If you look at the games of AnchorMan, a weak player but one that uses the standard approach of playing for the safe win - you may notice that it tends to play more naturally and does not suffer as much from this problem.
That's because it has tiny incentives to avoid moving into territory heavily owned by the opponent (or itself.) I was happy when I added this because it does make it seem less odd in the way it plays. It also sightly prefers capture moves (even when they don't help it actually win the game) which makes it more greedy. I think us humans have a certain "pride" that makes us cringe when the program doesn't kick the opponent when he is down. It's almost as if we feel embarassed that the program appeared to not notice that it might win a few extra stones. Or if it wins by 0.5 we imagine that it almost lost, barely scraping together the win when in fact it had the game well under control all along! - Don On Wed, 2007-04-04 at 19:57 +0200, Sylvain Gelly wrote: > > Would it be possible to encourage more substantial wins by tweaking > the "internal > > komi" used to drive move selection in this fashion? > > I tried that in two ways. > > First, try to put a bigger "internal komi" at the beginning decreasing > to 0 (assuming you play as black), so that the programs tries to play > "bigger" moves at the beginning. > Does not change anything, or can be worst if the internal komi is too > big of course. > > Second, try to adapt automatically the "internal komi" with the > position (if the position is better for you, increase it, else > decrease it). That does not give more wins, while mean score is > improved. > > Sylvain > _______________________________________________ > 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/
