Litcius/Paper detail

Hybridization of Evolutionary Algorithm and Deep Reinforcement Learning for Multiobjective Orienteering Optimization

Wei Liu, Rui Wang, Tao Zhang, Kaiwen Li, Wenhua Li, Hisao Ishibuchi, Xiangke Liao

2022IEEE Transactions on Evolutionary Computation57 citationsDOI

Abstract

Multiobjective orienteering problems (MO-OPs) are classical multiobjective routing problems and have received much attention in recent decades. This study seeks to solve MO-OPs through a problem-decomposition framework, that is, an MO-OP is decomposed into a multiobjective knapsack problem (MOKP) and a traveling salesman problem (TSP). The MOKP and TSP are then solved by a multiobjective evolutionary algorithm (MOEA) and a deep reinforcement learning (DRL) method, respectively. While the MOEA module is for selecting cities, the DRL module is for planning a Hamiltonian path for these cities. An iterative use of these two modules drives the population toward the Pareto front of MO-OPs. The effectiveness of the proposed method is compared against NSGA-II and NSGA-III on various types of MO-OP instances. Experimental results show that our method performs best on almost all the test instances and has shown strong generalization ability.

Topics & Concepts

OrienteeringKnapsack problemMathematical optimizationMulti-objective optimizationEvolutionary algorithmTravelling salesman problemReinforcement learningPopulationComputer scienceGeneralizationMathematicsDecompositionAlgorithmArtificial intelligenceSociologyDemographyMathematical analysisBiologyEcologyVehicle Routing Optimization MethodsAdvanced Multi-Objective Optimization AlgorithmsMetaheuristic Optimization Algorithms Research