An Automatic Configuration Memetic Algorithm with Reinforcement Learning Mechanism for Real-value Optimization Problems

Abstract

With the development of reinforcement learning technology, reinforcement learning is utilized in many areas. The real-value optimization problem is common and difficult in manufacturing. In this study, a memetic algorithm (called ACMA) with reinforcement learning mechanism is designed for solving real-value optimization problems. The multi-heuristic pool which contains various heuristic algorithms is employed in ACMA to realize the automatic configuration of global and local search algorithms via Q-learning. The process of ACMA is mainly divided into two phases, including the training phase and the testing phase. The effective heuristic algorithms are selected from the multi-heuristic pool during the training phase, and effective heuristic algorithms are learned in the testing phase. The ACMA, standard MA, and other algorithms are utilized to address CEC 2017 benchmark problems. The results show that ACMA is a potential algorithm to address real-value optimization problems.