Author: Uri Blass
Date: 13:30:51 12/12/00
Go up one level in this thread
On December 12, 2000 at 14:02:11, Thorsten Czub wrote: >On December 12, 2000 at 13:30:32, Christophe Theron wrote: > >>This way of explaining things shows that you don't know how programs can plan. >>It's not about changing weights of the evaluation terms. It's about looking at >>the position like a human would do and selecting the appropriate "goals", and >>then trying to achieve them by calculation. > >right. some programs really do so. >not in any game it can be easily seen. not in any game it works. >i think i have seen such a behaviour in some mchess games. >also gandalf comes to my mind. I think that the question is what is the definition of planning. I think that every program that is based on static evaluation is not planning. A plan can help humans to change their evaluation function. I do not know programs that think in the following words: "I cannot make progress in this structure so I will evaluate this structure as a draw" They have static evaluation of the structure and if the static evaluation of the structure is wrong it will never change. If the static evaluation is right you can get the illusion of planning but it is not planning by my definition. Uri
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.