Moritz Lange, M.Sc.

RUB
Computer Science
INI
People
Moritz Lange, M.Sc.

moritz.lange@ini.rub.de

Theory of Neural Systems

Ruhr-Universität Bochum
Institut für Neuroinformatik
Universitätsstraße 150
Building NB, Room NB 3/35

D-44801 Bochum, Germany

moritz.lange@ini.rub.de

Selected Publications

2025

Object-centric Denoising Diffusion Models for Physical Reasoning
Lange, M., Engelhardt, R. C., Konen, W., Melnik, A., & Wiskott, L.
arXiv preprint arXiv:2507.04920

arxiv link

@article{LangeEngelhardtKonenEtAl2025, author = {Lange, Moritz and Engelhardt, Raphael C and Konen, Wolfgang and Melnik, Andrew and Wiskott, Laurenz}, title = {Object-centric Denoising Diffusion Models for Physical Reasoning}, journal = {arXiv preprint arXiv:2507.04920}, year = {2025}, }

Lange, M., Engelhardt, R. C., Konen, W., Melnik, A., & Wiskott, L.. (2025). Object-centric Denoising Diffusion Models for Physical Reasoning. arXiv preprint arXiv:2507.04920.

2024

Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks
Lange, M., Engelhardt, R. C., Konen, W., & Wiskott, L.
In eXplainable AI approaches for Deep Reinforcement Learning

link

@inproceedings{LangeEngelhardtKonenEtAl2024, author = {Lange, Moritz and Engelhardt, Raphael C. and Konen, Wolfgang and Wiskott, Laurenz}, title = {Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks}, booktitle = {eXplainable AI approaches for Deep Reinforcement Learning}, year = {2024}, }

Lange, M., Engelhardt, R. C., Konen, W., & Wiskott, L.. (2024). Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks. In eXplainable AI approaches for Deep Reinforcement Learning. Retrieved from https://openreview.net/forum?id=s1oVgaZ3dQ
*Best Paper Award* Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-visual Environments: A Comparison
Lange, M., Krystiniak, N., Engelhardt, R. C., Konen, W., & Wiskott, L.
In G. Nicosia, Ojha, V., La Malfa, E., La Malfa, G., Pardalos, P. M., & Umeton, R. (Eds.), Machine Learning, Optimization, and Data Science (pp. 177–191) Cham: Springer Nature Switzerland

link

@inproceedings{LangeKrystiniakEngelhardtEtAl2024, author = {Lange, Moritz and Krystiniak, Noah and Engelhardt, Raphael C. and Konen, Wolfgang and Wiskott, Laurenz}, title = {*Best Paper Award* Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-visual Environments: A Comparison}, booktitle = {Machine Learning, Optimization, and Data Science}, editor = {Nicosia, Giuseppe and Ojha, Varun and La Malfa, Emanuele and La Malfa, Gabriele and Pardalos, Panos M. and Umeton, Renato}, pages = {177–191}, publisher = {Springer Nature Switzerland}, address = {Cham}, year = {2024}, doi = {10.1007/978-3-031-53966-4_14}, }

Lange, M., Krystiniak, N., Engelhardt, R. C., Konen, W., & Wiskott, L.. (2024). *Best Paper Award* Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-visual Environments: A Comparison. In G. Nicosia, Ojha, V., La Malfa, E., La Malfa, G., Pardalos, P. M., & Umeton, R. (Eds.), Machine Learning, Optimization, and Data Science (pp. 177–191). Cham: Springer Nature Switzerland. http://doi.org/10.1007/978-3-031-53966-4_14

2023

Benchmarks for Physical Reasoning AI
Melnik, A., Schiewer, R., Lange, M., Muresanu, A. I., Saeidi, M., Garg, A., & Ritter, H.
Transactions on Machine Learning Research

link

@article{MelnikSchiewerLangeEtAl2023, author = {Melnik, Andrew and Schiewer, Robin and Lange, Moritz and Muresanu, Andrei Ioan and Saeidi, Mozhgan and Garg, Animesh and Ritter, Helge}, title = {Benchmarks for Physical Reasoning AI}, journal = {Transactions on Machine Learning Research}, year = {2023}, }

Melnik, A., Schiewer, R., Lange, M., Muresanu, A. I., Saeidi, M., Garg, A., & Ritter, H. (2023). Benchmarks for Physical Reasoning AI. Transactions on Machine Learning Research. Retrieved from https://openreview.net/forum?id=cHroS8VIyN

2025

Object-centric Denoising Diffusion Models for Physical Reasoning
Lange, M., Engelhardt, R. C., Konen, W., Melnik, A., & Wiskott, L.
arXiv preprint arXiv:2507.04920

arxiv link

@article{LangeEngelhardtKonenEtAl2025, author = {Lange, Moritz and Engelhardt, Raphael C and Konen, Wolfgang and Melnik, Andrew and Wiskott, Laurenz}, title = {Object-centric Denoising Diffusion Models for Physical Reasoning}, journal = {arXiv preprint arXiv:2507.04920}, year = {2025}, }

Lange, M., Engelhardt, R. C., Konen, W., Melnik, A., & Wiskott, L.. (2025). Object-centric Denoising Diffusion Models for Physical Reasoning. arXiv preprint arXiv:2507.04920.

