Author: Dann Corbit
Date: 19:50:21 07/15/05
Go up one level in this thread
On July 15, 2005 at 22:19:44, Sune Fischer wrote: >On July 15, 2005 at 21:00:05, Dann Corbit wrote: >>> >>>Here you simply end op with an ever growing list of engines you have to keep >>>playing against, and because they play more and more games it will be harder and >>>harder to take them out. How do you break this circle? >> >>There is no value to break the circle until the engine is no longer strong >>enough (e.g. when it becomes 300 Elo weaker than the engine that you wish to >>calibrate, then the data loses its punch). As long as the engine is within 100 >>Elo of the test engine, the more games that have been played against an engine, >>the better it is to test with. If we had an engine with 1 trillion games >>against it by carefully calibrated known opponents and it was within 100 Elo of >>our engine, it would be the best possible measuring line. > >I would prefer a round robit type tournament with a roughly even number of games >per engine instead of forever gauntletting the oldtimers. > >I'm pretty sure it creates a more accurate rating too. Yes, probably that is better. With 2-4 games against a broad array of well known opponents, you will get an even better result. I think the difficulty here is setting up the tournaments. Probably, most of the testers do not have all of the programs. And some of the programs require manual intervention. >>>Take out the old engines and just play on against its opponents, there must be >>>many of those. >> >>The old hardware programs in the list don't have much value anymore, because >>most good amateur programs can clobber them. But Fritz 5.32 on a 450 MHz box >>will be plenty strong of an opponent for a couple years to come, probably. > >I think that one has earned its retirement. >:) > >-S >>[snip]
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.