Search papers, labs, and topics across Lattice.
This paper introduces Representational Empowerment (RepEmp), a framework for continual model construction that prioritizes the selection of representational elements based on their potential to enhance future modeling and planning capabilities. Through a hierarchical Curator-Actor architecture, the authors demonstrate that RepEmp outperforms traditional information-gain metrics in predicting human behavior in causal learning tasks and facilitates better structure recovery and generalization in simulations. The findings suggest that RepEmp is crucial for optimizing model representation under resource constraints, enabling agents to make more effective decisions about what to build and retain in their libraries.
RepEmp reveals that the future capacity to model and plan is more critical than immediate fidelity in representation selection, reshaping our understanding of model construction.
The first problem of modeling the world is not just estimating the right parameters or causal structure, but deciding what should be represented at all. We frame this problem as continual model construction: an agent maintains an environment-specific model M of an inaccessible world W and curates a persistent library L of reusable representational elements across environments. We propose Representational Empowerment (RepEmp) to score candidate elements by how much they expand the agent's future capacity to model and plan, complementing the classic definition of empowerment, but redefined as control over internal representations instead of external states. We realize the framework as a hierarchical Curator-Actor architecture and test it across three experiments. In a closed-vocabulary causal-learning task, human participants construct causal models at varying abstraction granularities to maximize goal reachability rather than fidelity to the world, a signature better predicted by RepEmp than by information-gain alternatives. Matched simulations reveal that RepEmp-guided construction contributes more than exploration to sufficient structure recovery and cross-task transfer. Finally, in an open-vocabulary planning domain, an LLM-augmented Curator builds more compact symbolic libraries, which also generalize better than baselines. Ablating RepEmp eliminates these benefits. Together, these results identify RepEmp as a key principle for continual model construction: deciding what to build, retain, and reuse under bounded resources.
