Dynamic selection of evolutionary algorithm operators based on online learning and fitness landscape metrics

Abstract. Self-adaptive mechanisms for the identification of the most suitable variation operator in Evolutionary meta-heuristics rely almost exclusively on the measurement of the fitness of the offspring, which may not be sufficient to assess the optimality of an operator (e.g., in a landscape with an high degree of neutrality). This paper proposes a novel Adaptive Operator Selection mechanism which uses a set of four Fitness Landscape Analysis techniques and an online learning al-gorithm, Dynamic Weighted Majority, to provide more detailed infor-mations about the search space in order to better determine the most suitable crossover operator on a set of Capacitated Arc Routing Prob-lem (CARP) instances. Extensive comparison with a state of the art approach has proved that this technique is able to produce comparable results on the set of benchmark problems.