That same statement baffles me. AMAF gives a huge boost with light playouts for me. As the number of playouts increase, AMAF gives less and less. After a few thousand playouts it's almost nothing but if it's worse than not doing AMAF it is difficult to measure. Of course MCTS never does thousands of playouts from a single node.
What is the definition of light playouts? I am referning only to purely random playouts and perhaps that is where the discrepency is. Don 2009/12/14 Olivier Teytaud <[email protected]> > > >> >> I've found that AMAF gives very little boost with light playouts, >> >> > Thanks for this interesting comment. > I would (erroneously) have believed that AMAF gives > better results with non-optimized implementation (e.g. in Havannah with no > expertise Amaf provides huge improvements). In particular, I believed it was > moderately efficient in 19x19 due to the patterns which already provide > relevant > informations - but I could never test it (testing properly this assumption > requires the tuning of the version without Rave, which would be time > consuming and boring :-) ). > > Best regards, > Olivier > > > _______________________________________________ > computer-go mailing list > [email protected] > http://www.computer-go.org/mailman/listinfo/computer-go/ >
_______________________________________________ computer-go mailing list [email protected] http://www.computer-go.org/mailman/listinfo/computer-go/
