Automated observation of multi-agent based simulations: a statistical analysis approach - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Studia Informatica Universalis Year : 2012

Automated observation of multi-agent based simulations: a statistical analysis approach

Abstract

Multi-agent based simulations (MABS) have been successfully used to model complex systems in different areas. Nevertheless a pitfall of MABS is that their complexity increases with the number of agents and the number of different types of behavior considered in the model. For average and large systems, it is impossible to validate the trajectories of single agents in a simulation. The classical validation approaches, where only global indicators are evaluated, are too simplistic to give enough confidence in the simulation. It is then necessary to introduce intermediate levels of validation. In this paper we propose the use of data clustering and automated characterization of clusters in order to build, describe and follow the evolution of groups of agents in simulations. These tools provides the modeler with an intermediate point of view on the evolution of the model. Those tools are flexible enough to allow the modeler to define the groups level of abstraction (i.e. the distance between the groups level and the agents level) and the underlying hypotheses of groups formation. We give an online application on a simple NetLogo library model (Bank Reserves) and an offline log application on a more complex Economic Market Simulation.
Fichier principal
Vignette du fichier
SimAnalyzerSIUfinalv1.pdf (554.68 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-00738384 , version 1 (04-10-2012)

Identifiers

  • HAL Id : hal-00738384 , version 1

Cite

Philippe Caillou, Javier Gil-Quijano, Xiao Zhou. Automated observation of multi-agent based simulations: a statistical analysis approach. Studia Informatica Universalis, 2012, 10 (3), pp.62--86. ⟨hal-00738384⟩
332 View
235 Download

Share

Gmail Mastodon Facebook X LinkedIn More