Author: Vincent Vega
Date: 13:57:27 02/13/00
Go up one level in this thread
On February 13, 2000 at 16:30:46, Andrew Dados wrote: >Take one, simplest example: basic ending KP vs K. Don Beal wrote a routine for >that; looking at it I can see some 20-30 exceptions which need to be handled >specially. Now applying neural nets or any genetic alghoritm would make my >program learn that ending after some time, sure; it still would not get to play >it perfect in sensible learning time. TDChess does learning using temporal >diference algorithm; takes it a while to get to some sensible 'conclusions'. >Also finger 'morph' on icc - it's rating is close to 1000. I wonder what rating >would totally random-moving program get (or program limited to ply 0 /qsearch/ >only). So is writing some 1-3 thousand lines for cute, state of art, hyphe >techniques worth it? For me - maybe in 2 places: to adjust some very limited and >dependand set of wages (like piece values you mentioned), or to try it to >determine best book line upon played games so far. Everything else I can (and >want) to adjust manually... I think that genetic algorithms could be used for determining best evaluation parameters for example. Neural nets and genetic algorithms are hard to apply to chess because chess is discrete and there is no randomness on the surface. In backgammon, for example, neural nets proved very successful. Pattern recognition is much more important in GO programs than in chess. Parallel and distributed programs are commonplace in all fields. These are not state of the art and hyped techniques anymore, maybe 10-20 years ago it was true. Today, they are used all over the place. I absolutely believe that even not very successful programs that use CS techniques that can be applied in other fields are much more interesting than dumb searchers. Luckily scientific journals editors seem to agree with me. They were fun 20 years ago; today they are just boring (maybe authors have fun with them, which is cool of course).
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.