Generating adequate representations for learning from interaction in complex multiagent simulations
Madeira, C.
Corruble, V.
Ramalho, G.
Lab. d'Informatique, Univ. Pierre et Marie Curie, Paris, France;
This paper appears in: Intelligent Agent Technology, IEEE/WIC/ACM International Conference on
Publication Date: 19-22 Sept. 2005
On page(s): 512- 515
ISBN: 0-7695-2416-8
INSPEC Accession Number: 8705547
Digital Object Identifier: 10.1109/IAT.2005.79
Current Version Published: 2006-01-03
Abstract
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 simulations. 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.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
