Author: Jay Scott
Date: 12:54:55 01/04/99
Go up one level in this thread
On January 04, 1999 at 15:10:07, James Robertson wrote: >Well; they know how to punish them, but they don't know why. All they know is >that they won the game at the end. The problem with chess learning is that every >aspect learned must be put in by the program by the programmer. e.g. if the >programmer puts piece/square table learning in, the program learns piece/square >tables. If they put doubled pawn awareness in, the program fiddles with the >doubled pawn scoring. And so on... Another note: the "knowing why" part in artificial intelligence is called explanation-based learning. The idea is that a program can explain why some event occurred in a specific instance (hmm, that knight attacked my king and my queen, and I had to move the king) and generalize the explanation to cover other cases (hmm, now I know what a fork is). EBL is potentially very powerful, but it's in a primitive state right now (in my opinion). EBL programs are smart enough to learn about forks, but not smart enough to learn about, say, passed pawns. It would be an interesting research project to try to use EBL to learn more difficult chess concepts. 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.