5 papers
FRInGe: Distribution-Space Integrated Gradients with Fisher--Rao Geometry
Gabriele Martino, Sebastian Tschiatschek
Gradient-based attribution methods are model-faithful and scalable, but Integrated Gradients (IG) can be brittle because explanations depend on heuristic baselines, straight-line p…
Plasticity Loss in Deep Reinforcement Learning: A Survey
Timo Klein, Christoph Luther, Manus McAuliffe +3
Plasticity refers to a network's ability to adapt to changing data distributions, which is crucial for the successful training of deep reinforcement learning agents. Loss of plasti…
Understanding and Improving Hyperbolic Deep Reinforcement Learning
Timo Klein, Thomas Lang, Andrii Shkabrii +6
The exponential volume growth of hyperbolic geometry can embed the hierarchical relationships between states in reinforcement learning (RL) with far less distortion than Euclidean…
Rule-Guided Reinforcement Learning Policy Evaluation and Improvement
Martin Tappler, Ignacio D. Lopez-Miguel, Sebastian Tschiatschek +1
We consider the challenging problem of using domain knowledge to improve deep reinforcement learning policies. To this end, we propose LEGIBLE, a novel approach, following a multi-…
Breaking the Reclustering Barrier in Centroid-based Deep Clustering
Lukas Miklautz, Timo Klein, Kevin Sidak +5
This work investigates an important phenomenon in centroid-based deep clustering (DC) algorithms: Performance quickly saturates after a period of rapid early gains. Practitioners c…