Some challenges of calibrating differentiable agent-based models

2023/07/03 by Arnau Quera-Bofarull, Joel Dyer, Quera-Bofarull, Arnau +5
Computer Science · Decision Sciences · #Artificial Intelligence (cs.AI) #Complex Systems and Decision Making #FOS: Computer and information sciences #FOS: Economics and business #Machine Learning (stat.ML) #Multi-Agent Systems and Negotiation #Multiagent Systems (cs.MA) #Semantic Web and Ontologies #Trading and Market Microstructure (q-fin.TR)

paper · pdf · doi:10.48550/arxiv.2307.01085

openalex publication_date 2023/07/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Agent-based models (ABMs) are a promising approach to modelling and reasoning about complex systems, yet their application in practice is impeded by their complexity, discrete nature, and the difficulty of performing parameter inference and optimisation tasks. This in turn has sparked interest in the construction of differentiable ABMs as a strategy for combatting these difficulties, yet a number of challenges remain. In this paper, we discuss and present experiments that highlight some of these challenges, along with potential solutions.

Related

• Bayesian calibration of differentiable agent-based models
• Automatic Differentiation of Agent-Based Models
• Surrogate Assisted Methods for the Parameterisation of Agent-Based\n Models
• Validation and Inference of Agent Based Models
• Automatic Calibration Framework of Agent-Based Models for Dynamic and Heterogeneous Parameters