This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
2005 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT'05)
Generating Adequate Representations for Learning from Interaction in Complex Multiagent Simulations
Compi?gne University of Technology, France
September 19-September 22
ISBN: 0-7695-2416-8
ASCII Text
x 
 
Charles Madiera, Vincent Corruble, Geber Ramalho, "Generating Adequate Representations for Learning from Interaction in Complex Multiagent Simulations," Intelligent Agent Technology, IEEE / WIC / ACM International Conference on, pp. 512-515, 2005 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT'05), 2005.
 
 
BibTex
x
 
@article{ 10.1109/IAT.2005.79,
author = {Charles Madiera and Vincent Corruble and Geber Ramalho},
title = {Generating Adequate Representations for Learning from Interaction in Complex Multiagent Simulations},
journal ={Intelligent Agent Technology, IEEE / WIC / ACM International Conference on},
volume = {0},
year = {2005},
isbn = {0-7695-2416-8},
pages = {512-515},
doi = {http://doi.ieeecomputersociety.org/10.1109/IAT.2005.79},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Intelligent Agent Technology, IEEE / WIC / ACM International Conference on
TI - Generating Adequate Representations for Learning from Interaction in Complex Multiagent Simulations
SN - 0-7695-2416-8
SP512
EP515
A1 - Charles Madiera,
A1 - Vincent Corruble,
A1 - Geber Ramalho,
PY - 2005
KW - null
VL - 0
JA - Intelligent Agent Technology, IEEE / WIC / ACM International Conference on
ER -
 
Charles Madiera, Laboratoire d'Informatique de Paris 6, Unibversite Pierre et Marie Curie, Paris Cedex France
Vincent Corruble, Laboratoire d'Informatique de Paris 6, Unibversite Pierre et Marie Curie, Paris Cedex France
Geber Ramalho, Centro de Informatica, Universidad Federal de Pernambuco, Caixa Postal,Brazil

Wargames are an example of complex multiagent simulations for which, specifying agent behavior adequately in advance for all potential situations is not feasible. In this context, we have applied reinforcement learning as an adaptive approach to design strategies for these similations. In this paper, we introduce our approach and focus on a novel algorithm for generating representations with adequate granularities for commanders of a military hierarchy.

Citation:
Charles Madiera, Vincent Corruble, Geber Ramalho, "Generating Adequate Representations for Learning from Interaction in Complex Multiagent Simulations," iat, pp.512-515, 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.