Path: utzoo!attcan!uunet!wuarchive!uwm.edu!uwvax!ai.cs.wisc.edu!finton
From: finton@ai.cs.wisc.edu (David J. Finton)
Newsgroups: comp.ai.neural-nets
Subject: tasks for reinforcement learning
Message-ID: <11054@spool.cs.wisc.edu>
Date: 15 Aug 90 17:28:08 GMT
Sender: news@spool.cs.wisc.edu
Distribution: all
Organization: U of Wisconsin CS Dept
Lines: 17

I'm looking for good demonstration tasks for my 
reinforcement-learning algorithm:

(1) Are there any good examples of real-world tasks which
require reinforcement learning -- where supervised techniques
such as back-prop would be unsuitable?

(2) Are there any studies which compare performance of 
reinforcement learning systems with standard techniques
(eg, back-prop, ID3) on such tasks?

(3) Are there available standard data sets for such tasks?

(4) Are there studies comparing reinforcement learning on 
with back-prop on standard back-prop tasks?

David Finton