Neural Comp. Sign up for ETOCS
HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
QUICK SEARCH:   [advanced]


     

This Article
Right arrow Full Text (PDF)
Right arrow Alert me when this article is cited
Right arrow Alert me if a correction is posted
Services
Right arrow Similar articles in this journal
Right arrow Alert me to new issues of the journal
Right arrow Download to citation manager
Right arrow reprints & permissions
Citing Articles
Right arrow Citing Articles via HighWire
Right arrow Citing Articles via Google Scholar
Google Scholar
Right arrow Articles by Dayan, P.
Right arrow Articles by Hinton, G. E.
Right arrow Search for Related Content
PubMed
Right arrow Articles by Dayan, P.
Right arrow Articles by Hinton, G. E.

Neural Computation, Vol 9, 271-278, Copyright © 1997 by The MIT Press

NOTES

Using Expectation-Maximization for Reinforcement Learning

Peter Dayan and Geoffrey E. Hinton

We discuss Hinton's (1989) relative payoff procedure (RPP), a static reinforcement learning algorithm whose foundation is not stochastic gradient ascent. We show circumstances under which applying the RPP is guaranteed to increase the mean return, even though it can make large changes in the values of the parameters. The proof is based on a mapping between the RPP and a form of the expectation-maximization procedure of Dempster, Laird, and Rubin (1977).


This article has been cited by other articles:


Home page
 The International Journal of Robotics ResearchHome page
J. Peters and S. Schaal
Learning to Control in Operational Space
The International Journal of Robotics Research, February 1, 2008; 27(2): 197 - 212.
[Abstract] [PDF]


HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
J COGNITIVE NEUROSCIENCE NEURAL COMPUTATION MIT PRESS JOURNALS
Copyright © 1997 by The MIT Press.