"Evolutionary Robotics" by Dario Floreano and Stefano Nolfi presents a thorough analysis of the most relevant work in this field up the the time of publishing (2000). It also provides an excellent overview and description of the processes involved in the development of evolutionary methodologies, particularly those which involve robotics or simulations of embodied agents. The approach of self-organization of behavior clearly has many advantages over traditional hand-crafted solutions. I found it a great introduction to this huge world, with many examples of how to design and conduct successful experiments. I was surprised with the sheer scope of possibilities that can be explored and investigated, from reactive architectures, to co-evolution, learning during lifetime, and changing morphologies. This book is definitely a primer and should be read by anyone that has even a remote interest in the field of Machine Learning and Robotics.