Using Machine Learning to Optimize Multi-objective Infectious Disease Control
Loading...
Date
2023-05
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Ohio State University
Abstract
Since Non-pharmaceutical interventions (NPIs) are the key tools that we have for combatting outbreaks and they often have substantial costs, it is important to investigate a better policy that can balance the cost and the effectiveness. We believe supervised learning can help us to find a better disease control policy that will directly reduce the infected rate of SARS-CoV-2 with an affordable cost. Additionally, optimizing contact tracing policy can be viewed as a multi-objective reinforcement learning problem and we show the potential of using reinforcement learning for this optimization problem.