2024

Ökolopoly: Case Study on Large Action Spaces in Reinforcement Learning
Engelhardt, R. C., Raycheva, R., Lange, M., Wiskott, L., & Konen, W.
In G. Nicosia, Ojha, V., La Malfa, E., La Malfa, G., Pardalos, P. M., & Umeton, R. (Eds.), Machine Learning, Optimization, and Data Science (pp. 109–123) Cham: Springer Nature Switzerland

@inproceedings{EngelhardtRaychevaLangeEtAl2024, author = {Engelhardt, Raphael C. and Raycheva, Ralitsa and Lange, Moritz and Wiskott, Laurenz and Konen, Wolfgang}, title = {Ökolopoly: Case Study on Large Action Spaces in Reinforcement Learning}, booktitle = {Machine Learning, Optimization, and Data Science}, editor = {Nicosia, Giuseppe and Ojha, Varun and La Malfa, Emanuele and La Malfa, Gabriele and Pardalos, Panos M. and Umeton, Renato}, pages = {109–123}, publisher = {Springer Nature Switzerland}, address = {Cham}, year = {2024}, }

Engelhardt, R. C., Raycheva, R., Lange, M., Wiskott, L., & Konen, W. (2024). Ökolopoly: Case Study on Large Action Spaces in Reinforcement Learning. In G. Nicosia, Ojha, V., La Malfa, E., La Malfa, G., Pardalos, P. M., & Umeton, R. (Eds.), Machine Learning, Optimization, and Data Science (pp. 109–123). Cham: Springer Nature Switzerland.
Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks
Lange, M., Engelhardt, R. C., Konen, W., & Wiskott, L.
In eXplainable AI approaches for Deep Reinforcement Learning

link

@inproceedings{LangeEngelhardtKonenEtAl2024, author = {Lange, Moritz and Engelhardt, Raphael C. and Konen, Wolfgang and Wiskott, Laurenz}, title = {Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks}, booktitle = {eXplainable AI approaches for Deep Reinforcement Learning}, year = {2024}, }

Lange, M., Engelhardt, R. C., Konen, W., & Wiskott, L.. (2024). Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks. In eXplainable AI approaches for Deep Reinforcement Learning. Retrieved from https://openreview.net/forum?id=s1oVgaZ3dQ
*Best Paper Award* Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-visual Environments: A Comparison
Lange, M., Krystiniak, N., Engelhardt, R. C., Konen, W., & Wiskott, L.
In G. Nicosia, Ojha, V., La Malfa, E., La Malfa, G., Pardalos, P. M., & Umeton, R. (Eds.), Machine Learning, Optimization, and Data Science (pp. 177–191) Cham: Springer Nature Switzerland

link

@inproceedings{LangeKrystiniakEngelhardtEtAl2024, author = {Lange, Moritz and Krystiniak, Noah and Engelhardt, Raphael C. and Konen, Wolfgang and Wiskott, Laurenz}, title = {*Best Paper Award* Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-visual Environments: A Comparison}, booktitle = {Machine Learning, Optimization, and Data Science}, editor = {Nicosia, Giuseppe and Ojha, Varun and La Malfa, Emanuele and La Malfa, Gabriele and Pardalos, Panos M. and Umeton, Renato}, pages = {177–191}, publisher = {Springer Nature Switzerland}, address = {Cham}, year = {2024}, doi = {10.1007/978-3-031-53966-4_14}, }

Lange, M., Krystiniak, N., Engelhardt, R. C., Konen, W., & Wiskott, L.. (2024). *Best Paper Award* Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-visual Environments: A Comparison. In G. Nicosia, Ojha, V., La Malfa, E., La Malfa, G., Pardalos, P. M., & Umeton, R. (Eds.), Machine Learning, Optimization, and Data Science (pp. 177–191). Cham: Springer Nature Switzerland. http://doi.org/10.1007/978-3-031-53966-4_14

2023

Sample-Based Rule Extraction for Explainable Reinforcement Learning
Engelhardt, R. C., Lange, M., Wiskott, L., & Konen, W.
In G. Nicosia, Ojha, V., La Malfa, E., La Malfa, G., Pardalos, P., Di Fatta, G., et al. (Eds.), Machine Learning, Optimization, and Data Science (pp. 330–345) Cham: Springer Nature Switzerland

@inproceedings{EngelhardtLangeWiskottEtAl2023, author = {Engelhardt, Raphael C. and Lange, Moritz and Wiskott, Laurenz and Konen, Wolfgang}, title = {Sample-Based Rule Extraction for Explainable Reinforcement Learning}, booktitle = {Machine Learning, Optimization, and Data Science}, editor = {Nicosia, Giuseppe and Ojha, Varun and La Malfa, Emanuele and La Malfa, Gabriele and Pardalos, Panos and Di Fatta, Giuseppe and Giuffrida, Giovanni and Umeton, Renato}, pages = {330–345}, publisher = {Springer Nature Switzerland}, address = {Cham}, year = {2023}, }

