Author: Jay Scott
Date: 09:59:47 02/06/99
Go up one level in this thread
On February 05, 1999 at 02:28:35, David Blackman wrote: >Are you sure TD learning can't learn tactics? I would have thought it could. >TD works by comparing eval for shallow and deep searches, doesn't it? And if the >deep search finds a big difference to the shallow one, the difference is because >of tactics. It could certainly learn about tactical potential, given the right parameters to set. But I notice that even we humans aren't quite sure whether the tactics work out unless we calculate them. I think it's the nature of the game. Jay
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.