Author: Pedro Gomes
Date: 07:15:38 03/04/05
Go up one level in this thread
On March 04, 2005 at 09:15:47, Milorad Madjar wrote: >On March 04, 2005 at 08:23:24, Pedro Gomes wrote: > >>On March 04, 2005 at 07:31:15, Milorad Madjar wrote: >> >>> >>>I played match Deep Fritz 8 and The King 3.33 with Nunn test and I want know >>>what I got with this match ? What this match say ? Fritz played better ....? >>>What Nunn test say ? >>> >>>S-WDBBO2D1R47DX, Blitz:5' 0 >>> >>> 12345678901234567890 >>>1 Deep Fritz 8 11½111½10½010010101½ 12.0/20 >>>2 The King 3.33 00½000½01½101101010½ 8.0/20 >>> >>>Milan >> >> >>Have you played two games for each position: >>first one with DF 8 as white, >>second one with TK 3.33 as white ? >> >>IF YES, then I think that 40 games giv better and more conlusive result. >> >>PG > >Yes I know result but, >I want know is it Nunn test position test or tactics test or ...... > >Milan Look here: http://www.aarontay.per.sg/Winboard/computer.html#opening Opening books, Nunn tests and Learning. Computer Chess results can be adversely effected by poor opening books. In fact, it has being suggested that some commercial programs have strong "killer" books, which accounts for much of their strength, and each new version improves because of a better book rather through the strength of the engine. This is of course, an extreme view. But we cannot deny that opening books play a big part in determining the results. The Nunn's test avoid the variability in quality of opening books, by starting all the chess programs from various [16] default opening positions. However just as humans use openings that suit their playing style, opening books are designed to allow each Chess engine to play to it's best and are a integral part of the Chess program. Another problem is that the Nunn's test insists that a program is only stronger than another if it demonstrates it's strength over it's rival in various opening positions [since the Nunn's test positions cover a range of openings]. This is extremely artificial, if you replace the two Programs with 2 Human GMs and consider the consequences. Many programs comes along with their own opening books, and some testers feel that those books should be used. On the other hand, self-made books have often being used as well. There is a question of whether learning should be turned on, especially in a tournament with engines that don't have this feature. My own personal view is that learning should be turned on, since the lack of the learning feature in one engine shouldn't handicap/hinder the use of it in a engine that has it. Of course, you might get a lot of repeated losses by the non-learning engine if the learning engine has aggressive positive book learning.
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.