Re: [Bug-gnubg] Re: Rollout jsd, statsig etc. [LONG]

[Timothy Y. Chow]

On Mon, 16 Nov 2009, Massimiliano Maini wrote:
> Tim, the point you made is very clear. In my original post I
> mentionned myself that in the "usual" interpretation there's some
> inaccuracy. Also, I said that your method is (quote) "by far the right
> conceptual way to answer the question".
> 
> That said, it seems that under usual conditions the multiple measures
> are very close and any of these is equally good for the goal: indicate
> if a rollout can be trusted or needs to be extended.

The main point I'm making is that whatever choice is made regarding what 
computation GNU Backgammon makes and what information is displayed, it 
should accurately report what it is actually computing.  If it computes A 
then it should say that it's computing A.  It should not compute A and say 
that it is computing B, and hide behind the excuse that A and B are close.  
If you want to report B, then compute B.  If you want to compute A, then 
compute and report A.  Don't compute and report A but claim that you're 
reporting B.

The goal of making the results clearly intelligible to the user is not 
served if GNU Backgammon perpetuates a widespread misconception by 
blurring an important distinction.

Tim