Agent-centric learning: from external reward maximization to internal knowledge curation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908472691392512 |
|---|---|
| author | Zhou, Hanqi Mantiuk, Fryderyk Nagy, David G. Wu, Charley M. |
| author_facet | Zhou, Hanqi Mantiuk, Fryderyk Nagy, David G. Wu, Charley M. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_22255 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Agent-centric learning: from external reward maximization to internal knowledge curation Zhou, Hanqi Mantiuk, Fryderyk Nagy, David G. Wu, Charley M. Machine Learning Artificial Intelligence Symbolic Computation 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. |
| title | Agent-centric learning: from external reward maximization to internal knowledge curation |
| topic | Machine Learning Artificial Intelligence Symbolic Computation |
| url | https://arxiv.org/abs/2507.22255 |