Author

Oliver Niggemann

h-index 6 View on Semantic Scholar

We have 1 of 46 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Knowledge- and Gradient-Guided Reinforcement Learning for Parametrized Action Markov Decision Processes

This paper proposes the novel Neuro-Symbolic Knowledge- and Gradient-Guided Reinforcement Learning (KGRL) algorithm, which outperforms state-of-the-art RL baselines for PAMDPs in both, sample efficiency and episodic return.

Jonas Ehrhardt, René Heesch, Oliver Niggemann · arXiv.org · 0 citations