leads to a 0.5 pt loss > b) may win if the opponent makes a stupid (!) mistake, but otherwise > leads to a bigger loss. > > It is generally better to play for the 0.5 point loss as the oppoenent > may make a end-game mistake and loses 1 point. > But naive MC programs typically go for (b) which will lead to a > devastating loss because the opponent usually does not make the 10 point > mistake, but may have made the 1 point mistake. I just want this to be seen for what it is, it's not a serious program improvement even if you can make it work.
What you are trying to do is more in the category of opponent modeling. You want to optimize for the case that you might occasionally salvage a game against an opponent that is much weaker than you but is beating you anyway. That's not a bad thing, but it will not make any serious difference in the strength of your program. If the opponent is beating you, he is probably relatively near your strength level. If your program KNOWS it is losing by 0.5 points, then it's reasonable to expect that your opponent does too, especially given the fact that he just outplayed you. So what you are trying to do is at best a very minor tweak. I would rather spend time making my program develop winning positions instead of trying to occasionally salvage a lost game with a swindle. Even in the case where your opponent hasn't figured it out yet (let's say this game is headed for an upset and your program really is much stronger) your window of opportunity is pretty small. If your program is sure of the loss, a few more moves will make it obvious even to a seriously inferior opponent (especially a MC based program.) So at best you hope your opponent will make a stupid mistake in an obviously lost position for you. There is nothing wrong with this, if it's what you want to lose sleep over, but how much do you expect to gain from it? I see people getting excited about this idea as if it's the holy grail of computer go and will add 50 ELO or more. If you want it as a cosmetic improvement, it's worth trying to make work. I think if you were marketing your programs commercially you would want to fix the MC type of behavior just because people generally don't understand it and it could give your program an undeserved bad reputation. - Don > > Christoph > _______________________________________________ > computer-go mailing list > computer-go@computer-go.org > http://www.computer-go.org/mailman/listinfo/computer-go/ > _______________________________________________ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/