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

BGonline.org Forums

Thx .,..now I understand

Posted By: Michael Depreli
Date: Wednesday, 16 September 2009, at 1:42 p.m.

In Response To: Thx .,..now I understand (neilkaz)

Yeah..I can see the XGR may make a couple of errors not made by any other tested bot setting (esp if close).

I can also see that the GNU@6 setting will do the same and even from your original 626 worse than .040 it is possible that a few plays would have been worse and therefor there might have been 630 to 635 original positions.

You got it.

XGR looks very strong though. It's odd that it doesn't use variance reduction. Although VR rollouts are slower, on gnubg at least you get a stat sig figure much much quicker (less trials). Obviously we can't test XGR with VR. Only Xavier can do that.

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.