Abstract
In most of this book we have been concerned with problems where the quality of a proposed solution can be relatively easily measured in isolation by some externally provided fitness function. Evaluating a solution may involve an element of random noise, but does not particularly depend on the context in which it is done. However, there are two obvious scenarios in which this set-up does not really hold. The first occurs when a solution represents some strategy or design that works in opposition to some competitor that is itself adapting. The most obvious example here would be adversarial game-playing such as chess. The second comes about when a solution being evolved does not represent a complete solution to a problem, but instead can only be evaluated as part of a greater whole, that together accomplishes some task. An example might be the evolution of a set of traffic-light controllers, each to be sited on a different junction, with fitness reflecting their joint performance in reducing congestion over a day’s simulated traffic. Both of these are examples of coevolution. This chapter gives an overview of the types of scenarios where coevolution might be usefully applied, and of some of the issues involved in designing a successful application.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Eiben, A.E., Smith, J.E. (2015). Coevolutionary Systems. In: Introduction to Evolutionary Computing. Natural Computing Series. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-44874-8_15
Download citation
DOI: https://doi.org/10.1007/978-3-662-44874-8_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-44873-1
Online ISBN: 978-3-662-44874-8
eBook Packages: Computer ScienceComputer Science (R0)