Mod`eles de Substitution pour les Mod`eles `a base d'Agents : Enjeux, M'ethodes et Applications

2025-05-17

AI Summary

Agent-based models (ABMs) suffer from high computational costs, hindering large-scale parameter exploration and real-time decision support. Method: This study proposes a lightweight, interpretable surrogate modeling framework that systematically integrates uncertainty quantification and global sensitivity analysis to jointly optimize accuracy, efficiency, and interpretability. The framework is validated across diverse base models—including regression, Gaussian processes, random forests, and neural networks—and benchmarked against the Schelling segregation model for cross-method performance evaluation. Contribution/Results: Experiments demonstrate that the proposed approach maintains fidelity in capturing emergent behaviors while reducing computational overhead by one to two orders of magnitude. It enables real-time simulation and scenario analysis at scales exceeding one thousand configurations. The method exhibits strong scalability and robustness in ecological modeling, urban planning, and economic simulation applications.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

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.

Problem

• High computational cost of agent-based models limits large-scale simulations
• Surrogate models reduce computational costs while maintaining accuracy
• Integrating surrogate models improves scalability and real-time decision support

Innovation

• Surrogate models reduce ABM computational costs
• Machine learning techniques approximate simulation data
• Uncertainty quantification enhances model reliability