Improving Performance of a Hyper-heuristic Using a Multilayer Perceptron for Vehicle Routing

A hyper-heuristic is a heuristic optimisation method which generates or selects heuristics (move operators) based on a set of components while solving a computationally difficult problem. Apprenticeship learning arises while observing the behaviour of an expert in action. In this study, we use a multilayer perceptron (MLP) as an apprenticeship learning algorithm to improve upon the performance of a state-of-the-art selection hyper-heuristic used as an expert, which was the winner of a cross-domain heuristic search challenge (CHeSC 2011). We collect data based on the relevant actions of the expert while solving selected vehicle routing problem instances from CHeSC 2011. Then an MLP is trained using this data to build a selection hyper-heuristic consisting of a number classifiers for heuristic selection, parameter control and move acceptance. The generated selection hyper-heuristic is tested on the unseen vehicle routing problem instances. The empirical results indicate the success of MLP-based hyper-heuristic achieving a better performance than the expert and some previously proposed algorithms.