A Microscopic Pandemic Simulator for Pandemic Prediction Using Scalable Million-Agent Reinforcement Learning

TL;DR

This paper introduces a scalable microscopic epidemic simulation model powered by deep reinforcement learning, enabling realistic prediction of outbreak dynamics and evaluation of government strategies with millions of agents.

Contribution

It presents a novel microscopic epidemic model using DRL with scalable agent simulation, improving realism and policy evaluation capabilities.

Findings

The model accurately predicts epidemic dynamics in real-world data.

It effectively evaluates government strategies like quarantine and information disclosure.

The approach demonstrates scalability to millions of agents.

Abstract

Microscopic epidemic models are powerful tools for government policy makers to predict and simulate epidemic outbreaks, which can capture the impact of individual behaviors on the macroscopic phenomenon. However, existing models only consider simple rule-based individual behaviors, limiting their applicability. This paper proposes a deep-reinforcement-learning-powered microscopic model named Microscopic Pandemic Simulator (MPS). By replacing rule-based agents with rational agents whose behaviors are driven to maximize rewards, the MPS provides a better approximation of real world dynamics. To efficiently simulate with massive amounts of agents in MPS, we propose Scalable Million-Agent DQN (SMADQN). The MPS allows us to efficiently evaluate the impact of different government strategies. This paper first calibrates the MPS against real-world data in Allegheny, US, then demonstratively evaluates two government strategies: information disclosure and quarantine. The results validate the effectiveness of the proposed method. As a broad impact, this paper provides novel insights for the application of DRL in large scale agent-based networks such as economic and social networks.