A Q-learning Evolutionary Multiobjective Framework for Multiobjective Optimization with Separable and Interacting Variables

Many multiobjective evolutionary algorithms (MOEAs) have been proposed for dealing with various problem difficulties in multiobjective optimization over the past three decades. However, none of them can perform best for all problem difficulties. When solving a certain multiobjective optimization problem (MOP), a good multiobjective optimizer should take its problem features into account. When the problem features are unknown in advance, it is difficult to choose an appropriate algorithm as the prior solver. In this paper, we propose a Q-learning evolutionary multiobjective framework, denoted by QL-MOEA, to solve the MOPs with both separable variables and interacting variables. In QL-MOEA, either NSGA-II or MOEA/D is adaptively selected by intelligent agent in different stages of the evolution of population. Our experimental results show that QL-MOEA outperforms the baseline NSGA-II or MOEA/D in convergence speed.