Using a map-based encoding to evolve plastic neural networks

Many controllers for complex agents have been successfully generated by automatically desiging artificial neural networks with evolutionary algorithms. However, typical evolved neural networks are not able to adapt themselves online, making them unable to perform tasks that require online adaptation. Nature solved this problem on animals with plastic nervous systems. Inpired by neuroscience models of plastic neural-network, the present contribution proposes to use a combination of Hebbian learning, neuro-modulation and a a generative map-based encoding. We applied the proposed approach on a problem from operant conditioning (a Skinner box), in which numerous different association rules can be learned. Results show that the map-based encoding scaled up better than a classic direct encoding on this task. Evolving neural networks using a map-based generative encoding also lead to networks that works with most rule sets even when the evolution is done on a small subset of all the possible cases. Such a generative encoding therefore appears as a key to improve the generalization abilities of evolved adaptive neural networks.