Agents
The Geometry of Empowerment
arXiv:2610.07796v1 Announce Type: cross Abstract: Empowerment captures the capacity for an agent to actively control its environment. While conceptually appealing as an information-theoretic quantity,
arXiv:2610.07796v1 Announce Type: cross Abstract: Empowerment captures the capacity for an agent to actively control its environment. While conceptually appealing as an information-theoretic quantity, the connection between empowerment and structurally central states that provide broad access to future outcomes has remained an open question. In this work, we link empowerment maximization and skill-learning methods to provide new geometries for interpreting and analyzing empowerment. Our analyses answer longstanding open questions on the connections between empowerment and structural centrality. Our analyses also reveal distinctions between information and reward geometries, highlighting important theoretical implications to build scalable empowerment-maximization methods. Website and code can be found at https://empowerment-geometry.github.io/.
Related
- SphUnc: Hyperspherical Uncertainty Decomposition and Causal Identification via Information Geometry
- An Information-Theoretic Definition for Open-Ended Learning
- Architectures for Robust Self-Organizing Energy Systems under Information and Control Constraints
- Token-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of Labor
Source: arXiv cs.AI | 2026-10-07