Optimal control problem of various epidemic models with uncertainty based on deep reinforcement learning

Abstract

We investigate an optimal control problem of various epidemic models with uncertainty using stochastic differential equations, random differential equations, and agent-based models. We discuss deep reinforcement learning (RL), which combines RL with deep neural networks, as one method to solve the optimal control problem. The deep Q-network algorithm is introduced to approximate an action-value function and consequently obtain the optimal policy. Numerical simulations show that in order to effectively prevent the spread of infectious diseases, it is essential to vaccinate at the highest rate for the first few days and then gradually reduce the rate.

A Statistical Moment-Based Spectral Approach to the Chance-Constrained Stochastic Optimal Control of Epidemic Models

“…The optimal vaccination strategy for an hepatitis B epidemic model with the inclusion of white noise and Markovian switching is analysed in [22]. Several OCPs for various epidemic models with uncertainty are formulated in [23], which are solved using deep reinforcement learning. A robust economic model predictive controller for the management of stochastic epidemic processes is developed in [24], which efficiently drives the epidemic process to extinction while minimizing the use of control resources.…”