loading...
Reinforcement Learning in Swarms that Learn
Compi?gne University of Technology, France September 19-September 22
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/IAT.2005.1452005 IEEE/WIC/ACM International Confe ...
 This Article 
 
PDF
HTML
 
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
James F. Peters, University of Manitoba Department of Electrical and Computer Engineering 15 Gillson St., Winnipeg, Manitoba, Canada R3T 5V6
Christopher Henry, University of Manitoba Department of Electrical and Computer Engineering 15 Gillson St., Winnipeg, Manitoba, Canada R3T 5V6
Sheela Ramanna, Department of Applied Computer Science University of Winnipeg Winnipeg, Manitoba R3B 2E9 Canada

This paper introduces an approach to reinforcement learning by cooperating agents using a variation of the actor critic method. This is made possible by considering behavior patterns of swarms in the context of approximation spaces. Rough set theory introduced by Zdzis - law Pawlak in 1982 provides a ground for deriving pattern-based rewards within approximation spaces. The framework provided by an approximation space makes it possible to derive pattern-based reference rewards used to estimate action preferences. Approximation spaces are used to derive action-based reference rewards at the swarm intelligence level. Two different forms of the actor critic reinforcement learning method are considered as a part of a study of learning in realtime by a swarm. The contribution of this article is the presentation of a new actor critic method defined in the context of approximation spaces. An ecosystem designed to facilitate study of reinforcement learning by swarms is briefly described. In addition, the results of ecosystem experiments for two forms of the actor critic method are given.

Citation:
James F. Peters, Christopher Henry, Sheela Ramanna, "Reinforcement Learning in Swarms that Learn," iat, pp.400-406, 2005 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT'05), 2005
Usage of this product signifies your acceptance of the Terms of Use.