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

Hanqi Zhou, Fryderyk Mantiuk, David G Nagy, Charley M Wu

Keywords: reinforcement learning, representation learning, empowerment, continual learning, program induction

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.

Submission Number: 16