collaborators

5 papers

cs.LG2026

Learning in Low-Dimensional Subspaces: Orthogonal Bottlenecks for Reinforcement Learning

Aleksandar Todorov, Matthia Sabatelli

Deep reinforcement learning (RL) agents commonly rely on high-dimensional neural representations, despite growing evidence that task-relevant value and policy structure may be intr…

cs.GT2026

Parametric Open Source Games

Aleksandar Todorov, Jesse ten Napel, Alexander Müller

Open-source game theory studies agents whose behavior may depend on one another's decision procedures, but most existing models use discrete or symbolic programs. We introduce para…

cs.LG2026

Trace-Mediated Peak Bias: Bridging Temporal Credit Assignment and Cognitive Heuristics in Deep Reinforcement Learning

Viktor Veselý, Aleksandar Todorov, Erwan Escudie +1

Temporal credit assignment is central to both biological and artificial intelligence, yet its interaction with non-linear function approximation is poorly understood. We identify a…

cs.LG2025

On The Presence of Double-Descent in Deep Reinforcement Learning

Viktor Veselý, Aleksandar Todorov, Matthia Sabatelli

The double descent (DD) paradox, where over-parameterized models see generalization improve past the interpolation point, remains largely unexplored in the non-stationary domain of…

cs.LG2025

Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning

Aleksandar Todorov, Juan Cardenas-Cartagena, Rafael F. Cunha +2

Plasticity loss, a diminishing capacity to adapt as training progresses, is a critical challenge in deep reinforcement learning. We examine this issue in multi-task reinforcement l…