Designing pheromone update strategies with strongly typed genetic programming

  • Authors:
  • Jorge Tavares;Francisco B. Pereira

  • Affiliations:
  • CISUC, Department of Informatics Engineering, University of Coimbra Polo II, Coimbra, Portugal;CISUC, Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal and ISEC, Coimbra, Portugal

  • Venue:
  • EuroGP'11 Proceedings of the 14th European conference on Genetic programming
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Ant Colony algorithms are population-based methods widely used in combinatorial optimization problems. We propose a strongly typed genetic programming approach to automatically evolve the communication mechanism that allows ants to cooperatively solve a given problem. Results obtained with several TSP instances show that the evolved pheromone update strategies are effective, exhibit a good generalization capability and are competitive with human designed variants.