Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Are computer ugly looking moves better moves?

Author: Steve Schooler

Date: 14:24:56 06/30/02

Go up one level in this thread


I suspect _ugly_ often coincides with not following a plan (i.e. inconsistent).
Obviously, Hiarcs (et al) can't form a plan.  Suppose in a specific game (series
of positions), Hiarcs evaluation function places more of a premium on
mobility/space than Fritz' evaluation function.  Then Hiarcs' moves might
plausibly resemble a human plan.

I think that Darwinian evolution (e.g. extra mobility square = .03 pawns) has
fine tuned and is continuing to fine tune evaluation functions.




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.