Author: Jay Scott
Date: 10:33:06 01/06/99
Go up one level in this thread
On January 06, 1999 at 11:12:12, Ulrich Tuerke wrote: >(However, Tiger might very well dominate a considerably weaker learner, because >the learning won't work in case the learner can't score at all.) That's not necessarily true. If the weak learning program simply plays the stronger program's moves against it, the weak program will eventually learn enough to win games, provided the stronger program doesn't learn too. This might take an extremely long time if the strong program has a varied opening book, of course. And it might not be possible at all if the weak program also has to learn against other opponents. But if there's only one opponent, and the strong program is truly fixed so that in the same position it always plays the same move, then it won't be long before the weak program figures out how to win every game. Jay
This page took 0.01 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.