Evolving integrated controllers for autonomous learning robots using dynamic neural networks.

In 1994, Yamauchi and Beer (1994) attempted to evolve a dynamic neural network as a control system for a simulated agent capable of performaning learned behaviour. They tried to evolve an integrated network, i.e. not modularized; this attempt failed. They ended up having to use independent evolution of separate controller modules, arbitrarily partitioned by the researcher. Moreover, they "provided" the agents with hard-wired reinforcement signals. The model we describe in this paper demonstrates that it is possible to evolve an integrated dynamic neural network that successfully controls the behaviour of a khepera robot engaged in a simple learning task. We show that dynamic neural networks, based on leaky-integrator neuron, shaped by evolution, appear to be able to integrate reactive and learned behaviour with an integrated control system which also benefits from its own reinforcement signal.