ken regan has done some modeling the complexity of chess positions, and perhaps more interestingly, the modeling of the ability of a human player based upon how he or she makes move choices -- this only works because a computer player can vastly outplay a human player (and can act a bit like an oracle for many positions). so in computer go it should only be expected to be applicable when the human player is very, very weak.
so there's some hope for giving large handicap, but it shouldn't be expected to be useful for taking large handicap. s. 2009/7/13 terry mcintyre <terrymcint...@yahoo.com>: > Is it possible to design metrics for "complexity" of positions? An opponent > model could make use of that information; there are positions which some > players will totally fail to grok. > > Double-digit kyu players are weak on life-and-death, ko, and seki. Some > otherwise strong programs will fail to read seki properly. As players move > up in rank, they read life-and-death at an earlier point. Human players, > with practice, discover the weaknesses of their particular opponents. > > Terry McIntyre <terrymcint...@yahoo.com> > > “We hang the petty thieves and appoint the great ones to public office.” -- > Aesop > > ________________________________ > From: Magnus Persson <magnus.pers...@phmp.se> > > I am open to opponent modeling such as make the playouts of black in > handicap games weaker. But in this case I think real gain if any would come > from making the statistics more sensitive to the qualitative difference in > available moves, rather than actually modeling the opponent, by bringing the > win rates closer to 50%. Although I think it would be really hard to degrade > the black moves in the playouts in a realistic way. > > > > _______________________________________________ > 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/
