On Sun, 2007-04-08 at 10:09 -0400, [EMAIL PROTECTED] wrote: > The question here is not about UCT(yes, it gaves the same rusults as > alpha-beta). It's about MC scoring. It has not been proved that MC > score will generate the optimum play with large enough simulation.
MC is obviously wrong as an evaluation function - it is not guaranteed to return a correct or even a good score no matter how many simulations. However, UCT eventually turns into a pure tree where MC is not a factor. These programs, in theory, will play perfect GO given enough time. - Don > Now the best super computer uses about 500,000 CPUs, which is 2 to the > 18th power of computation increase. Don's curve can be tested to the > number 18 now. _______________________________________________ computer-go mailing list [email protected] http://www.computer-go.org/mailman/listinfo/computer-go/
