On Mon, 2007-04-09 at 09:47 -0400, [EMAIL PROTECTED] wrote: > Don, here is a question. Your curves plotted the playing level vs the > computer speed. By computer speed you mean the number of MC > simulations per node with all other factors fixed. Is this correct? > If it is, it's legitimate for people to speculate that the curve could > level off beyond some number of simulations per node. Actually this is > an important question, because it relates to the nature of the MC > simulation. Daniel Liu
I'm not sure I understand what you mean by the number of MC simulations per node. The level that does 1024 simulations does 1024 play-outs period, over the whole game tree. I suppose if you could fit a curve to the data, with a few more doublings and LOT of data, you might be able to estimate the level that achieves perfect play. But this would probably be farily fuzzy estimate. - Don _______________________________________________ computer-go mailing list [email protected] http://www.computer-go.org/mailman/listinfo/computer-go/
