Michael Kölle, M.Sc.

Michael Kölle, M.Sc.

Lehrstuhl für Mobile und Verteilte Systeme

Ludwig-Maximilians-Universität München, Institut für Informatik

Oettingenstraße 67
80538 München

Raum E109

Telefon: +49 89 / 2180-9160

Fax: +49 89 / 2180-9148

Mail: michael.koelle@ifi.lmu.de

🔬 Research Interests

  • Quantum Artificial Intelligence
  • Reinforcement Learning
  • Multi-Agent Systems

🎓 Teaching (Assistance)

  • Rechnerarchitektur: SS23, SS22 (Lehrpreis beste Bachelor Vorlesung), SS21
  • Betriebssysteme: WS23/24, WS22/23, WS21/22, WS20/21
  • Quantum Applications: SS23, SS22
  • Intelligent Systems: WS23/24, WS22/23
  • Quantum Computing Programming: WS23/24, SS23, WS22/23, SS22, WS21/22, SS21

We are always looking for new tutors: Tutor:in für den Lehrbetrieb (m/w/d)

💡 Open thesis ideas

  • Evaluating Weight Shaping for Quantum Layers in Variational Quantum Circuits
  • Quantum Aware Optimizers – (e.g. Quantum-aware Adam)
  • Multi Agent Quantum Reinforcement Learning using Quantum Boltzmann Machines
  • Benchmarking State-of-the-Art Quantum Computing Frameworks (Simulators) for Quantum Machine Learning Applications
  • Optimizing/Building Quantum Circuits with Reinforcement Learning
  • Quantum Planning – Monte Carlo Rollouts with Quantum Walks
  • Emergent Boids in a Predator-Prey Setting using Reinforcement Learning
  • Quantum Soups – Self Replicating Quantum Neural Networks
  • Emergent Cooperation through Quantum Networks
  • Evaluating Quantum Actor-Critic Methods for Reinforcement Learning
  • Evaluating Metaheuristic Optimization Algorithms for Quantum Reinforcement Learning
  • Audio Preparation and Classification using Variational Quantum Circuits.

If you are interested in one of the advertised topics above or have your own ideas, send us: Anfrage Abschlussarbeiten

📖 Theses in progress

  • Quantum-Enhanced Denoising Diffusion Model – Gerhard Stenzel
  • Dimensionality Reduction with Autoencoders for Efficient Classification with Variational Quantum Circuits – Jonas Maurer
  • Efficient unsupervised quantum anomaly detection using one-class support vector machines – Afrae Ahouzi
  • A Reinforcement-Learning Environment for purposeful Quantum Circuit Design and Quantum State Preparation – Tom Schubert
  • Parameter reduction with quantum circuits – The potential of Quantum Proximal Policy Optimization – Timo Witter
  • Anomalous Sound Detection with Multimodal Embeddings – Lara Lanz
  • Exploring Multi-Agent Reinforcement Learning Strategies in a Predator-Prey Setting – Yannick Erpelding

✅ Completed theses

  • Multi-Agent Exploration through Peer Incentivization – Johannes Tochtermann
  • Analyzing Reinforcement Learning strategies from a parameterized quantum walker – Lorena Wemmer
  • Quantum Multi-Agent Reinforcement Learning using Evolutionary Optimization – Felix Topp
  • Efficient quantum circuit architecture for parameterized coined quantum walks on many bipartite graphs – Viktoryia Patapovich
  • Scalable Discrete Communication in Decentralized MARL using Clustering – Valentin Kerle
  • Generalizing Agents in the Starcraft Multi-Agent Challenge – Balthasar Schüss
  • Quantum Enhanced Policy Gradient Methods for Reinforcement Learning – Mohamad Hgog
  • Embedding Classical Data for efficient Quantum Machine Learning – David Münzer
  • Efficient Data Embedding for offline Handwriting Recognition using Quantum Support Vector Machines – Leopold Bodendörfer
  • Efficient embedding in Quantum Support Vector Machines using a specialized NISQ approach – Jonathan Wulf
  • A comparison of Generative Adversarial Networks and Variational Autoencoders for Density Estimation – Gerhard Stenzel
  • Anomaly Detection on Medical Images using Classification of Clustering Results – Sebastian Haugg
  • A Risk-Sensitive Approach for modeling the Hedging Portfolio Problem with Reinforcement Learning – Quentin Mathieu
  • Exploring the impact of markets on the credit assignment problem in a multi-agent environment – Zarah Zahreddin
  • Learning to Participate through Trading of Reward Shares – Tim Matheis

📚 Publications

2023

  • T. Phan, F. Ritz, P. Altmann, M. Zorn, J. NNüßlein, M. Kölle, T. Gabor, and C. Linnhoff-Popien, „Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Observability,“ in Proceedings of the 40th International Conference on Machine Learning (ICML), 2023.
    [BibTeX] [Download PDF]
    @inproceedings{phanICML23,
    author = {Thomy Phan and Fabian Ritz and Philipp Altmann and Maximilian Zorn and Jonas NN{\"u}{\ss}lein and Michael K{\"o}lle and Thomas Gabor and Claudia Linnhoff-Popien},
    title = {Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Observability},
    year = {2023},
    publisher = {PMLR},
    booktitle = {Proceedings of the 40th International Conference on Machine Learning (ICML)},
    location = {Hawaii, USA},
    url  = {https://thomyphan.github.io/publication/2023-07-01-icml-phan},
    eprint  = {https://thomyphan.github.io/files/2023-icml-preprint.pdf},
    }

