Kenneth O. Stanley - Novel Opportunities in Open-Endedness @ UCL DARK

As interest in the field of open-endedness expands, ideas like continual discovery and increasingly complexity have gained significant attention. The aim of this talk is to bring attention to two lesser-known facets of open-endedness that nevertheless merit significantly more attention. First, evidence so far suggests that representations achieved through open-ended processes seem radically different from representations discovered through optimization, even if they solve the same problem. The implications of this observation are unknown but potentially significant. Second, while the agents themselves in an open-ended system are of course critical, in processes analogous to civilization (as opposed to evolution), the artifacts those agents put into and leave in the environment (e.g. houses and cars for humans) are also critical to the trajectory of the system, yet little studied or understood. New advances, such as Evolution through Large Models, make studying this issue more feasible. The hope is that this talk will inspire further investigation into both considerations.

#ML #Generative #Creativity