A Reinforcement Learning-Based Coronavirus Herd Immunity Optimizer for PFSP
摘要
The basic reproduction rate holds a pivotal position as a crucial control parameter within the Coronavirus Herd Immunity Optimizer (CHIO). It serves as a determinant for the operators employed in the CHIO and exerts a direct and significant influence on both the performance and convergence characteristics of the algorithm. A Reinforcement Learning-based Coronavirus Herd Immunity Optimizer (RLCHIO) is introduced. Under the control of the reinforcement learning strategy, the value of the basic reproduction rate can automatically select a different value according to the current state of the population. The proposed algorithm was tested on different permutation flow shop scheduling problems (PFSP). The experimental results show that the RLCHIO exhibits better optimization capabilities in solving PFSP.