Modeling and control of COVID-19 disease using deep reinforcement learning method

The prevalence of epidemics has been studied by researchers in various fields. In the last 2 years, the outbreak of COVID-19 has affected the health, economy, and industry of communities around the world and has caused the death of millions of people. Therefore, many researchers have tried to model and control the prevalence of this disease. In this article, the new SQEIAR model for the spread of the COVID-19 disease is provided, which, compared to previous models, explores the effects of additional interventions on the outbreak and incorporates a wider range of variables and parameters to enhance its accuracy and alignment with reality. These modifications in the model lead to a more rapid eradication and control of the disease. This model includes six variables of the group of susceptible, quarantined, exposed, symptomatic, asymptomatic, and recovered individuals and includes three control inputs such as quarantine of susceptible, vaccination, and treatments. In order to minimize symptomatic infectious individuals and susceptible individuals and also to reduce treatment, vaccination, and quarantine costs, an optimal control approach using the Deep Deterministic Policy Gradient (DDPG) method has been applied to the system. This algorithm is applied to the model in different cases of control inputs, and for each case, optimal control inputs are obtained. In the following, the number of deaths due to the disease and the total number of symptomatic infectious individuals for each of these optimal control cases has been calculated. The results of the implemented control structure demonstrated a reduction of 60% in the number of deaths and 74% in the number of symptomatically infected individuals compared to the uncontrolled model. Finally, to test the performance of the control system, noise was applied to the system in various ways, including three methods: applying noise to observer variables, applying noise to control inputs, and applying uncertainty to model parameters. Therefore, we found that this control system was robust and performed well in different conditions despite the disturbance.