Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Hello from Edmonton (and on Temporal Differences)

Author: Russell Reagan

Date: 09:01:00 08/01/02

Go up one level in this thread


On August 01, 2002 at 02:56:30, Rémi Coulom wrote:

>The best introduction to reinforcement learning is Sutton and Barto's book. You
>will find an on-line version at Sutton's site, as well as a reinforcement
>learning FAQ.
>http://www-anw.cs.umass.edu/~rich/sutton.html
>The book has one section about TD-Gammon and one section about Samuel's checker
>program. It has some greek symbols, but I think they are really hard to avoid in
>any RL text! Many chapters are understandable without mathematical knowledge.
>
>Rémi

Thanks, I will check it out. I'm not opposed entirely to all of the math symbols
and predicate logic stuff, but I probably won't understand it unless it's either
simple, or I already understand the material being discussed. For example, if I
read a paper that described alpha-beta in those terms, I could probably figure
out what it was gettig at. Thanks again.

Russell



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.