Agent-centric learning: from external reward maximization to internal knowledge curation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 20 of its 52 references that are in the map. First posted on arXiv 29 Jul 2025.
Builds on
20 of 52 references.
References · 20
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
- 2019Risks from Learned Optimization in Advanced Machine Learning Systemscited by 258
- 2021Benchmarking the Spectrum of Agent Capabilitiescited by 200
- 2020Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Surveycited by 85
- 2017Surprise-Based Intrinsic Motivation for Deep Reinforcement Learningcited by 83
- 2021On the Expressivity of Markov Rewardcited by 71
- 2013Empowerment -- an Introductioncited by 68
- 2022Top-Down Synthesis for Library Learningcited by 58
- 2022Settling the Reward Hypothesiscited by 33
- 2020Meta-learning curiosity algorithmscited by 25
- 2025Rethinking the Foundations for Continual Reinforcement Learningcited by 15
8 more
- 2024Goals as Reward-Producing Programscited by 14
- 2024Three Dogmas of Reinforcement Learningcited by 14
- 2023Exploring the hierarchical structure of human plans via program generationcited by 12
- 2022A taxonomy of surprise definitionscited by 8
- 2025Intrinsically-Motivated Humans and Agents in Open-World Explorationcited by 8
- 2025From Curiosity to Competence: How World Models Interact with the Dynamics of Explorationcited by 5
- 2024Harmonizing Program Induction with Rate-Distortion Theorycited by 4
- 2022Reward is not Necessary: How to Create a Modular & Compositional Self-Preserving Agent for Life-Long Learningcited by 2
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.