Evolution of Plastic Neurocontrollers for Situated Agents

In this paper we investigate a novel approach to the evolutionary development of autonomous situated agents based on the assumption that the neural mechanisms underlying ontogenetic learning are themselves developed and shaped by the evolutionary process. A genetic algorithm is used to evolve neural structures that can be continuously modified during life according to the mechanisms specified in the genotype. The evolutionary process is carried out on a real mobile robot. The analysis of one of the best evolved individuals shows rapid development of stable behavior mediated by fast-changing synapses which are dynamically stable. 1 Introduction Adaptation to the environment takes place at multiple levels and time-scales: it ranges from the long-term dynamics of phylogenetic evolution to the fast process of ontogenetic learning. At the neural level, these adaptation modalities, that are well-timed and co-ordinated, are responsible for the development of robust and complex control syst..