Author: Dan Andersson
Date: 15:35:49 07/01/01
Go up one level in this thread
Quite a few programs have positional learning. Two free examples are YACE and Crafty. Crafty is open source, so it's possible to study the mechanism. These are two of many. So learning from mistakes is not something inherently or even hard to implement. This doesn't mean they learn typical attack patterns. But there is noting stopping programs from varying their play by either recognizing misevaluated positions in search or form tuning their own eval.
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.