Coevolution (i.e., the evolution of two or more competing populations with
coupled fitness) has several features that may potentially enhance the powe
r of adaptation of artificial evolution. In particular, as discussed by Daw
kins and Krebs [3], competing populations may reciprocally drive one anothe
r to increasing levels of complexity by producing an evolutionary "arms rac
e." In this article we will investigate the role of coevolution in the cont
ext of evolutionary robotics. In particular, we will try to understand in w
hat conditions coevolution can lead to "arms races." Moreover, we will show
that in some cases artificial coevolution has a higher adaptive power than
simple evolution. Finally, by analyzing the dynamics of coevolved populati
ons, we will show that in some circumstances well-adapted individuals would
be better advised to adopt simple but easily modifiable strategies suited
for the current competitor strategies rather than incorporate complex and g
eneral strategies that may be effective against a wide range of opposing co
unter-strategies.