Optimal Resource Allocation during Epidemics using Reinforcement Learning

Epidemics can prove to be disastrous, which has been further emphasized by the recent COVID-19 pandemic, and several countries like India lack sufficient resources to meet the population's needs. It is therefore important that the limited testing and protective resources are utilized such that the disease spread is minimized and their reach to the most vulnerable demographic is maximized. This paper studies the scope of intelligent agents in aiding authorities with such policy-making decisions. This is done by exploring the performance of various action selection methods on custom environments dealing with socio-economic groups and Indian states. Experiments using multi-armed bandit techniques provide greater insight into administrative decisions surrounding resource allocation and their future potential for greater use in similar scenarios.