In the 19 years since Karl Sims' landmark publication on
evolving virtual creatures (Sims, 1994), much of the future
work he proposed has been implemented, having a significant
impact on multiple fields including graphics, evolutionary
computation, and artificial life. There has, however been one
notable exception to this progress. Despite the potential
benefits, there has been no clear increase in the behavioral
complexity of evolved virtual creatures (EVCs) beyond the
light following demonstrated in Sims' original work.
This paper presents an open-ended method to move beyond this
limit, making use of high-level human input in the form
of a syllabus of intermediate learning tasks--along with
mechanisms for preservation, reuse, and combination of
previously learned tasks. This method (named ESP for
its three components: encapsulation, syllabus, and
pandemonium) is employed to evolve a virtual creature with
behavioral complexity that clearly exceeds previously achieved
levels. ESP thus demonstrates that EVCs may indeed have the
potential to one day rival the behavioral complexity--and
therefore the entertainment value--of their non-virtual
counterparts.
Video