Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Communication during learning in heterogeneous teams of learning agents

Communication during learning in heterogeneous teams of learning agents The objective of this work is to determine how/if learning agents can benefit from exchanging information during learning in problems where each team uses a different learning algorithm. In recent studies several problems were exposed, such as lack of coordination, exchange of useless information and difficulties in the adequate choice of advisors. In this work we propose new solutions and test them in two different domains (predator-prey and traffic-control). Our solutions involve hybrid algorithms derived from Q-Learning and Evolutionary Algorithms. Results indicate that some combinations of learning algorithms are more suited to the use of external information than others and that the difference in the results achieved, with and without communication, is problem dependent. The results also show that, in situations where communication is useful, the gain in quality and learning-time can be significant if the right combination of techniques is used to process external information. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Intelligent Decision Technologies IOS Press

Communication during learning in heterogeneous teams of learning agents

Loading next page...
 
/lp/ios-press/communication-during-learning-in-heterogeneous-teams-of-learning-rlG585QFKH

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
IOS Press
Copyright
Copyright © 2008 by IOS Press, Inc
ISSN
1872-4981
eISSN
1875-8843
Publisher site
See Article on Publisher Site

Abstract

The objective of this work is to determine how/if learning agents can benefit from exchanging information during learning in problems where each team uses a different learning algorithm. In recent studies several problems were exposed, such as lack of coordination, exchange of useless information and difficulties in the adequate choice of advisors. In this work we propose new solutions and test them in two different domains (predator-prey and traffic-control). Our solutions involve hybrid algorithms derived from Q-Learning and Evolutionary Algorithms. Results indicate that some combinations of learning algorithms are more suited to the use of external information than others and that the difference in the results achieved, with and without communication, is problem dependent. The results also show that, in situations where communication is useful, the gain in quality and learning-time can be significant if the right combination of techniques is used to process external information.

Journal

Intelligent Decision TechnologiesIOS Press

Published: Jan 1, 2008

There are no references for this article.