Encyclopedia of Machine Learning

2010 Edition
| Editors: Claude Sammut, Geoffrey I. Webb

Coevolutionary Learning

  • R. Paul Wiegand
Reference work entry
DOI: https://doi.org/10.1007/978-0-387-30164-8_137

Synonyms

Definition

Coevolutionary learning is a form of evolutionary learning (see  Evolutionary Algorithms) in which the fitness evaluation is based on interactions between individuals. Since the evaluation of an individual is dependent on interactions with other evolving entities, changes in the set of entities used for evaluation can affect an individual’s ranking in a population. In this sense, coevolutionary fitness is subjective, while fitness in traditional evolutionary learning systems typically uses an objective performance measure.

Motivation and Background

Ideally, coevolutionary learning systems focus on relevant areas of a search space by making adaptive changes between interacting, concurrently evolving parts. This can be particularly helpful when problem spaces are very large – infinite search spaces in particular. Additionally, coevolution is useful when applied to problems when no intrinsic objective measure exists. The...

This is a preview of subscription content, log in to check access.

Recommended Reading

  1. Angeline, P., & Pollack, J. (1993). Competitive environments evolve better solutions for complex tasks. In S. Forest (Ed.), Proceedings of the fifth international conference on genetic algorithms (pp. 264–270). San Mateo, CA: Morgan Kaufmann.Google Scholar
  2. Axelrod, R. (1984). The evolution of cooperation. New York: Basic Books.Google Scholar
  3. Bader-Natal, A., & Pollack, J. (2005). Towards metrics and visualizations sensitive to Coevolutionary failures. In AAAI technical report FS-05-03 coevolutionary and coadaptive systems. AAAI Fall Symposium, Washington, DC.Google Scholar
  4. Bucci, A., & Pollack, J. B. (2002). A mathematical framework for the study of coevolution. In R. Poli, et al. (Eds.), Foundations of genetic algorithms VII (pp. 221–235). San Francisco: Morgan Kaufmann.Google Scholar
  5. Bucci, A., & Pollack, J. B. (2003). Focusing versus intransitivity geometrical aspects of coevolution. In E. Cantú-Paz, et al. (Eds.), Proceedings of the 2003 genetic and evolutionary computation conference (pp. 250–261). Berlin: Springer.Google Scholar
  6. Bull, L. (1997). Evolutionary computing in multi-agent environments: Partners. In T. Bäck (Ed.), Proceedings of the seventh international conference on genetic algorithms (pp. 370–377). San Mateo, CA: Morgan Kaufmann.Google Scholar
  7. Cliff, D., & Miller, G. F. (1995). Tracking the red queen: Measurements of adaptive progress in co-evolutionary simulations. In Proceedings of the third European conference on artificial life (pp. 200–218). Berlin: Springer.Google Scholar
  8. de Jong, E. (2004). The maxsolve algorithm for coevolution. In H. Beyer, et al. (Eds.), Proceedings of the 2005 genetic and evolutionary computation conference (pp. 483–489). New York, NY: ACM Press.Google Scholar
  9. de Jong, E., & Pollack, J. (2004). Ideal evaluation from coevolution. Evolutionary Computation, 12, 159–192.Google Scholar
  10. Ficici, S. G. (2004). Solution concepts in coevolutionary algorithms. PhD thesis, Brandeis University, Boston, MA.Google Scholar
  11. Fogel, D. (2001). Blondie24: Playing at the edge of artificial intelligence. San Francisco: Morgan Kaufmann.Google Scholar
  12. Hillis, D. (1991). Co-evolving parasites improve simulated evolution as an optimization procedure. Artificial life II, SFI studies in the sciences of complexity (Vol. 10, pp. 313–324).Google Scholar
  13. Moriarty, D., & Miikkulainen, R. (1997). Forming neural networks through efficient and adaptive coevolution. Evolutionary Computation, 5, 373–399.Google Scholar
  14. Nolfi, S., & Floreano, D. (1998). Co-evolving predator and prey robots: Do “arm races” arise in artificial evolution? Artificial Life, 4, 311–335.Google Scholar
  15. Pagie, L. (1999). Information integration in evolutionary processes. PhD thesis, Universiteit Utrecht, the Netherlands.Google Scholar
  16. Panait, L. (2006). The analysis and design of concurrent learning algorithms for cooperative multiagent systems. PhD thesis, George Mason University, Fairfax, VA.Google Scholar
  17. Paredis, J. (1994). Steps towards co-evolutionary classification networks. In R. A. Brooks & P. Maes (Eds.), Artificial life IV, proceedings of the fourth international workshop on the synthesis and simulation of living systems (pp. 359–365). Cambridge, MA: MIT Press.Google Scholar
  18. Popovici, E. (2006). An analysis of multi-population co-evolution. PhD thesis, George Mason University, Fairfax, VA.Google Scholar
  19. Potter, M. (1997). The design and analysis of a computational model of cooperative co-evolution. PhD thesis, George Mason University, Fairfax, VA.Google Scholar
  20. Rosin, C., & Belew, R. (1996). New methods for competitive coevolution. Evolutionary Computation, 5, 1–29.Google Scholar
  21. Sims, K. (1994). Evolving 3D morphology and behavior by competition. In R. A. Brooks & P. Maes (Eds.), Artificial life IV, proceedings of the fourth international workshop on the synthesis and simulation of living systems (pp. 28–39). Cambridge, MA: MIT Press.Google Scholar
  22. Stanley, K. (2004). Efficient evolution of neural networks through complexification. PhD thesis, The University of Texas at Austin, Austin, TX.Google Scholar
  23. Watson, R., & Pollack, J. (2001). Coevolutionary dynamics in a minimal substrate. In L. Spector, et al. (Eds.), Proceedings from the 2001 genetic and evolutionary computation conference (pp. 702–709). San Francisco: Morgan Kaufmann.Google Scholar
  24. Wiegand, R. P. (2003). An analysis of cooperative coevolutionary algorithms. PhD thesis, George Mason University, Fairfax, VA.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • R. Paul Wiegand

There are no affiliations available