Author: Chris Carson
Date: 15:10:32 08/01/02
Go up one level in this thread
On August 01, 2002 at 17:55:39, GuyHaworth wrote: > >Good information in the answers, illuminating some of the issues. Thanks. > >First, my focus is on 'rating' chess-engines on the basis of play against solely >human opponents under controlled conditions. > >As VD says, FIDE defines the conditions it requires for the awarding of norms. > >Other conditions might be attached to the fact that the chess-player is silicon >rather than carbon, e.g. the configuration of the engine in all essential >parameters must be logged and maybe 'mothballed' for later replication. > >I was not suggesting that humans should be rated against computers 'with a FIDE >rating'. There is still the question of replicating the engine that got the >rating, as VD's scenario about powersaving/small_hash_table/etc/etc engines >illustrates. > >It seems that HIARCS missed out by 0.5 points, though the other criteria were >arguably met. > >There have certainly been cases of engines achieving norms (in principle) in the >past, e.g. BELLE (UKCF Chess Master?), DEEP THOUGHT, DEEP JUNIOR, <your >nomination goes here> > >g If you are interested in Rated Human vs Computer games under FIDE conditions, see: http://home.interact.se/~w100107/manmachine.htm
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.