A cognitive architecture made of a bag of networks

Our aim was to produce a cognitive architecture for modelling some properties of sensorimotor learning in infants, namely the ability to accumulate adaptations and skills over multiple tasks in a manner which allows recombination and re-use of task specific competences. The control architecture we invented consisted of a population of compartments (units of neuroevolution) each containing networks capable of controlling a robot with many degrees of freedom. The nodes of the network undergo internal mutations, and the networks undergo stochastic structural modifications, constrained by a mutational and recombinational grammar. The nodes used consist of dynamical systems such as dynamical movement primitives, continuous time recurrent neural networks and high-level supervised and unsupervised learning algorithms. Edges in the network represent the passing of information from a sending node to a receiving node. The networks in a compartment working together encode a space of possible subsumption-like architectures that are used to successfully evolve a variety of behaviours for a Nao H25 humanoid robot.