[Computer-go] Experiment?

Martin Mueller mmueller at ualberta.ca
Thu Mar 11 13:14:46 PST 2010


Hi Olivier,

do you think those are program-specific or a general problem with UCT (or more likely the way simulations are run)?
Can you post a few specific cases?

In Fuego, we also have many performance test failures that do not seem to go away, even at long time limits. But we never tried with REALLY long time limits.

	Martin

> - in particular, there are situations in which chosen moves are bad whenever N is 
>      very very very large.




More information about the Computer-go mailing list