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: WS22/23, WS21/22, WS20/21
  • Quantum Applications: SS23, SS22
  • Intelligent Systems: WS22/23
  • Quantum Computing Programming: 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

  • Quantum Auto Encoder using Variational Quantum Circuits
  • Evaluating Amplitude Embedding and Auto Encoded Angle Embedding for Variational Quantum Circuits and Convolutional Quantum Neural Networks
  • Multi Agent Quantum Reinforcement Learning using Quantum Boltzmann Machines
  • Evaluating Weight Shaping for Quantum Layers in Variational Quantum Circuits
  • 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 3D Fish Domain using Reinforcement Learning
  • Quantum Aware Optimizers

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

📖 Theses in progress

  • Multi-Agent Exploration through Peer Incentivization – Johannes Tochtermann
  • Quantum Multi-Agent Reinforcement Learning using Evolutionary Optimization – Felix Topp
  • Analyzing Reinforcement Learning strategies from a parameterized quantum walker – Lorena Wemmer
  • Generalizing Agents in the Starcraft Multi-Agent Challenge – Balthasar Schüss
  • 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
  • Quantum-Enhanced Denoising Diffusion Model – Gerhard Stenzel
  • Dimensionality Reduction with Autoencoders for Efficient Classification with Variational Quantum Circuits – Jonas Maurer

✅ Completed theses

  • 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

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}
}