[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums

Inconclusive high ply many trials rollout

Posted By: Timothy Chow
Date: Saturday, 26 February 2011, at 9:17 p.m.

In Response To: Inconclusive high ply many trials rollout (leobueno)

Let me push back on your question just to make sure you're really asking the question you intended to ask.

First, there's a distinction between the correct play and the play that tops the rollout. We can give you plenty of examples where the play that clearly tops the rollout is clearly the wrong play. Is that something you're interested in?

Suppose instead that you want to restrict your attention to positions where the general belief is that the play that tops the GNU rollout is the best play. Do you want cases where a long rollout demonstrates that there are two plays that are very close in equity, or cases where two plays may or may not be close in equity and it is hard to tell even after a long rollout? Nack, Stick, and MCG seem to have interpreted your question as asking for the former; that is, they have given examples of rollouts that are long enough to have driven down the variance, and two plays are shown to be very close. However, it is also possible to give examples of positions where there is still a lot of variance left even after 46656 trials. Is that something you're interested in?

Messages In This Thread

 

Post Response
Your Name:
Your E-Mail Address:
Subject:
Message:

If necessary, enter your password below:

Password:
 

 

[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums is maintained by Stick with WebBBS 5.12.