MadSci Network: Computer Science

Subject: How can a (e.g.) chessprogram LEARN from playing with people?

Date: Wed May 23 14:10:02 2001
Posted by Mikael
Grade level: undergrad School: college (engineering and psychology)
City: Borås State/Province: No state entered. Country: Sweden
Area of science: Computer Science
ID: 990641402.Cs

I´ve read that chesscomputerprograms can get better if they play with good 
players, i.e. they can learn!!!
How is this (if it´s true) possible (I´m stunned over the fact that the 
worldchampion in chess is a computerprogram!!!)?
I have read that the computer remembers all the playes it has won or part of 
them (which is it??????) and forgets the playes it lost, or psrt of it. If it is 
s psrt of a game it learn from - how does "it know" who many operations back it 
should remember.
In short: can you program a computer to LEARN and GET BETTER??????
Sincerely Mikael!!

Re: How can a (e.g.) chessprogram LEARN from playing with people?

Current Queue | Current Queue for Computer Science | Computer Science archives

Try the links in the MadSci Library for more information on Computer Science.

MadSci Home | Information | Search | Random Knowledge Generator | MadSci Archives | Mad Library | MAD Labs | MAD FAQs | Ask a ? | Join Us! | Help Support MadSci

MadSci Network,
© 1995-2001. All rights reserved.