I very strongly suspsect that Many Faces, Mogo, Crazy Stone and others are heavily optimized to play well on exactly the hardware we have at the moment.
There is the huge problem that you cannot easily test scalability because you cannot produce the thousands of game needed to get accurate numbers except at very fast games. And you cannot get reliable results against humans without waiting weeks. I think after a very rapid development period where we saw incredible and amazing results, anything less is discouraging and we are ready to throw in the towel. - Don 2009/6/11 Olivier Teytaud <teyt...@lri.fr> > > In my humble opinion, we need a change in the algorithm. The numbers are > misleading - 95% of win of > MoGo on 32 nodes against MoGo on 1 node (this is a real number for 19x19) > certainly means that the > parallel version is stronger than the sequential version, but not "much" > better, far less than what suggests > this 95%. MCTS algorithms adapt the beginning of simulations only, and for > many cases we have to deal > with predictions on the end of simulations: something like "if the opponent > plays X, I'll reply Y". The bias > on semeais is, in my humble opinion, equivalent to this fact that we learn > only the beginning of the simulations > (the tree part) and not the end. > > I don't know if the good word is to say that it's a wall or a mountain, but > I think the idea is that we need > something really different - perhaps heavy playouts that solve some > tactical elements, or perhaps > some statistical trick for modifying the playouts depending on the > simulations - I'd like to solve this with > supervised learning like "when I reply X to move Y then I win with higher > probability". It would be a nice > solution, efficient beyond the game of Go. > > Well, as I've spent a lot of time on this idea without finding an > implementation which works better than the > baseline, perhaps my ideas are not very interesting :-) > > > > Regarding Moore's Law, I'd love to hear the Mogo team's perspective on >> this; they have probably had more opportunity to test their algorithms >> extensively on big-n-count computers than any of us. >> >> > > _______________________________________________ > 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/
