Resolving Conflicts Among Actions in Concurrent Behaviors: Learning to Coordinate
Henry H. Hexmoor · 2000
A robotic agent must coordinate its coupled concurrent behaviors to produce a coherent response to stimuli. Reinforcement learning has been used extensively in coordinating sensing to acting of a single behavior and it has been shown useful in loosely coupled concurrent behaviors. We present a technique for applying Q values developed in learning individual behaviors for coordination among coupled concurrent behaviors.