Skip navigation
PDF 427 KB
DOI: http://dx.doi.org/10.7551/978-0-262-33936-0-ch049
Page 284
First published July 1 2016

Evolvability of Minimally Cognitive Agents

Matthew Setzler and Eduardo Izquierdo

Abstract (Excerpt)

This work investigates evolvability of continuous-time recurrent neural networks to support the behavior of model-agents subject to fitness criteria that changes over the evolutionary timescale. A population of agents is alternatingly evolved to perform two tasks with inverted fitness awards. Evidence of evolvability is reported; it is shown that the population locates a region of "meta-fitness" in the landscape in which sub-regions of optimality for each task are easily accessible from one another.