Christoph Brüne

Low Dimensional State Representation Learning with Reward-shaped Priors

2021

Reinforcement Learning has been able to solve many complicated robotics tasks without any need for feature engineering in an end-to-end fashion. However, learning the optimal policy directly from the sensory inputs, i.e the observations, often …

Deep Networks are Reproducing Kernel Chains

2025 · arXiv (Cornell University)

Identifying an appropriate function space for deep neural networks remains a key open question. While shallow neural networks are naturally associated with Reproducing Kernel Banach Spaces (RKBS), deep networks present unique challenges. In this work, …