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/

Reply via email to