Author: Uri Blass
Date: 13:36:45 01/08/03
Go up one level in this thread
On January 08, 2003 at 16:28:48, Kolss wrote: >On January 08, 2003 at 15:47:56, Uri Blass wrote: > >>On January 08, 2003 at 15:40:21, Rajen Gupta wrote: >> >>>On January 08, 2003 at 15:18:18, Roger D Davis wrote: >>> >>>>We occasionally see posts where engines take turns playing the Nunn positions, >>>>the idea being to give the engines an equal footing, but with some development. >>>>But has anyone looked at whether white or black wins more often for each Nunn >>>>position? Presumably, if white wins some 55% of the time for all openings (or >>>>whatever the figure it, consult your database), then the same should hold true >>>>for the Nunn positions: Given equal engines, white should win 55% of the time. >>>> >>>>Some large inequality between white or black would indicate that a particular >>>>position ought to be deleted from the set, or some other position substituted. >>>> >>>>Roger >>> >>>i see the point that you are trying to make ie that there maybe some positions >>>that are not strictly neutral to begin with; however each engine gets an equal >>>bite at the cherry so to speak and even if a particular position were to >>>inherently favour one colour, both engines get to play that colour and the final >>>result depends upon which engine can win more often; so i guess the nunn >>>positions are a pretty good test for evaluating engines; however the valid >>>argument is that programmers can tune their engines to perfom well on these >>>tests; >> >>In theory they can do it but I doubt if they practically do it when 99% of the >>tournaments are not done from the nunn positions. >> >>Uri > >You will automatically tune your engine for certain opening positions (e.g. Nunn >I or Nunn II or Noomen Select X) as soon as you use these as part of your >testing method - whether you want or not, whether you are aware of it or not. > >The same holds for testsuites, of course. As soon as you use them to check your >engine's progress, you will automatically tune the engine for the respective >testsuite(s). > >In fact, you always tune your engine for something - testsuites, opening >positions, opening books, opponents; and actually, you have to do this - or stop >developing a chess engine. The only thing you can do is chose "what" you want to >tune for. > > >Regards, Munjong. tuning the engines to beat the opponent is done but I doubt how many programmers use the nunn positions. Even if they use the nunn positions for testing it does not mean tuning the engine for these positions. The point is that a change can be good also in other positions. When I think about tuning for the nunn positions I think about changing the evaluation specifically for the nunn positions. I think that changes in the search rules that help in the nunn positions will usually help also in other positions. 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.