Learning to Adapt to Changing Environments in Evolving Neural Networks

To study learning as an adaptive process, one must take into consideration the role of evolution, which is the primary adaptive process. In addition, learning should be studied in (artificial) organisms that live in an independent physical environment in such a way that the input from the environment can be at least partially controlled by the organisms' behavior. To explore these issues, we used a genetic algorithm to simulate the evolution of a population of neural networks, each controlling the behavior of a small mobile robot that must explore efficiently an environment surrounded by walls. Because the environment changes from one generation to the next, each network must learn during its life to adapt to the particular environment into which it happens to be born. We found that evolved networks incorporate a genetically inherited predisposition to learn that can be described as (1) the presence of initial conditions that tend to canalize learning in the right directions; (2) the tendency to behave in a way that enhances the perceived differences between different environments and determines input stimuli that facilitate the learning of adaptive changes; and (3) the ability to reach desirable stable states.