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

BGonline.org Forums

15552-game rollout of 41Z-65R-43

Posted By: Timothy Chow
Date: Sunday, 27 December 2009, at 2:02 a.m.

In Response To: 15552-game rollout of 41Z-65R-43 (Nack Ballard)

Nack Ballard wrote:

(at least in the early game) I trust a 1k [truncated] rollout more than a short full rollout -- one with fewer than 5k trials.

I've argued—at least on rec.games.backgammon, if not here—that truncated rollouts might sometimes be preferable to full rollouts, especially given a fixed amount of computation time. I don't think I convinced anybody, but it's good to see someone else coming independently to a similar conclusion.

In statistician-speak, the point is that unbiasedness is not to be idolized. There's an old and very nerdy poem by Maurice Kendall called Hiawatha Designs an Experiment that makes this point. But you might have to be both a fan of Longfellow's original poem and have gotten into heated arguments about biased estimators to get the full enjoyment out of Kendall's brilliant piece.

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.