Fabian Ritz, M.Sc.

Fabian Ritz, M.Sc.

Lehrstuhl für Mobile und Verteilte Systeme

Ludwig-Maximilians-Universität München, Institut für Informatik

Oettingenstraße 67
80538 München

Raum E 107

Telefon: +49 89 / 2180-9218

Fax: +49 89 / 2180-9148

Mail: fabian.ritz@ifi.lmu.de

Teaching

Research

  • Deep Reinforcement Learning in Multi-Agent Systems:
    • Exploration strategies
    • Reward shaping
    • Implicite and explicite coordination
    • (Safety-) Specification compliance

Theses

  • Study the impact of different potential based reward shaping (PBRS) schemes on the convergence of RL algorithms (discrete multi agent domain) [master]
  • Evolve RL predators in a closed ecosystem with reproducing prey (continuous multi agent domain) [master]
  • Auto-evolve RL reward-functions to reach specification compliance (discrete single- or multi-agent domain) [bachelor, master]

If you have any questions or would like to apply for a topic, please send me an e-mail. Always feel free to pitch your own ideas regarding any of my research!

Publications

2020

  • Fabian Ritz, Felix Hohnstein, Robert Müller, Thomy Phan, Thomas Gabor, Carsten Hahn and Claudia Linnhoff-Popien, „Towards Ecosystem Management from Greedy Reinforcement Learning in a Predator-Prey Setting“, in Artificial Life Conference Proceedings, MIT Press, 2020, pp. 518-525. [DOI][PDF]
  • Carsten Hahn, Fabian Ritz, Paula Wikidal, Thomy Phan, Thomas Gabor, and Claudia Linnhoff-Popien, „Foraging Swarms using Multi-Agent Reinforcement Learning“, in Artificial Life Conference Proceedings, MIT Press, 2020, pp. 333–340. [DOI][PDF]
  • Thomas Gabor, Leo Sünkel, Fabian Ritz, Thomy Phan, Lenz Belzner, Christoph Roch, Sebastian Feld, Claudia Linnhoff-Popien, „The Holy Grail of Quantum Artificial Intelligence: Challenges in Accelerating the Machine Learning Pipeline“, in First International Workshop on Quantum Software Engineering (Q-SE), 2020. [PDF]
  • Thomy Phan, Thomas Gabor, Andreas Sedlmeier, Fabian Ritz, Bernhard Kempter, Cornel Klein, Horst Sauer, Reiner Schmid, Jan Wieghardt, Marc Zeller, and Claudia Linnhoff-Popien, „Learning and Testing Resilience in Cooperative Multi-Agent Systems“, in 19th Conference on Autonomous Agents and Multiagent Systems (AAMAS ’20), 2020, pp. 1055-1063. [DOI][PDF][video]
  • Thomy Phan, Lenz Belzner, Kyrill Schmid, Thomas Gabor, Fabian Ritz, Sebastian Feld, and Claudia Linnhoff-Popien, „A Distributed Policy Iteration Scheme for Cooperative Multi-Agent Policy Approximation“, in Adaptive and Learning Agents Workshop (ALA@AAMAS ’20), 2020. [DOI][PDF][video]
  • Carsten Hahn, Thomy Phan, Sebastian Feld, Christoph Roch, Fabian Ritz, Andreas Sedlmeier, Thomas Gabor, and Claudia Linnhoff-Popien, „Nash Equilibria in Multi-Agent Swarms“, in 12th International Conference on Agents and Artificial Intelligence (ICAART), SciTePress, 2020, pp. 234-241. [DOI][PDF]
  • Thomas Gabor, Andreas Sedlmeier, Thomy Phan, Fabian Ritz, Marie Kiermeier, Lenz Belzner, Bernhard Kempter, Cornel Klein, Horst Sauer, Reiner Schmid, Jan Wieghardt, Marc Zeller and Claudia Linnhoff-Popien, „The scenario coevolution paradigm: adaptive quality assurance for adaptive systems, in International Journal on Software Tools for Technology Transfer (2020) Vol. 22, Springer, 2020,  pp. 457–476 [DOI][PDF]

2019

  • Robert Müller, Stefan Langer, Fabian Ritz, Cristoph Roch, Steffen Illium, and Claudia Linnhoff-Popien, „Soccer Team Vectors“, in Machine Learning and Knowledge Discovery in Databases: International Workshops of ECML PKDD 2019, Springer, 2019, pp. 247-257. [DOI][PDF]
  • Daniel Elsner, Stefan Langer, Fabian Ritz, Robert Müller and Steffen Illium, „Deep Neural Baselines for Computational Paralinguistics“, in Proc. Interspeech 2019, ISCA Archive, 2019, pp. 2388-2392. [DOI][PDF]

2018

  • Fabian Ritz and Alf Zugenmaier, „The Impact of Uncle Rewards on Selfish Mining in Ethereum“, in 2018 IEEE European Symposium on Security and Privacy Workshops (EuroS&PW), IEEE Computer Society, 2018, pp. 50-75. [DOI][PDF]