A controller architecture for the evolution of state-persistent controllers: Behaviour oriented decision tree (BODT)

In this paper we present a new controller architecture. A central design choice is that the controller can be easily modified or changed by evolution. Our aim is to initially endow the agents with as little knowledge as possible and to let them evolve their controllers autonomously. One particular aspect of the controller that we will investigate in this research is the evolution of state persistent controllers. With this is meant controllers that that can carry out multiple tasks. Without state persistency, agents may suffer from so-called ldquounfocused attentionrdquo: the case where an agent is caught in the middle between tasks and interchangeably executes these partially, but can and will never fully commit to either one and therefore never accomplish any. We will present the state-persistent controller architecture and demonstrate this property in an experiment.