  • J. Stein, F. Chamanian, M. Zorn, J. Nüßlein, S. Zielinski, M. Kölle, and C. Linnhoff-Popien, „Evidence that PUBO outperforms QUBO when solving continuous optimization problems with the QAOA,“ arXiv preprint arXiv:2305.03390, 2023.
    [BibTeX]
    @article{stein2023evidence,
    title={Evidence that PUBO outperforms QUBO when solving continuous optimization problems with the QAOA},
    author={Stein, Jonas and Chamanian, Farbod and Zorn, Maximilian and N{\"u}{\ss}lein, Jonas and Zielinski, Sebastian and K{\"o}lle, Michael and Linnhoff-Popien, Claudia},
    journal={arXiv preprint arXiv:2305.03390},
    year={2023},
    }

  • M. Kölle, S. Illium, M. Zorn, J. Nüßlein, P. Suchostawski, and C. Linnhoff-Popien, „Improving Primate Sounds Classification using Binary Presorting for Deep Learning.“ 2023.
    [BibTeX]
    @inproceedings {koelle23primate,
    title = {Improving Primate Sounds Classification using Binary Presorting for Deep Learning},
    author = {K{\"o}lle, Michael and Illium, Steffen and Zorn, Maximilian and N{\"u}{\ss}lein, Jonas and Suchostawski, Patrick and Linnhoff-Popien, Claudia},
    year = {2023},
    organization = {Int. Conference on Deep Learning Theory and Application - DeLTA 2023},
    publisher = {Springer CCIS Series},
    }

2022

  • S. Illium, G. Griffin, M. Kölle, M. Zorn, J. Nüßlein, and C. Linnhoff-Popien, VoronoiPatches: Evaluating A New Data Augmentation MethodarXiv, 2022. doi:10.48550/ARXIV.2212.10054
    [BibTeX] [Download PDF]
    @misc{https://doi.org/10.48550/arxiv.2212.10054,
    doi = {10.48550/ARXIV.2212.10054},
    url = {https://arxiv.org/abs/2212.10054},
    author = {Illium, Steffen and Griffin, Gretchen and Kölle, Michael and Zorn, Maximilian and Nüßlein, Jonas and Linnhoff-Popien, Claudia},
    keywords = {Computer Vision and Pattern Recognition (cs.CV), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {VoronoiPatches: Evaluating A New Data Augmentation Method},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
    }

  • S. Illium, M. Zorn, C. Lenta, M. Kölle, C. Linnhoff-Popien, and T. Gabor, Constructing Organism Networks from Collaborative Self-ReplicatorsarXiv, 2022. doi:10.48550/ARXIV.2212.10078
    [BibTeX] [Download PDF]
    @misc{https://doi.org/10.48550/arxiv.2212.10078,
    doi = {10.48550/ARXIV.2212.10078},
    url = {https://arxiv.org/abs/2212.10078},
    author = {Illium, Steffen and Zorn, Maximilian and Lenta, Cristian and Kölle, Michael and Linnhoff-Popien, Claudia and Gabor, Thomas},
    keywords = {Neural and Evolutionary Computing (cs.NE), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {Constructing Organism Networks from Collaborative Self-Replicators},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
    }

  • K. Schmid, M. Kölle, and T. Matheis, „Learning to Participate through Trading of Reward Shares,“ , 2022.
    [BibTeX]
    @article{schmidlearning,
    title = {Learning to Participate through Trading of Reward Shares},
    author = {Schmid, Kyrill and Kölle, Michael and Matheis, Tim},
    year = {2022}
    }

  • M. Kölle, L. Rietdorf, and K. Schmid, Decentralized scheduling through an adaptive, trading-based multi-agent systemarXiv, 2022. doi:10.48550/ARXIV.2207.11172
    [BibTeX] [Download PDF]
    @misc{https://doi.org/10.48550/arxiv.2207.11172,
    doi = {10.48550/ARXIV.2207.11172},
    url = {https://arxiv.org/abs/2207.11172},
    author = {Kölle, Michael and Rietdorf, Lennart and Schmid, Kyrill},
    keywords = {Artificial Intelligence (cs.AI), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {Decentralized scheduling through an adaptive, trading-based multi-agent system},
    publisher = {arXiv},
    year = {2022},
    copyright = {arXiv.org perpetual, non-exclusive license}
    }

  • A. Sedlmeier, M. Kölle, R. Müller, L. Baudrexel, and C. Linnhoff-Popien, „Quantifying Multimodality in World Models,“ in Proceedings of the 14th International Conference on Agents and Artificial Intelligence – Volume 1: ICAART,, 2022, pp. 367-374. doi:10.5220/0010898500003116
    [BibTeX]
    @conference{multimod_icaart22,
    author = {Andreas Sedlmeier and Michael Kölle and Robert Müller and Leo Baudrexel and Claudia Linnhoff-Popien},
    title = {Quantifying Multimodality in World Models},
    booktitle = {Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
    year = {2022},
    pages = {367-374},
    publisher = {SciTePress},
    organization = {INSTICC},
    doi = {10.5220/0010898500003116},
    isbn = {978-989-758-547-0}
    }