C-Strategy: A Dynamic Adaptive Strategy for the CLONALG Algorithm

Maria Cristina Riff (1) , Elizabeth Montero (1, 2) , Bertrand Neveu (3, 4)

1 Departamento de Informatica [Valparaíso, Chile]
2 UNS - Université Nice Sophia Antipolis (1965 - 2019)
3 COPRIN - Constraints solving, optimization and robust interval analysis
4 LIGM - Laboratoire d'Informatique Gaspard-Monge

The control of parameters during the execution of bioinspired algorithms is an open research area. In this paper, we propose a new parameter control strategy for the immune algorithm CLONALG. Our approach is based on reinforcement learning ideas. We focus our attention on controlling the number of clones. Our approach provides an efficient and low cost adaptive technique for parameter control. We use instances of the Travelling Salesman Problem. The results obtained are very encouraging.

Domaines: Informatique [cs]; Intelligence artificielle [cs.AI]

Maria Cristina Riff, Elizabeth Montero, Bertrand Neveu. C-Strategy: A Dynamic Adaptive Strategy for the CLONALG Algorithm. Marina L. Gavrilova and C. J. Kenneth Tan. Transactions on Computational Science VIII, Springer-Verlag, pp.41-55, 2010, Lecture Notes in Computer Science, 978-3-642-16235-0. ⟨10.1007/978-3-642-16236-7_3⟩. ⟨hal-00654389⟩