Author: Ed Schröder
Date: 09:40:11 03/17/98
Go up one level in this thread
>>Why not throw learners out? >>They hide the real playing strength of a chess engine. >>See my below "double game" definition. >I disagree. I would say they "show" the real strength, because if you >don't learn, you get killed. If you do learn, you don't get killed... >And even against humans that is critical... I fully agree with you Bob. Against humans is a total different story. However my topic is comp-comp games and especially those on SSDF using AUTO232. >>Definition of a double game for COMP_X vs COMP_Y games... >>Whenever X or Y leaves the book. >>Simple as that. >>A second situation is a double game. >>Get rid of double games. What do they contribute to comp-comp games? >>Nothing in my opinion. >your definition is flawed in the case of Crafty. Crafty not only learns >book stuff, it learns after it is out of book... and even if you follow >the same book line it may play differently. Your "learning" view is far >too narrow, because there are other ways to learn also. See also >"knightcap" >on the servers. It is a very sophisticated learning program that is >getting >better and better as it plays. >I'd call a "double" a game that is the same from the first move to the >last move. Cutting it off anywhere earlier would dilute the type of >learning I (and Ferret and probably others) do in addition to my book >learning... I know that. But for testing an improvement of the engine my used formula is perfect since all learners have no influence. Result, clean engine-engine fights. Reliable engine results. - Ed -
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.