Computer Modeling of the Dynamics of Epidemiological Processes

The paper analyzes dynamic models with a delay in describing the processes of epidemics. The introduction of a delay makes it possible to make models adequate for natural processes. SIR simulations of the lag model describing the COVID-19 pandemic showed that the numerical results agree with the data. Utilizing reinforcement learning approaches to model virus spread presents a complex challenge due to numerous uncertainties and fluctuations. Nevertheless, some methodologies allow the application of reinforcement learning to accurately model disease dynamics, which have shown promise in forecasting the spread of COVID-19 and adapting public health policies.