Emergence of New Local Search Algorithms with Neuro-Evolution

This paper explores a novel approach aimed at overcoming existing challenges in the realm of local search algorithms. The main objective is to better manage information within these algorithms, while retaining simplicity and generality in their core components. Our goal is to equip a neural network with the same information as the basic local search and, after a training phase, use the neural network as the fundamental move component within a straightforward local search process. To assess the efficiency of this approach, we develop an experimental setup centered around NK landscape problems, offering the flexibility to adjust problem size and ruggedness. This approach offers a promising avenue for the emergence of new local search algorithms and the improvement of their problem-solving capabilities for black-box problems.