Calibration of Multi-Agent Simulations through a Participatory Experiment - Laboratoire Interdisciplinaire des Sciences du Numérique Access content directly
Conference Papers Year : 2015

Calibration of Multi-Agent Simulations through a Participatory Experiment

Abstract

In the context of agent-based simulation, a major issue is to define relevant parameters of the agent model and calibrate them. In this paper, we propose to log and analyse agents behaviours to evaluate their similarity to humans behaviours in an immersive virtual environment. The behaviour archetypes are studied in terms of cluster members in order to identify agent missing behaviours, capacities and errors. This study enables to (1) dismiss invalid parameter sets, (2) calibrate valid simulations and (3) explain lacks in the agent models for further improvement.
Fichier principal
Vignette du fichier
ea139-darty_2.pdf (181.95 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01159551 , version 1 (03-06-2015)

Identifiers

  • HAL Id : hal-01159551 , version 1

Cite

Kévin Darty, Julien Saunier, Nicolas Sabouret. Calibration of Multi-Agent Simulations through a Participatory Experiment. 14th International Conference on Autonomous Agents and Multiagent Systems, May 2015, Istanbul, Turkey. pp.1683-1684. ⟨hal-01159551⟩
166 View
82 Download

Share

Gmail Facebook X LinkedIn More