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

TL;DR

This paper introduces a machine learning-based statistical framework to efficiently optimize policies in complex agent-based models of environmental systems, demonstrated on a resource harvesting model.

Contribution

It presents a novel combination of sensitivity testing and reinforcement learning to accelerate policy optimization in computationally expensive ABMs.

Findings

Rapid identification of optimal policies

Improved policy performance over baseline methods

Insightful sensitivity and dynamic analysis

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.