Application of reinforcement learning for effective vaccination strategies of coronavirus disease 2019 (COVID-19)

Abstract

Since December 2019, the new coronavirus has raged in China and subsequently all over the world. From the first days, researchers have tried to discover vaccines to combat the epidemic. Several vaccines are now available as a result of the contributions of those researchers. As a matter of fact, the available vaccines should be used in effective and efficient manners to put the pandemic to an end. Hence, a major problem now is how to efficiently distribute these available vaccines among various components of the population. Using mathematical modeling and reinforcement learning control approaches, the present article aims to address this issue. To this end, a deterministic Susceptible-Exposed-Infectious-Recovered-type model with additional vaccine components is proposed. The proposed mathematical model can be used to simulate the consequences of vaccination policies. Then, the suppression of the outbreak is taken to account. The main objective is to reduce the effects of Covid-19 and its domino effects which stem from its spreading and progression. Therefore, to reach optimal policies, reinforcement learning optimal control is implemented, and four different optimal strategies are extracted. Demonstrating the efficacy of the proposed methods, finally, numerical simulations are presented.

Modeling and optimal control of mutated COVID-19 (Delta strain) with imperfect vaccination

“…The fractional derivative can be regarded as the globalization of the integral derivative, which can show more properties that the integral derivative does not have. Many scholars have applied fractional derivative differential equations to study the spread of COVID-19, and many important research results have been obtained [31] , [32] , [33] , [34] , [35] , [36] . If we consider fractional COVID-19 model for parameter estimation, different results with higher fitting degree may be obtained, and the measures taken may be changed.…”

“…One of the important ideas is to study the spread of COVID-19 through mathematical models. To that end, a number of mathematical models have been developed over the past two years to study local infections, estimate peaks in the number of people infected, and suggest ways to control the spread of the disease [7] , [8] , [9] , [10] , [11] , [12] , [13] , [14] , [15] , [16] , [28] , [29] , [30] , [31] , [32] , [33] , [34] , [35] , [36] , [37] , [38] , [39] , [40] .…”

HRL4EC: Hierarchical reinforcement learning for multi-mode epidemic control

“…The epidemic modeling mainly falls into three main categories, i.e., compartmental epidemiological models [6] , [7] , agent-based models [8] , [9] , and machine learning enabled models [10] , [11] . While epidemic control roughly includes two types of interventions, i.e., pharmacological interventions [12] , [13] , [14] , and non-pharmacological interventions [15] , [16] , [17] . Since dynamics and uncertainty accompany epidemic transmission, the rule-of-thumb intervention strategy is not flexible enough for the transient epidemic.…”

Optimal control and cost-effectiveness analysis for a COVID-19 model with individual protection awareness

“…Some strategies have been implemented to control the COVID-19 such as wearing masks [24] , washing hands frequently, maintaining a certain social distance [25] , spraying disinfectant in the environment and vaccinating the entire population [26] . These measures are found to be effective in reducing the number of people infected with COVID-19 [27] .…”