[Pachi] Criticality

valkyria at phmp.se valkyria at phmp.se
Tue Apr 26 00:10:31 CEST 2011


I compute criticality in Valkyria but is uncertain if it is of any use  
directly.

What I can see from looking at values generated by my implementation  
is that criticality rarely point out good local moves, but in a vague  
sense all move near critical stones. Valkyria computes criticality for  
all stones, and I can see that is a really good measure to point out  
which stones are actually critical.

But from this it is not so easy to see what to do with it. Maybe using  
criticality as a feature in pattern matching to better distinguish  
between Life and Death and gaining territory would be a good use.

-Magnus

Quoting Petr Baudis <pasky at ucw.cz>:

>   Hi!
>
>   I just merged a promising-looking change into master. I have
> resurrected a criticality implementation I wrote few months ago.
> The main purpose for this metric is to set ltree goals, but just
> to test things out, I implemented support in UCB1AMAF for including
> this in the RAVE term.
>
>   After some very basic tuning, it seems now that it should be couple
> tens of elo gain unless the confidence bounds are playing it nasty.
> But I think I'm still far from the optimum values and I'll need the
> resources for other testing soon, so help with fine-tuning is welcome.
>
> --
> 				Petr "Pasky" Baudis
> UNIX is user friendly, it's just picky about who its friends are.
> _______________________________________________
> Pachi mailing list
> Pachi at v.or.cz
> http://rover.ms.mff.cuni.cz/mailman/listinfo/pachi
>




More information about the Pachi mailing list