Referenced Items are not available for this document.
The authors consider the problem of model-free control via a reinforcement learning method that uses, as additional learning information, the distance between sampled and represented states, embedded in actions that are the result of a distancewise local interpolation scheme over states. Fast learning and a reduced number of trials resulted, as demonstrated in the real-time control of a magnetic levitation system
Published in:
Electronics Letters
(Volume:34
,
Issue:
21
)
Date of Publication: 15 Oct 1998
- Page(s):
- 2070 - 2071
- ISSN :
- 0013-5194
- INSPEC Accession Number:
- 6078224
- Digital Object Identifier :
- 10.1049/el:19981423
- Product Type:
- Journals & Magazines
- Date of Current Version :
- 06 August 2002
- Issue Date :
- 15 Oct 1998
- Sponsored by :
- Institution of Engineering and Technology
About IEEE Xplore | Contact | Help | Terms of Use | Nondiscrimination Policy | Site Map | Privacy & Opting Out of Cookies
A not-for-profit organization, IEEE is the world's largest professional association for the advancement of technology.
© Copyright 2013 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.
