Learning Pareto-Optimal Pandemic Intervention Policies with MORL

2025-10-02

AI Summary

Public health crises pose a fundamental trade-off between epidemic control and socioeconomic stability. To address this, we propose a multi-objective reinforcement learning framework integrated with a high-fidelity stochastic differential equation–based epidemiological simulator, enabling Pareto-optimal intervention policy learning across multiple pathogens (SARS-CoV-2, polio, influenza, measles). We introduce a novel Pareto-conditioned network agent that explicitly models how pathogen transmission dynamics—such as basic reproduction number and immunity waning—shape policy preferences, and quantifies the nonlinear impact of declining vaccination coverage on control costs. Calibrated and validated against global COVID-19 data, the framework yields interpretable, transferable policies: for instance, a 5% drop in vaccination coverage necessitates substantially stricter—and costlier—non-pharmaceutical interventions. Our approach enhances transparency, adaptability, and scientific rigor in public health decision-making.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Humans and AI: Learning Human Values and Preferences
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The COVID-19 pandemic underscored a critical need for intervention strategies that balance disease containment with socioeconomic stability. We approach this challenge by designing a framework for modeling and evaluating disease-spread prevention strategies. Our framework leverages multi-objective reinforcement learning (MORL) - a formulation necessitated by competing objectives - combined with a new stochastic differential equation (SDE) pandemic simulator, calibrated and validated against global COVID-19 data. Our simulator reproduces national-scale pandemic dynamics with orders of magnitude higher fidelity than other models commonly used in reinforcement learning (RL) approaches to pandemic intervention. Training a Pareto-Conditioned Network (PCN) agent on this simulator, we illustrate the direct policy trade-offs between epidemiological control and economic stability for COVID-19. Furthermore, we demonstrate the framework's generality by extending it to pathogens with different epidemiological profiles, such as polio and influenza, and show how these profiles lead the agent to discover fundamentally different intervention policies. To ground our work in contemporary policymaking challenges, we apply the model to measles outbreaks, quantifying how a modest 5% drop in vaccination coverage necessitates significantly more stringent and costly interventions to curb disease spread. This work provides a robust and adaptable framework to support transparent, evidence-based policymaking for mitigating public health crises.

Problem

• Balancing disease containment with socioeconomic stability during pandemics
• Developing high-fidelity pandemic simulation using multi-objective reinforcement learning
• Creating adaptable intervention policies for different pathogens and vaccination scenarios

Innovation

• Multi-objective reinforcement learning optimizes pandemic policies
• Stochastic differential equation simulator enhances outbreak modeling
• Pareto-conditioned network agent balances health and economy