Nested evolution of an autonomous agent using descriptive encoding
Jae-Yoon Jung, James A. Reggia · 2008
In this paper, we investigate the use of nested evolution in which each step of one evolutionary process involves running a second evolutionary process. We apply this approach to build a neuroevolution system for reinforcement learning (RL) problems. Genetic programming based on a descriptive encoding is used to evolve the neural architecture, while a nested evolution strategy is used to evolve the needed connection weights. We test this hierarchical evolution on a non-Markovian RL problem involving an autonomous foraging agent, finding that the evolved networks significantly outperform a rule-based agent serving as a control.