Yes! We could actually train neural networks with different characteristics.
Let's say we do one loop through the training dataset, and for each position we add a little notch to the winning probabilities for all positions that have an opponent checker on the bar (and maybe even a bigger notch if there's two or more checkers on the bar). Then we do supervised training with this modified trainset. This will hopefully create a more aggressive player that will be more eager to hit loose on checkers, and hopefully create a player with an attacking style. Then - Let's say we do one loop through the training dataset, and for each position we subtract a little notch to the winning probabilities for all positions that have a blot that can be hit (and maybe even a bigger notch if there's several of it's blot that can be hit). Then we do supervised training with this modified trainset. This will hopefully create a more careful player that will rather create high stacks than playing flexible. Typically seen by beginner players. 4-1 opening roll is then played 13/8, they seldom split backcheckers etc. Of course I have no idea if this will work or not. But I think I will be able to do something like this. (But not now as I'm leaving for vacation tomorrow morning) We probably need some interface that can read custom neural networks. I have lost the touch when it comes to GTK coding, but someone may be able to specify. -Øystein fre. 4. aug. 2023 kl. 15:39 skrev Superfly Jon <[email protected]>: > Different nets sound like a good addition for people who want to play > against the computer. This could be combined with an old idea of having a > list of opponents with different characteristics (e.g. more / less > aggressive) where the move equities are adjusted based e.g. on the number > of blots, leading to weaker play with different styles. Maybe the > different neural nets already do this to some degree? > > Unfortunately I haven't the time to commit to this currently, but maybe > others might and I may have more time in the future. > > Jon > > On Tue, 1 Aug 2023 at 06:52, Joseph Heled <[email protected]> wrote: > >> >> Hi, >> >> As part of my recent research (Elo systems and PR) I generate a number of >> neural nets, ranging from 500 Elo to about 1800. >> >> I thought it might be a nice feature to have for beginners, to play a >> weaker, less frustrating, computer opponent. Might also be useful for >> stronger players - practicing playing against weaker players. >> >> I am willing to adapt the nets to GNUbg. If anyone wants to collaborate >> with me on the rest, i.e. user interface and glue to the rest of the >> system, please contact me and we can discuss feasibility. >> >> -Joseph >> >
