Evolution of Wandering Behavior in a Multi Agent System: An Experiment

In this article we discuss our approach to the evolution of wandering behavior in a multi agent system (MAS). Our discussion covers the various aspects of the system setup, the performed experiments and the interpre- tation of the results observed. Utilizing a genetic algorithm (GA) and multi layer perceptrons (ANN) we show how wandering behavior is developed provided a single fitness criterion. Finally we conclude by reviewing the proposed experiment and point out some future directions of research.