Modèles de Substitution pour les Modèles à base d'Agents : Enjeux, Méthodes et Applications
Paul Saves, Nicolas Verstaevel, Benoît Gaudou
TL;DR
Ce papier traite du coût élevé des simulations multi-agent et propose des modèles de substitution comme solution efficace pour des analyses à grande échelle et en temps réel. Il compare plusieurs approches d apprentissage automatique, incluant des Gaussian Process surrogates, des forêts et des réseaux neuronaux, en mettant l'accent sur la quantification de l'incertitude et l'explicabilité. Une étude de cas sur un modèle de ségrégation illustre les défis de fiabilité, de validation et d'interprétation des prédictions issues des substituts appris à partir de jeux de données parcimonieux. Les résultats suggèrent que les méthodes basées sur GP, RF et RBF offrent de bons compromis entre précision et interprétabilité, et que les outils explicatifs comme SHAP, PDP et ICE facilitent l'interprétation des effets des paramètres.
Abstract
Multi-agent simulations enables the modeling and analyses of the dynamic behaviors and interactions of autonomous entities evolving in complex environments. Agent-based models (ABM) are widely used to study emergent phenomena arising from local interactions. However, their high computational cost poses a significant challenge, particularly for large-scale simulations requiring extensive parameter exploration, optimization, or uncertainty quantification. The increasing complexity of ABM limits their feasibility for real-time decision-making and large-scale scenario analysis. To address these limitations, surrogate models offer an efficient alternative by learning approximations from sparse simulation data. These models provide cheap-to-evaluate predictions, significantly reducing computational costs while maintaining accuracy. Various machine learning techniques, including regression models, neural networks, random forests and Gaussian processes, have been applied to construct robust surrogates. Moreover, uncertainty quantification and sensitivity analysis play a crucial role in enhancing model reliability and interpretability. This article explores the motivations, methods, and applications of surrogate modeling for ABM, emphasizing the trade-offs between accuracy, computational efficiency, and interpretability. Through a case study on a segregation model, we highlight the challenges associated with building and validating surrogate models, comparing different approaches and evaluating their performance. Finally, we discuss future perspectives on integrating surrogate models within ABM to improve scalability, explainability, and real-time decision support across various fields such as ecology, urban planning and economics.