I set up gnubg to mimic XG Roller settings

Truncated @6
first 2 moves 1-ply cube 0-ply checker
others 0-ply.

No Variance Reduction

XG Roller uses 3600 trials.

Instead of using number of trials I decided to roll them out until JSD reached 
2.58 minimum trials 144.

If you do the same with VR ON, it takes MUCH less time by a huge factor to 
reach the same JSD.

I'm not a statistician but isn't JSD important if you only need to rank plays 
rather than need absolute equity?

Why not do it with VR ON ?



I'm sure I must have overlooked something obvious...



Michael



_________________________________________________________________
View your other email accounts from your Hotmail inbox. Add them now.
http://clk.atdmt.com/UKM/go/167688463/direct/01/
_______________________________________________
Bug-gnubg mailing list
[email protected]
http://lists.gnu.org/mailman/listinfo/bug-gnubg

Reply via email to