HackerPapers

arXiv:1310.1863cs.AI

Empowerment -- an Introduction

Christoph Salge, Cornelius Glackin, Daniel Polani

Abstract

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.

arXiv comments
46 pages, 8 figures, to be published in Prokopenko, M., editor, Guided Self-Organization: Inception. Springer. In Press
Journal reference
DOI
Subjects
cs.AIArtificial Intelligence cs.ITInformation Theory nlin.AOAdaptation and Self-Organizing Systems

On Hacker News

Linked by 2 identifiable commenters in 5 comments across 5 threads, from May 2017 to Apr 2025.

Comments linking this paper, per year.

Discussed in comments5 threads

  1. How to build Intrinsic Motivation: a review of the science 1 comment

    • From an AI perspective, I have a rough idea of what intrinsic motivation means to me: To allow an embodied agent to perform actions within an environment that would generally be considered positive, without the definition of an objective function. To break that down, to be…

      bArrayView on HNParent context

  2. Call of Duty: Warzone Caldera Data Set for Academic Use 1 comment

    • From an information theory perspective, it should be possible to define strategically important locations in terms of Empowerment [1]. As a map designer there are likely some rough rules you want to abide by, such as roughly equal highly empowered locations throughout the map to…

      bArrayView on HNParent context

  3. Evidence for entropy maximisation in human free choice behaviour 1 comment

    • There is some work that explores this from an AI perspective with relative success [1]. It turns out that you can create quite intelligent agents if they look to maximize future entropy, with interesting results [2]. It's still quite computationally expensive, but your normal…

      bArrayView on HNParent context

  4. Software and Hardware for General Robots 1 comment

    • I believe robotics hardware is near and damn it there, and has been for a while now. We're already seeing semi-reliable robots such as 'smart' hoovers enter homes. The biggest problem by far is the software - in particular the AI. The biggest companies in the world have thrown…

      bArrayView on HNParent context

  5. Is there a tension between creativity and accuracy? 1 comment

    • Neural networks also need to balance exploration and exploitation. You will find it in the form of: + generalization / overfitting + cross-domain knowledge transfer In a more embodied approach it is free energy minimization as advocated by Friston. Consider us divided by the…

      MrQuincleView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.