The IMA Workshop on Evolutionary Algorithms brought together many of the top researchers in the area of Evolutionary Computation for a week of intensive interaction. The field of Evolutionary Computation has developed significantly over the past 30 years and today consists of a variety of subfields such as genetic algorithms, evolution strategies, evolutionary programming, and genetic programming, each with its own algorithmic perspectives and goals. The workshop did a great deal to clarify the current state of the theory of Evolutionary Algorithms. The existing theory might be characterized as deriving from two principal approaches. There is a high level macro-theory that looks at the processing of building blocks and schemata that are shared by many good solutions when searching a problem space. There is also a low level micro-theory that builds exact Markov models of the search process. It is sometimes hard for researchers working at such different levels of abstraction to interact. The IMA workshop allowed researchers working at these different levels to present their points of view and to move toward common ground.There was real progress in communication between theorists and practitioners in the evolutionary computation field. Speakers presented applications across a wide range of problem areas. In some of those cases, theoretically motivated methods work quite well. In other cases, practitioners used domain-based methods to obtain better performance than could be achieved by using a pure evolutionary algorithm. Individuals on both sides went away with a better appreciation of the successes and failures of current theory.

This book constitutes the refereed proceedings of the 9th International Conference on Parallel Problem Solving from Nature, PPSN 2006, held in Reykjavik, Iceland in September 2006.

The 106 revised full papers presented were carefully reviewed and selected from 255 submissions. The papers cover a wide range of topics, from evolutionary computation to swarm intelligence and from bio-inspired computing to real-world applications; they are organized in topical sections on theory, new algorithms, applications, multi-objective optimization, evolutionary learning, as well as representations, operators, and empirical evaluation.