Home   >   CSC-OpenAccess Library   >    Manuscript Information
Full Text Available

(1.55MB)
This is an Open Access publication published under CSC-OpenAccess Policy.
Publications from CSC-OpenAccess Library are being accessed from over 74 countries worldwide.
Using Learning Automata in Coordination Among Heterogeneous Agents in a Complex Multi-Agent Domain
Mohammadreza Khojasteh, Aida Kazimi
Pages - 39 - 59     |    Revised - 15-05-2012     |    Published - 20-06-2012
Volume - 3   Issue - 3    |    Publication Date - June 2012  Table of Contents
MORE INFORMATION
KEYWORDS
Distributed Artificial Intelligence, Learning Automata, Coordination, Heterogeneous Agents, RoboCup Rescue Simulation
ABSTRACT
This paper describes our use of Learning Automata as a reinforcement learning method in coordination among three heterogeneous teams of agents acting in RoboCup Rescue Simulation environment. We provide a brief introduction to Learning Automata and Cellular Learning Automata, the reinforcement machine learning methods that we have used in lots of parts of our agents’ development. Then we will describe the major challenges each team of agents should be concerned about in such a complex domain and for each challenge, we propose our approaches to develop cooperative teams. Finally, some results of using Learning Automata in coordinating these heterogeneous teams of agents that cooperate to mitigate the disastrous damages in a simulated city are evaluated.
1 Google Scholar 
2 CiteSeerX 
3 refSeek 
4 Scribd 
5 SlideShare 
6 PdfSR 
1 M. R. Khojasteh. “Cooperation in multi-agent systems using Learning Automata.” M.A. thesis, Amirkabir University of Technology, Iran, 2002.
2 M. R. Khojasteh, M. R. Meybodi. “Using Learning Automata in Cooperation among Agents in a Team.” In Proc. the 12th Portuguese Conference on Artificial Intelligence, 2005, pp. 306-312.
3 M. R. Khojasteh, M. R. Meybodi. “Evaluating Learning Automata as a Model for Cooperation in Complex Multi-Agent Domains,” in RoboCup-2006: Robot Soccer World Cup X. G. Lakemeyer, E. Sklar, D. Sorenti, and T. Takahashi, Eds. Berlin: Springer-Verlag, 2007, pp. 410-417.
4 “RoboCup.” Internet: www.robocup.org.
5 Z. Luo, Q. Cao and Y. Zhao. “A Self-adaptive Predictive Policy for Pursuit-evasion Game.” Information Science and Engineering, Vol. 24, pp. 1397-1407, 2008.
6 S. B. M. Post, M. L. Fassaert. “A communication and coordination model for RoboCup Rescue agents,” M.A. thesis, Universiteit Van Amsterdam (UvA), Netherlands, 2004.
7 K.S. Narendra, M.A.L. Thathachar. Learning Automata: An Introduction. Prentice Hall, 1989.
8 M. Taherkhani. “Proposing and Studying Cellular Learning Automata as a Tool for Modeling Systems.” M.A. thesis, Amirkabir University of Technology, Iran, 2000.
9 M. R. Meybodi, M. R. Khojasteh. “Cellular Learning Automata as a model for Commerce Networks.” In Proc. 6th annual conference of Computer Society of Iran (CSICC'2001), 2001, pp. 268-281.
10 S. Wolfrom. Theory and Application of Cellular Automata. World Scientific Publishing, Singapore, 1986.
11 M. R. Khojasteh, M. R. Meybodi. “The Best Corner in State Square technique for generalization of environmental states in a cooperative multi-agent domain.” In Proc. 8th annual conference of Computer Society of Iran (CSICC'2003), 2003, pp. 446-455.
12 P. Stone. “Layered Learning in Multi_Agent Systems.” Ph.D. thesis, Carnegie Mellon University, USA, 1998.
13 M. Brenner, A. Kleiner, M. Exner, M. Degen, M. Metzger, T. Nussle, and I. Thon. “Resq Freiburg: Deliberative limitation of damage.” Team Description Paper, 2004.
14 S.A. Amraii, B. Behsaz, M. Izadi, H. Janzadeh, F. Molazem, A. Rahimi, M.T. Ghinani, and H. Vosoughpour. “S.O.S. 2004: An attempt towards a multi-agent rescue team.” Team Description Paper, 2004.
15 T.H. Cormen, C.E. Leiserson, and R.L. Rivest. Introduction to Algorithms. MIT Press, McGraw-Hill, New York, NY, 1990.
16 A.A. Bitaghsir, F. Taghiyareh, A. Simjour, A. Mazloumian, and B. Bostan. “Layered learning in robocup rescue simulation.” Team Description Paper, 2004.
17 B Eker, H.L. Akin. “Roboakut 2004 rescue team.” Team Description Paper, 2004. [
18 C. Skinner, J. Teutenberg, G. Cleveland, M. Barley, H. Guesgen, P. Riddle, and U. Loerch. “The black sheep team.” Team Description Paper, 2004.
Mr. Mohammadreza Khojasteh
Department of Computer Engineering, Shiraz Branch, Islamic Azad University - Iran
khojasteh@iaushiraz.ac.ir
Mr. Aida Kazimi
Department of Computer Engineering, Shiraz Branch, Islamic Azad University - Iran