Research

Paper

TESTING February 19, 2026

Environmental policy in the context of complex systems: Statistical optimization and sensitivity analysis for ABMs

Authors

Dylan Munson, Arijit Dey, Simon Mak

Abstract

Coupled human-environment systems are increasingly being understood as complex adaptive systems (CAS), in which micro-level interactions between components lead to emergent behavior. Agent-based models (ABMs) hold great promise for environmental policy design by capturing such complex behavior, enabling a sophisticated understanding of potential interventions. One limitation, however, is that ABMs can be computationally costly to simulate, which hinders their use for policy optimization. To address this, we propose a new statistical framework that exploits machine learning techniques to accelerate policy optimization with costly ABMs. We first develop a statistical approach for sensitivity testing of the optimal policy, then leverage a reinforcement learning method for efficient policy optimization. We test this framework on the classic ``Sugarscape'' model, an ABM for resource harvesting. We show that our approach can quickly identify optimal and interpretable policies that improve upon baseline techniques, with insightful sensitivity and dynamic analyses that connect back to economic theory.

Metadata

arXiv ID: 2602.17079
Provider: ARXIV
Primary Category: stat.AP
Published: 2026-02-19
Fetched: 2026-02-21 18:51

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.17079v1</id>\n    <title>Environmental policy in the context of complex systems: Statistical optimization and sensitivity analysis for ABMs</title>\n    <updated>2026-02-19T04:56:29Z</updated>\n    <link href='https://arxiv.org/abs/2602.17079v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.17079v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Coupled human-environment systems are increasingly being understood as complex adaptive systems (CAS), in which micro-level interactions between components lead to emergent behavior. Agent-based models (ABMs) hold great promise for environmental policy design by capturing such complex behavior, enabling a sophisticated understanding of potential interventions. One limitation, however, is that ABMs can be computationally costly to simulate, which hinders their use for policy optimization. To address this, we propose a new statistical framework that exploits machine learning techniques to accelerate policy optimization with costly ABMs. We first develop a statistical approach for sensitivity testing of the optimal policy, then leverage a reinforcement learning method for efficient policy optimization. We test this framework on the classic ``Sugarscape'' model, an ABM for resource harvesting. We show that our approach can quickly identify optimal and interpretable policies that improve upon baseline techniques, with insightful sensitivity and dynamic analyses that connect back to economic theory.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='stat.AP'/>\n    <published>2026-02-19T04:56:29Z</published>\n    <arxiv:primary_category term='stat.AP'/>\n    <author>\n      <name>Dylan Munson</name>\n    </author>\n    <author>\n      <name>Arijit Dey</name>\n    </author>\n    <author>\n      <name>Simon Mak</name>\n    </author>\n  </entry>"
}