Empowerment -- an Introduction
It provides a foundational concept for intrinsic motivation in AI, applicable across various sensor-motor configurations, but is incremental as it builds on prior work.
The chapter introduces 'Empowerment', an information-theoretic utility function that measures an agent's control over its perceived world, and presents a fast approximation for continuous domains.
This book chapter is an introduction to and an overview of the information-theoretic, task independent utility function "Empowerment", which is defined as the channel capacity between an agent's actions and an agent's sensors. It quantifies how much influence and control an agent has over the world it can perceive. This book chapter discusses the general idea behind empowerment as an intrinsic motivation and showcases several previous applications of empowerment to demonstrate how empowerment can be applied to different sensor-motor configuration, and how the same formalism can lead to different observed behaviors. Furthermore, we also present a fast approximation for empowerment in the continuous domain.