activity
20242026
collaborators

5 papers

math.OC2026

A Two-Timescale Primal-Dual Framework for Reinforcement Learning via Online Dual Variable Guidance

Axel Friedrich Wolter, Tobias Sutter

We study reinforcement learning by combining recent advances in regularized linear programming formulations with the classical theory of stochastic approximation. Motivated by the…

cs.LG2025

Reliability-Adjusted Prioritized Experience Replay

Leonard S. Pleiss, Tobias Sutter, Maximilian Schiffer

Experience replay enables data-efficient learning from past experiences in online reinforcement learning agents. Traditionally, experiences were sampled uniformly from a replay buf…

math.OC2025

Distributional Adversarial Attacks and Training in Deep Hedging

Guangyi He, Tobias Sutter, Lukas Gonon

In this paper, we study the robustness of classical deep hedging strategies under distributional shifts by leveraging the concept of adversarial attacks. We first demonstrate that…

math.OC2025

Asymptotic Optimality in Data-Driven Decision Making

Radek Salač, Michael Kupper, Tobias Sutter

Given data generated by an observable stochastic process, we study how to construct statistically optimal decisions for general stochastic optimization problems. Our setting encomp…

cs.LG2024

Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms

Felix Petersen, Christian Borgelt, Tobias Sutter +3

When training neural networks with custom objectives, such as ranking losses and shortest-path losses, a common problem is that they are, per se, non-differentiable. A popular appr…