Author: Michel Langeveld
Date: 04:37:46 07/08/03
Go up one level in this thread
On July 08, 2003 at 06:23:55, Geoff wrote: >Hi > >Q1 >In some test suites I have seen moves with 'am' in front of it apart from the >usual 'bm'. I can't recall which test suite it was now to check. >Does this stand for 'alternate' good move or 'avoid' move ? am = avoid move ... it's count if a chessprogram don't play this move. bm = best move pm = preferred move ... common used for strategical moves >Q2 >Is there a method or utility program to determine the absolute rating strength >of a chess program? After a quick peruse of the ELO rating system, it seems to >have 2 drawbacks. Firstly, it is reminiscent of a Nuclear physics equation, >secondly and more importantly it is a relative rating. I had a quick tinker with >ELOSTAT, this removes the awkwardness of the calculation but the result was >totally dependent on the quess I made for the start rating. Testing is a different thing ... I do now the following: - let it play WAC 2 seconds ( I would like to see a score of 265 or higher) - let it play WAC 5 seconds ( I would like to see a score of 277 or higher) - Then I use ECM (middlegame) - MES (endgame) - BWTC (mates) - ??? (gambits like Bxg6, etc) to see how it scores futher on testpositions - Then I play games on 3 minutes and games in 40 moves in 5 minutes. Most of the time around 200 or so. I have also some special builtin tests of nullmover ... which tests the hashing On all the results I try to look what goes right and wrong... I do tests mostly overnight on a dual 800Mhz machine. If u can find a method what can test a program let's say in 15 minutes with a error rate of 50 elo that would be a welcome item. Best regards, Michel
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.