Author: Simon Read
Date: 03:42:08 01/29/98
Go up one level in this thread
On January 28, 1998 at 17:36:06, Bruce Moreland wrote: >There are lots of places to apply what has traditionally been thought of >as AI to chess, not necessarily just in the search. I think Crafty's >learning is an interesting AI experiment -- Bob is teaching Crafty to >play a series of chess games well rather than just one. > >I think he should find some examples where it has adapted in order to >improve its results against specific opponents, and write something up, >I think it would make an interesting article. Indeed. Bob did say some things on r.g.c.c. about how crafty modified its behaviour. Such behaviour is indeed fascinating: crafty no longer makes the same mistake twice. Especially that bit about having the hedgehog (IIRC) played against it so many times, crafty itself used the hedgehog to beat someone. These are definitely interesting symptoms for a program to have. An article in ICCA would be interesting. Simon
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.