Abstract
We develop a novel coevolutionary algorithm based upon the concept of Pareto optimality. The Pareto criterion is core to conventional multi-objective optimization (MOO) algorithms. We can think of agents in a coevolutionary system as performing MOO, as well: An agent interacts with many other agents, each of which can be regarded as an objective for optimization. We adapt the Pareto concept to allow agents to follow gradient and create gradient for others to follow, such that co-evolutionary learning succeeds. We demonstrate our Pareto coevolution methodology with the majority function, a density classification task for cellular automata.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
D. Andre et al. Evolution of intricate long-distance communication signals in cellular automata using genetic programming. In C. G. Langton and K. Shimohara, editors, Artificial Life V, pages 16–18. MIT Press, 1996.
J. E. Baker. Reducing bias and inefficiency in the selection algorithm. In Proc. Second Int. Conf. on Genetic Algorithms, pages 14–21. Lawrence Earlbaum, 1987.
D. Cliff and G. F. Miller. Tracking the red queen: Measurements of adaptive progress in co-evolutionary simulations. In F. Moran et al., editors, Third Euro. Conf. on Artificial Life, pages 200–218. Springer, 1995.
S. G. Ficici and J. B. Pollack. A game-theoretic approach to the simple coevolutionary algorithm. In Schoenauer et al. [19], pages 467–476.
C. M. Fonseca and P. J. Fleming. An overview of evolutionary algorithms in multiobjective optimization. Evolutionary Computation, 3(1):1–16, 1995.
D. Hillis. Co-evolving parasites improves simulated evolution as an optimization procedure. In C. Langton et al., editors, Artificial Life II, pages 313–324. Addison-Wesley, 1991.
H. Juillé. Methods for Statistical Inference: Extending the Evolutionary Computation Paradigm. PhD thesis, Brandeis University, 1999.
H. Juillé and J. B. Pollack. Co-evolving intertwined spirals. In L. J. Fogel et al., editors, Proc. Fifth Annual Conf. on Evolutionary Programming, pages 461–468. MIT Press, 1996.
H. Juillé and J. B. Pollack. Coevolutionary learning: a case study. In J. Shavlik, editor, Proc. Fifteenth Int. Conf. on Machine Learning, pages 251–259. Morgan Kaufmann, 1998.
H. Juillé and J. B. Pollack. Coevolving the “ideal” trainer: Application to the discovery of cellular automata rules. In J. R. Koza et al., editors, Proc. Third Annual Conf. on Genetic Programming, pages 519–527. Morgan Kaufmann, 1998.
M. Land and R. K. Belew. No perfect two-state cellular automata for density classification exists. Physical Review Letters, 74(25):1548–1550, 1995.
M. Mitchell et al. Evolving cellular automata to perform computations: Mechanisms and impediments. Physica D, 75:361–391, 1994.
J. Noble and R. A. Watson. Pareto coevolution: Using performance against coevolved opponents in a game as dimensions for pareto selection. In L. Spector et al., editors, Proc. 2001 Genetic and Evo. Comp. Conf. Morgan Kaufmann, 2001.
G. M. B. Oliveira et al. Evolving solutions of the density classification task in 1d cellular automata, guided by parameters that estimate their dynamic behaviour. In M. A. Bedau et al., editors, Artificial Life VII, pages 428–436. MIT Press, 2000.
B. Olsson. NK-landscapes as test functions for evaluation of host-parasite algorithms. In Schoenauer et al. [19], pages 487–496.
J. Paredis. Towards balanced coevolution. In Schoenauer et al. [19], pages 497–506.
J. B. Pollack and A. D. Blair. Co-evolution in the successful learning of backgammon strategy. Machine Learning, 32(3):225–240, 1998.
C. D. Rosin. Coevolutionary Search Among Adversaries. PhD thesis, University of California, San Diego, 1997.
M. Schoenauer et al., editors. Parallel Prob. Solv. from Nature 6. Springer, 2000.
R. A. Watson and J. B. Pollack. Symbiotic combination as an alternative to sexual recombination in genetic algorithms. In Schoenauer et al. [19], pages 425–434.
J. Werfel et al. Resource sharing and coevolution in evolving cellular automata. IEEE Transactions on Evolutionary Computation, 4(4):388–393, 2000.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ficici, S.G., Pollack, J.B. (2001). Pareto Optimality in Coevolutionary Learning. In: Kelemen, J., Sosík, P. (eds) Advances in Artificial Life. ECAL 2001. Lecture Notes in Computer Science(), vol 2159. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44811-X_34
Download citation
DOI: https://doi.org/10.1007/3-540-44811-X_34
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42567-0
Online ISBN: 978-3-540-44811-2
eBook Packages: Springer Book Archive