|
From: | Joseph Heled |
Subject: | Re: [Bug-gnubg] Questions on pruning net |
Date: | Thu, 25 Nov 2004 09:39:04 +1300 |
User-agent: | Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.7) Gecko/20040616 |
Ian Shaw wrote:
-----Original Message-----From: Joseph Heled [mailto:address@hidden Sent: 23 November 2004 21:24Ian Shaw wrote:
I think most of you still miss the point of the prune nets. It just pre-filters the options in a move selection *inside a higher ply*. If the move is on it's top 10 list, the error is 0. If not, the error is the equity difference between the top move on the list and the top *0 ply* move.So the pruning nets pick the pest 10 moves, then these 10 moves are evaluated using the main net as before.
Exactly.
2. How strong are the pruning nets in their own right? How do they compare with 0-ply?[snip interesting details] Do you equivalent numbers for 1-ply and higher?So, prune error rate per move is ~ three time higher than 0 ply.... but about 10 times worse on cube decisions. I don't really understand how this can be, since you are still looking at play selections to evaluate the overall cube equity.
Why not? Cube decisions are more difficult, since you need to get the probabilities right. move selection is about relative numbers. (There is no move selection involved in 0-ply cube actions ..)
-Joseph
[Prev in Thread] | Current Thread | [Next in Thread] |