Deep Reinforcement Learning Based Adaptive Environmental Selection for Evolutionary Multi-Objective Optimization

Evolutionary algorithms have demonstrated superior performance in solving multi-objective optimization problems (MOPs), but no single algorithm is consistently effective across all MOPs. When using evolutionary algorithms to solve MOPs, environmental selection strategies determining which solutions should survive are crucial to population evolution. While different environmental selection strategies exhibit different search behaviors on various MOPs, existing multi-objective evolutionary algorithms rarely focus on the adaptation of environmental selection strategies. To fill this gap, this paper proposes a framework for assembling environmental selection strategies, which utilizes neural networks to assess the effects of different strategies on population evolution, and employs reinforcement learning to adaptively select the most effective strategies. The effectiveness and versatility of the proposed framework are verified on four test sets, where the proposed framework shows significant superiority over the state-of-the-art.

I. Introduction

Multi-objective optimization problems (MOPs) inherently involve multiple conflicting objectives, making it challenging to find a solution that optimizes all of them simultaneously [1], [2]. Among various types of optimizers, multi-objective evolutionary algorithms (MOEAs) have proven advantageous in addressing MOPs. These algorithms initialize a population, iteratively generate new solutions through variation operators, and employ environmental selection strategies to eliminate inferior solutions, resulting in well-converged and diversified solutions forming a Pareto set in the decision space and a Pareto front in the objective space [3], [4].