collaborators

5 papers

cs.LG2023

A Multi-Task Approach to Robust Deep Reinforcement Learning for Resource Allocation

Steffen Gracla, Carsten Bockelmann, Armin Dekorsy

With increasing complexity of modern communication systems, machine learning algorithms have become a focal point of research. However, performance demands have tightened in parall…

cs.LG2023

On the Importance of Exploration for Real Life Learned Algorithms

Steffen Gracla, Carsten Bockelmann, Armin Dekorsy

The quality of data driven learning algorithms scales significantly with the quality of data available. One of the most straight-forward ways to generate good data is to sample or…

cs.LG2023

Robust Deep Reinforcement Learning Scheduling via Weight Anchoring

Steffen Gracla, Edgar Beck, Carsten Bockelmann +1

Questions remain on the robustness of data-driven learning methods when crossing the gap from simulation to reality. We utilize weight anchoring, a method known from continual lear…

eess.SY2023

Learning Resource Scheduling with High Priority Users using Deep Deterministic Policy Gradients

Steffen Gracla, Edgar Beck, Carsten Bockelmann +1

Advances in mobile communication capabilities open the door for closer integration of pre-hospital and in-hospital care processes. For example, medical specialists can be enabled t…

eess.SP2023

Learning Model-Free Robust Precoding for Cooperative Multibeam Satellite Communications

Steffen Gracla, Alea Schröder, Maik Röper +3

Direct Low Earth Orbit satellite-to-handheld links are expected to be part of a new era in satellite communications. Space-Division Multiple Access precoding is a technique that re…