Interpretable AI for policy-making in pandemics

TL;DR

This paper introduces an interpretable hybrid AI approach combining reinforcement learning and evolutionary computation to generate effective, simple pandemic policies that outperform previous methods and traditional government strategies in simulations.

Contribution

It presents a novel hybrid AI method for creating transparent, effective pandemic policies, addressing the black-box limitations of prior machine learning approaches.

Findings

Our approach yields highly effective, simple policies in simulations.

The generated policies outperform previous AI and government strategies.

Policies are interpretable and suitable for real-world application.

Abstract

Since the first wave of the COVID-19 pandemic, governments have applied restrictions in order to slow down its spreading. However, creating such policies is hard, especially because the government needs to trade-off the spreading of the pandemic with the economic losses. For this reason, several works have applied machine learning techniques, often with the help of special-purpose simulators, to generate policies that were more effective than the ones obtained by governments. While the performance of such approaches are promising, they suffer from a fundamental issue: since such approaches are based on black-box machine learning, their real-world applicability is limited, because these policies cannot be analyzed, nor tested, and thus they are not trustable. In this work, we employ a recently developed hybrid approach, which combines reinforcement learning with evolutionary computation, for the generation of interpretable policies for containing the pandemic. These policies, trained on an existing simulator, aim to reduce the spreading of the pandemic while minimizing the economic losses. Our results show that our approach is able to find solutions that are extremely simple, yet very powerful. In fact, our approach has significantly better performance (in simulated scenarios) than both previous work and government policies.