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

arXiv: https://arxiv.org/abs/2507.22255 · HTML: https://mlsanity.com/paper/2507.22255/

## 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 (most cited first, 20 of 20)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Risks from Learned Optimization in Advanced Machine Learning Systems](https://mlsanity.com/paper/1906.01820/) (2019)
- [Benchmarking the Spectrum of Agent Capabilities](https://mlsanity.com/paper/2109.06780/) (2021)
- [Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey](https://mlsanity.com/paper/2012.09830/) (2020)
- [Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning](https://mlsanity.com/paper/1703.01732/) (2017)
- [On the Expressivity of Markov Reward](https://mlsanity.com/paper/2111.00876/) (2021)
- [Empowerment -- an Introduction](https://mlsanity.com/paper/1310.1863/) (2013)
- [Top-Down Synthesis for Library Learning](https://mlsanity.com/paper/2211.16605/) (2022)
- [Settling the Reward Hypothesis](https://mlsanity.com/paper/2212.10420/) (2022)
- [Meta-learning curiosity algorithms](https://mlsanity.com/paper/2003.05325/) (2020)
- [Rethinking the Foundations for Continual Reinforcement Learning](https://mlsanity.com/paper/2504.08161/) (2025)
- [Goals as Reward-Producing Programs](https://mlsanity.com/paper/2405.13242/) (2024)
- [Three Dogmas of Reinforcement Learning](https://mlsanity.com/paper/2407.10583/) (2024)
- [Exploring the hierarchical structure of human plans via program generation](https://mlsanity.com/paper/2311.18644/) (2023)
- [A taxonomy of surprise definitions](https://mlsanity.com/paper/2209.01034/) (2022)
- [Intrinsically-Motivated Humans and Agents in Open-World Exploration](https://mlsanity.com/paper/2503.23631/) (2025)
- [From Curiosity to Competence: How World Models Interact with the Dynamics of Exploration](https://mlsanity.com/paper/2507.08210/) (2025)
- [Harmonizing Program Induction with Rate-Distortion Theory](https://mlsanity.com/paper/2405.05294/) (2024)
- [Reward is not Necessary: How to Create a Modular & Compositional Self-Preserving Agent for Life-Long Learning](https://mlsanity.com/paper/2211.10851/) (2022)

## Built on by (most cited first, 2 of 2)

- [Empowerment Gain and Causal Model Construction: Children and adults are sensitive to controllability and variability in their causal interventions](https://mlsanity.com/paper/2512.08230/) (2025)
- [What Is Worth Representing? Representational Empowerment for Continual Model Construction](https://mlsanity.com/paper/2609.02322/) (2026)

## 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.