[Bug-gnubg] Best Rollout Parameters?

[crawling . weasel]

Hello!

What are the best (1st: reliable (!!!) 2nd: as fast as possible) parameters for 
rollouts, please? 

Years ago Gary Wong recommended 1296 trials, 2 ply, no truncation and variance 
reduction. Still 
the same? 2ply seems a lot and slow ...

Meanwhile there are a lot more parameters. Should I use:

"Stop when STD are small enough"?
"Stop rollout of multiple moves based on j.s.d."?
"Cubeful"?

Anything else important? 

Thanks a lot in advance.

Hans