Charlotte Beylier

Charlotte Beylier, Hannah Selder, Arthur Fleig et al.

While deep reinforcement learning agents demonstrate high performance across domains, their internal decision processes remain difficult to interpret when evaluated only through performance metrics. In particular, it is poorly understood which input features agents rely on, how these dependencies evolve during training, and how they relate to behavior. We introduce a scientific methodology for analyzing the learning process through quantitative analysis of saliency. This approach aggregates saliency information at the object and modality level into hierarchical attention profiles, quantifying how agents allocate attention over time, thereby forming attention trajectories throughout training. Applied to Atari benchmarks, custom Pong environments, and muscle-actuated biomechanical user simulations in visuomotor interactive tasks, this methodology uncovers algorithm-specific attention biases, reveals unintended reward-driven strategies, and diagnoses overfitting to redundant sensory channels. These patterns correspond to measurable behavioral differences, demonstrating empirical links between attention profiles, learning dynamics, and agent behavior. To assess robustness of the attention profiles, we validate our findings across multiple saliency methods and environments. The results establish attention trajectories as a promising diagnostic axis for tracing how feature reliance develops during training and for identifying biases and vulnerabilities invisible to performance metrics alone.

Charlotte Beylier, Parvaneh Joharinad, Jürgen Jost et al.

Utilizing recently developed abstract notions of sectional curvature, we introduce a method for constructing a curvature-based geometric profile of discrete metric spaces. The curvature concept that we use here captures the metric relations between triples of points and other points. More significantly, based on this curvature profile, we introduce a quantitative measure to evaluate the effectiveness of data representations, such as those produced by dimensionality reduction techniques. Furthermore, Our experiments demonstrate that this curvature-based analysis can be employed to estimate the intrinsic dimensionality of datasets. We use this to explore the large-scale geometry of empirical networks and to evaluate the effectiveness of dimensionality reduction techniques.

Charlotte Beylier, Simon M. Hofmann, Nico Scherf

The learning process of a reinforcement learning (RL) agent remains poorly understood beyond the mathematical formulation of its learning algorithm. To address this gap, we introduce attention-oriented metrics (ATOMs) to investigate the development of an RL agent's attention during training. In a controlled experiment, we tested ATOMs on three variations of a Pong game, each designed to teach the agent distinct behaviours, complemented by a behavioural assessment. ATOMs successfully delineate the attention patterns of an agent trained on each game variation, and that these differences in attention patterns translate into differences in the agent's behaviour. Through continuous monitoring of ATOMs during training, we observed that the agent's attention developed in phases, and that these phases were consistent across game variations. Overall, we believe that ATOM could help improve our understanding of the learning processes of RL agents and better understand the relationship between attention and learning.