Some challenges of calibrating differentiable agent-based models
Multiagent Systems
2023-07-04 v1 Artificial Intelligence
Trading and Market Microstructure
Machine Learning
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.
Cite
@article{arxiv.2307.01085,
title = {Some challenges of calibrating differentiable agent-based models},
author = {Arnau Quera-Bofarull and Joel Dyer and Anisoara Calinescu and Michael Wooldridge},
journal= {arXiv preprint arXiv:2307.01085},
year = {2023}
}
Comments
Accepted at the ICML 2023 Differentiable Almost Everything Workshop