An architecture for behaviour coordination learning

摘要

This paper describes a neural architecture for learning coordination of different behaviours in a situated agent. Behaviour-oriented approaches define the control of an agent directly in terms of its tasks. A key challenge is how to manage the agent's ongoing tasks so that action conflict is minimized and the desired levels of compliance with overall goals are achieved. We present mechanisms for adapting the coordination strategy through short- and long-term adaptive inhibition and time-varying performance feedback. Finally, we present preliminary experimental results for a simulated robot which demonstrate the effectiveness of this method.