Hi!
On Mon, Mar 09, 2015 at 10:08:04AM +0100, Urban Hafner wrote:
> I'm currently running Brown (random bot) and GnuGo on CGOS 13x13. Mainly to
> get a feel for the strength of my own bot. And my bot is really bad. ;) So
> bad that it looses all games against GnuGo, but wins all games against
> Brown. So, the rating is a bit useless I assume as there are no bots that
> are in strength between GnuGo and the random player. Are there any bots in
> that range out there? I'd be willing to run them myself on CGOS.
What about libego? That used to be a pretty basic MCTS.
Or you could try running a "super-weak Pachi":
> Pachi can be used as a test opponent for development of other go-playing
> programs. For example, to get the "plainest UCT" player, use:
>
> ./pachi -t =5000
> policy=ucb1,playout=light,prior=eqex=0,dynkomi=none,pondering=0,pass_all_alive
(see "Experiments and Testing" section in README for more details)
This is plain UCT with light playouts and no move priors. If you just
implemented the basic algorithms, your program should be equal or better
than this.
(Of course you can then gradually enable some pieces, or even just
some of the priors/playout heuristics. I'd recommend implementing, in
the order of priority, captures and 3x3 patterns in playouts, priors for
the same in the tree, and RAVE. Don't bother tuning things too much
before having RAVE as that is a big game-changer; but it probably won't
work well without at least the playout heuristics I mentioned.)
--
Petr Baudis
If you do not work on an important problem, it's unlikely
you'll do important work. -- R. Hamming
http://www.cs.virginia.edu/~robins/YouAndYourResearch.html
_______________________________________________
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
