Author: Vincent Vega
Date: 23:31:44 03/10/00
Go up one level in this thread
On March 10, 2000 at 12:53:57, Bruce Moreland wrote: >There's never been any consensus as to what knowledge is. People assume that >programs with low NPS are high knowledge programs, but these programs could be >doing tactical evaluation that may as well be search. > >If I have a program that evaluates at the tips, maybe it will do 200K nps. But >if I suddenly decide that my "eval function" is the last three plies of search, >it will fall to a few K nps. It didn't get any more knowledeable. > >bruce I agree that NPS by itself is a bad measure of knowledge. It's hard to come up with anything better because something that can be considered knowledge and implemented as such in one program, could be found by very deep search in another program. I think a better distinction between high and low knowledge programs could be achieved by creating a suite of "tactical" and "positional" positions (blurry distinction) and looking at how the programs' evaluations of them change over time, but it’s much harder to do.
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.