Agent-centric learning: from external reward maximization to internal knowledge curation

TL;DR

This paper introduces representational empowerment, a novel agent-centric learning approach that emphasizes internal knowledge control over external rewards to foster adaptability and better preparedness in intelligent systems.

Contribution

It proposes a new internal control-focused paradigm called representational empowerment, shifting from external reward maximization to internal knowledge curation for adaptable AI.

Findings

Defines representational empowerment as an internal control measure

Highlights the importance of internal knowledge structures for adaptability

Suggests a new framework for designing flexible intelligent agents

Abstract

The pursuit of general intelligence has traditionally centered on external objectives: an agent's control over its environments or mastery of specific tasks. This external focus, however, can produce specialized agents that lack adaptability. We propose representational empowerment, a new perspective towards a truly agent-centric learning paradigm by moving the locus of control inward. This objective measures an agent's ability to controllably maintain and diversify its own knowledge structures. We posit that the capacity -- to shape one's own understanding -- is an element for achieving better ``preparedness'' distinct from direct environmental influence. Focusing on internal representations as the main substrate for computing empowerment offers a new lens through which to design adaptable intelligent systems.