Co-Evolutionary Algorithms: A Useful Computational Abstraction?
Interest in co-evolutionary algorithms was triggered in part with Hillis 1991 paper describing his success in using one to evolve sorting networks. Since then there have been heightened expectations for using this nature-inspired technique to improve on the range and power of evolutionary algorithms for solving difficult computation problems. However, after more than two decades of exploring this promise, the results have been somewhat mixed.
In this talk I summarize the progress made and the lessons learned with a goal of understanding how they are best used and identify a variety of interesting open issues that need to be explored in order to make further progress in this area.
KeywordsNash Equilibrium Fitness Landscape Evolutionary Game Theory Reproductive Variation Difficult Optimization Problem
- 1.Angeline, P.J., Pollack, J.B.: Competitive environments evolve better solutions for complex tasks. In: Proceedings of the 5th International Conference on Genetic Algorithms, pp. 264–270. Morgan Kaufmann Publishers Inc., San Francisco (1993)Google Scholar
- 3.Bucci, A., Pollack, J.B.: A mathematical framework for the study of coevolution. In: Proceedings of the Seventh Workshop on Foundations of Genetic Algorithms, Torremolinos, Spain, pp. 221–236, 2–4 September 2002Google Scholar
- 5.Ficici, S.G.: Solution Concepts in Coevolutionary Algorithms. Ph.D. thesis, Brandeis University, Waltham, MA, USA (2004). AAI3127125Google Scholar
- 6.Hillis, D.: SFI studies in the sciences of complexity co-evolving parasites improve simulated evolution as an optimization procedure. Artificial Life II 10, 313–324 (1991)Google Scholar
- 7.Juille, H., Pollack, J.B.: Coevolving the "ideal" trainer: application to the discovery of cellular automata rules. In: University of Wisconsin, pp. 519–527. Morgan Kaufmann (1998)Google Scholar
- 9.Popovici, E.: An analysis of two-population coevolutionary computation. Ph.D. thesis, George Mason University, Fairfax, VA (2006)Google Scholar
- 11.Popovici, E., De Jong, K.A.: Relationships between internal and external metrics in co-evolution. In: Proceedings of the IEEE Congress on Evolutionary Computation, CEC 2005, Edinburgh, UK, pp. 2800–2807, 2–4 September 2005Google Scholar
- 13.Potter, M.A., De Jong, K.A.: A cooperative coevolutionary approach to function optimization. In: Davidor, Y., Männer, R., Schwefel, H.-P. (eds.) PPSN 1994. LNCS, vol. 866. Springer, Heidelberg (1994) Google Scholar
- 15.Sarma, J.: An analysis of decentralized and spatially distributed genetic algorithms. Ph.D. thesis, George Mason University, Fairfax VA, USA (1998)Google Scholar
- 16.Wiegand, R.P.: An analysis of cooperative coevolutionary algorithms. Ph.D. thesis, George Mason University, Fairfax, VA (2004)Google Scholar
- 17.Wiegand, R.P., Liles, W., De Jong, K.: An empirical analysis of collaboration methods in cooperative coevolutionary algorithms. In: Proceedings of Genetic and Evolutionary Computation - GECCO 2001, pp. 1235–1242. Morgan Kaufmann (2001)Google Scholar
- 18.Wiegand, R.P., Sarma, J.: Spatial embedding and loss of gradient in cooperative coevolutionary algorithms. In: Yao, X., Burke, E.K., Lozano, J.A., Smith, J., Merelo-Guervós, J.J., Bullinaria, J.A., Rowe, J.E., Tiňo, P., Kabán, A., Schwefel, H.-P. (eds.) PPSN 2004. LNCS, vol. 3242, pp. 912–921. Springer, Heidelberg (2004) CrossRefGoogle Scholar