Resolving Conflicts Among Actions in Concurrent Behaviors

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.

• Type: Conference
• Year: 2000
• Where: FLAIRS
• Authors: Henry Hexmoor
• Keywords: Artificial Intelligence, Coherent Response, Concurrent Behaviors, FLAIRS 2000, Robotic Agent