> >> I clearly stated what I meant by effective: >> "How much faster you find the correct move. Not interesting is: how many >> positions you search per second or how many playouts you do per second." >> > > What is "correct" move? It has sense only for some artificial > problems or very limited positions, and so, it cannot evaluate total > performance of a program. >
This is true, I learned long ago that problem tests do not measure program performance well at all. However, in this case my guess is that it would be an accurate measure of effective program speedup. It's possible this assumption is wrong but I am assuming that parallelizing UCT does not change the characteristics of the playing strength in a measurable way - just the efficiency. - Don > >> The fact that parallel UCT is not the same as serial UCT does not change >> anything at all with the above definition. Either it finds good moves >> faster, and hence is stronger, or it does not. >> > > I agree but how to? One way I can think of is to run a program on > cgos or similarbut Olivier wrote it's not allowed. > > -Hideki > -- > [EMAIL PROTECTED] (Kato) > _______________________________________________ > 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/
