REVIEW 2 cited by
Empowerment -- an Introduction
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 2 Pith papers
-
Constructive Alignment: Governing Preference Dynamics in Human-AI Interaction
Alignment should be a control problem over layered, dynamic, interaction-constructed preference trajectories, constrained by coherence, reflective endorsement, bounded influence, epistemic integrity, and empowerment.
-
Intrinsic motivation as constrained entropy maximization
Three formal accounts of intrinsic motivation, active inference, empowerment, and maximum occupancy, are reframed as constrained entropy maximization, with maximum occupancy shown to lean on a hidden survival constraint.
Discussion (0). Continue with ORCID to comment.