LEARNING AND EVOLUTION Stefano Nolfi* Dario Floreano~ *Institute of Psychology, National Research Council Viale Marx 15, Roma, Italy stefano@kant.irmkant.rm.cnr.it ~LAMI - Laboratory of Microcomputing Swiss Federal Institute of Technology EPFL, Lausanne, Switzerland Dario.Floreano@epfl.ch In the last few years researchers have used artificial evolution techniques (e.g. genetic algorithms) and learning techniques (e.g. neural networks) to the study of the interaction between learning and evolution. These studies have been conducted with two different purposes: (a) looking at the advantages,in terms of performance, that the interaction gives to evolution; (b) understanding the role of the interaction between learning and evolution in natural organisms. In this paper we describe some of the most representative experiments conducted in this area and we will try to point out the implications from both these points of view. As we will show the problem of understanding the interaction between learning and evolution is probably one of the best examples in which computational studies have shed light on problems that are difficult to study with the research tools of evolutionary biology and biology in general. From and engineering point of view, the most relevant results are those showing that adaptation in dynamic environments is favored by a combination of evolution and learning. These studies also demonstrate how the interaction between learning and evolution deeply alters the evolutionary and the learning process themselves. The study of learning in an evolutionary perspective, is still in its infancy. We believe that the study of learning in interaction with evolution will produce in the next years an enormous impact on our understanding of what learning and evolution are.