Engelhardt, R. C., Lange, M., Wiskott, L., & Konen, W. (2023). Sample-Based Rule Extraction for Explainable Reinforcement Learning. In G. Nicosia, Ojha, V., La Malfa, E., La Malfa, G., Pardalos, P., Di Fatta, G., et al. (Eds.), Machine Learning, Optimization, and Data Science (pp. 330–345). Cham: Springer Nature Switzerland.
Iterative Oblique Decision Trees Deliver Explainable RL Models
Engelhardt, R. C., Oedingen, M., Lange, M., Wiskott, L., & Konen, W.
Algorithms, 16(6)

link

@article{EngelhardtOedingenLangeEtAl2023, author = {Engelhardt, Raphael C. and Oedingen, Marc and Lange, Moritz and Wiskott, Laurenz and Konen, Wolfgang}, title = {Iterative Oblique Decision Trees Deliver Explainable RL Models}, journal = {Algorithms}, volume = {16}, number = {6}, year = {2023}, doi = {10.3390/a16060282}, }

Engelhardt, R. C., Oedingen, M., Lange, M., Wiskott, L., & Konen, W. (2023). Iterative Oblique Decision Trees Deliver Explainable RL Models. Algorithms, 16(6). http://doi.org/10.3390/a16060282
Benchmarks for Physical Reasoning AI
Melnik, A., Schiewer, R., Lange, M., Muresanu, A. I., Saeidi, M., Garg, A., & Ritter, H.
Transactions on Machine Learning Research

link

@article{MelnikSchiewerLangeEtAl2023, author = {Melnik, Andrew and Schiewer, Robin and Lange, Moritz and Muresanu, Andrei Ioan and Saeidi, Mozhgan and Garg, Animesh and Ritter, Helge}, title = {Benchmarks for Physical Reasoning AI}, journal = {Transactions on Machine Learning Research}, year = {2023}, }

Melnik, A., Schiewer, R., Lange, M., Muresanu, A. I., Saeidi, M., Garg, A., & Ritter, H. (2023). Benchmarks for Physical Reasoning AI. Transactions on Machine Learning Research. Retrieved from https://openreview.net/forum?id=cHroS8VIyN

Winter Term 2024/2025

Project seminar

Machine Learning: Unsupervised Methods (with Problem Based Learning)

Summer Term 2023

Lab courses

Introduction to Python

Summer Term 2022

Lab courses

Introduction to Python

2023

Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks

This project applies slow feature analysis to navigation tasks in reinforcement learning. It analyzes the state representations learned by slow feature analysis and compares them to those learned by convolutional neural networks and principal component analysis.

2023

Effects of Distributional Biases on Gradient-Based Causal Discovery in the Bivariate Categorical Case

An investigation of the effects of distributional biases on gradient-based methods for causal discovery, based on an empirical and theoretical analysis of the case of two categorical variables.

2023

Object-centric Denoising Diffusion Models for Physical Reasoning

A novel denoising diffusion architecture for physical reasoning. It is designed in an object-centric way, which enables it to model the trajectories of multiple interacting objects. Two novel conditioning approaches for diffusion make it possible to condition trajectories on arbitrary states at arbitrary time points for different objects.

2022

Benchmarks for Physical Reasoning AI

A survey of physical reasoning benchmarks and approaches in artificial intelligence.

2021

Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments

An empirical comparison of common auxiliary tasks in reinforcement learning, on five different non-visual environments and two reinforcement learning algorithms.

About the INI

The Institut für Neuroinformatik (INI) is a research unit of the Faculty of Computer Science at the Ruhr-Universität Bochum. Its scientific goal is to understand the fundamental principles through which organisms generate behavior and cognition while linked to their environments through sensory and effector systems. Inspired by our insights into such natural cognitive systems, we seek new solutions to problems of information processing in artificial cognitive systems. We draw from a variety of disciplines that include experimental psychology and neurophysiology as well as machine learning, neural artificial intelligence, computer vision, and robotics.

Contact

Universitätsstr. 150, Building NB, Room 3/32
D-44801 Bochum, Germany

Tel: (+49) 234 32-28967
Fax: (+49) 234 32-14210

sekretariat@ini.rub.de
www.ini.rub.de

Moritz Lange, M.Sc.

Theory of Neural Systems

Ruhr-Universität Bochum Institut für Neuroinformatik Universitätsstraße 150 Building NB, Room NB 3/35

D-44801 Bochum, Germany

Selected Publications

2025

2024

2023

2025

2024

2023

Winter Term 2024/2025

Summer Term 2023

Summer Term 2022

Ruhr-Universität Bochum
Institut für Neuroinformatik
Universitätsstraße 150
Building NB, Room NB 3/35