BEN : An Agent Architecture for Explainable and Expressive Behavior in Social Simulation

Mathieu Bourgais (1) , Patrick Taillandier (2) , Laurent Vercouter (3)

1 MIND - LITIS - Equipe Multi-agent, Interaction, Décision
2 UMMISCO - Unité de modélisation mathématique et informatique des systèmes complexes [Bondy]
3 Mines Saint-Étienne MSE - École des Mines de Saint-Étienne

Social Simulations are used to study complex systems featuring human actors. This means reproducing real-life situations involving people in order to explain an observed behavior. However, there are actually no agent architectures among the most popular platforms for agent-based simulation enabling to easily model human actors. This situation leads modelers to implement simple reactive behaviors while the EROS principle (Enhancing Realism Of Simulation) fosters the use of psychological and social theory to improve the credibility of such agents. This paper presents the BEN architecture (Behavior with Emotions and Norms) that uses cognitive, affective and social dimensions for the behavior of social agents. This agent architecture has been implemented in the GAMA platform so it may be used by a large audience to model agents with a high level explainable behavior. This architecture is used on an evacuation case, showing how it creates believable behaviors in a real case scenario.

Domaines: Modélisation et simulation; Intelligence artificielle [cs.AI]; Système multi-agents [cs.MA]

Mathieu Bourgais, Patrick Taillandier, Laurent Vercouter. BEN : An Agent Architecture for Explainable and Expressive Behavior in Social Simulation. EXTRAAMAS, May 2019, Montréal, Canada. ⟨hal-02283816⟩