[Computer-go] 7.0 Komi and weird deep search result

Petr Baudis pasky at ucw.cz
Mon Apr 4 19:27:08 PDT 2011


On Mon, Apr 04, 2011 at 12:56:54PM -0400, Brian Sheppard wrote:
> >> MCTS using RAVE prioritization *does* converge to game theoretic values
> in a
> >> binary-valued space.
> 
> >Can you reference some more detailed analysis claiming this?
> 
>  
> 
> Theorem: In a binary-valued game of finite length, the RAVE score of all
> winning moves converges to 1, provided that 0 < FPU < 1.

Oh of course, it is obvious. Sorry for being slow and confused.

But it seems it should be possible to prove that even theoretical
convergence in case of RAVE discrepecancies is much slower than with
plain UCT... Might be a fun exercise.

				Petr "Pasky" Baudis



More information about the Computer-go mailing list