Author: James Swafford
Date: 20:48:47 08/01/02
Go up one level in this thread
On August 01, 2002 at 02:56:30, Rémi Coulom wrote: >On August 01, 2002 at 00:12:28, Russell Reagan wrote: An interesting and relevant quote from Sutton: " For AI it is not enough merely to achieve a better system; it matters how the system was made. The reason it matters can ultimately be considered a practical one, one of scaling. An AI system too reliant on manual tuning, for example, will not be able to scale past what can be held in the heads of a few programmers. This, it seems to me, is essentially the situation we are in today in AI. Our AI systems are limited because we have failed to turn over responsibility for them to them. " -- James > >>If you know of any easier to understand resources for it, I'd love to read them. >>Websites, papers, books, whatever. As long as it's not gibberish to the average >>person. >> >>Russell > >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
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.