Artificial Life VI

Evolving Novel Behaviors via Natural Selection

A.D. Channon
University of Southampton, UK

R.I. Damper
University of Southampton, UK


The traditional fitness function based methodology of artificial evolution is argued to be inadequate for the construction of entities with behaviors novel to their designers. Evolutionary emergence via natural selection (without an explicit fitness function) is the way forward. This paper further considers the question of what to evolve, the focus being on principles of developmental modularity in neural networks. To develop and test the ideas, an artificial world containing autonomous organisms has been created and is described. Results show the developmental system to be well suited to long-term incremental evolution. Novel emergent strategies are identified both from an observer's perspective and in terms of their neural mechanisms.

Material included on the CDROM

Geb: an artificial world containing organisms which evolve by natural selection. (i386-Linux Binary,58k) (sun4-SunOS Binary,82k) (Windows95/NT Executable,215k) (version 03a)
(Source code[C++,X11/Borland],58k) (Snapshot,25k)

Further information
Further and updated information, including related papers and code in various formats, is available here.

Back to ALife6 Table of Contents / Keyword Index / Author Index / Meeting Schedule