Decision Sciences & Systems
Technical University of Munich

Web 2 sw

Nils Kohring

Department of Informatics (I18)
Technical University of Munich
E-Mail: nils.kohringzzin.tum.de
Boltzmannstr. 3
85748 München, Germany
Phone: +49 (0) 89 289 - 17506
Hours: by arrangement

I'm a Ph.D. student at the DSS chair supervised by Prof. Bichler. My research focuses on the computation of equilibria in markets and auctions via multi-agent reinforcement learning methods.


Short Bio


  • 2016 - 2019             Master of Economathematics (M.Sc.), University of Cologne
  • 2018                        Visiting Student at The University of Tokyo, Japan
  • 2013 - 2016             Bachelor of Economathematics (B.Sc.), University of Cologne

Working Experience

  • 2019/06 - 2019/08   Data Science Intern at Fintech Startup
  • 2018/08 - 2019/02   Intern in the Applied Mathematics Team, Bayer (Leverkusen)
  • 2016/09 - 2018/04   Student Tutor for different mathematics lectures, University of Cologne
  • 2015/08 - 2015/10   Intern in Process Management, Deutsche Bank (Frankfurt a.M.)



Bichler, M.; Fichtl, M.; Heidekrüger, S.; Kohring, N.; and Sutterer, P.: Learning to Bid: Computing Bayesian Nash Equilibrium Strategies in Auctions via Neural Pseudo-gradient Ascent, Working Paper, 2020. Presented at the 2020 annual meeting of NBER Market Design Working Group. http://conference.nber.org/conf_papers/f144729.pdf.

M. Bichler, M. Fichtl, S. Heidekrüger, N. Kohring, and P. Sutterer. Learning equilibria in symmetric auction games using artificial neural networks. Nature Machine Intelligence, (3), 2021. [ link | pdf ]

S. Heidekrüger, N. Kohring, P. Sutterer, and M. Bichler. Equilibrium learning in combinatorial auctions: Computing approximate bayesian nash equilibria. In AAAI-21 Workshop on Reinforcement Learning in Games (AAAI-RLG 21), Online, Online, 2021.

S. Heidekrüger, N. Kohring, P. Sutterer, and M. Bichler. Multiagent learning for equilibrium computation in auction markets. In AAAI Spring Symposium on Challenges and Opportunities for Multi-Agent Reinforcement Learning (COMARL-21), Online, Online, 2021.

S. Heidekrüger, P. Sutterer, N. Kohring, and M. Bichler. Learning bayesian nash equilibria in auction games. In INFORMS Workshop on Data Science, Online, 2020.

S. Heidekrüger, P. Sutterer, N. Kohring, and M. Bichler. Equilibrium learning in combinatorial auctions: Computing approximate bayesian nash equilibria. In Workshop on Information Technology and Systems (WITS20), Online, Online, 2020.


Conference Talks

Learning Bayesian Nash Equilibria in Auction Games (Workshop on Data Science at the virtual INFORMS annual meeting, Washington D.C., USA, 11/2020)



For available thesis projects, check out our current thesis topics.


  • Business Analytics, Teaching Assistant (since WS19/20)
  • Seminar on Data Mining, Teaching Assistant (since SoSe20)

 Supervised Theses

  • Hyperparameter Optimization of a Deep Reinforcement Learning System for Equilibrium Computation, B.Sc. Informatics (2020)
  • Learning Approximate Bayes-Nash Equilibria with Opponent-Learning Awareness, M.Sc. Data Engineering and Analytics (2021)
  • Predicting the Individual Suitability for E-Mobility Using Machine Learning, M.Sc. Information Systems (2021), in cooperation with BMW
  • Data-driven Marketing Attribution Model Based Attention Mechanism for a Quantitative Estimation of TV-Advertisement Effects, M.Sc. Informatics (2021), in cooperation with ProSiebenSat.1 Media
  • A Survey on Particle Swarm Optimization with an Application to non-differentiable Vector Optimization, M.Sc. Information Systems (2021)


Decision Sciences & Systems (DSS), Department of Informatics (I18), Technische Universität München, Boltzmannstr. 3, 85748 Garching, Germany
©2002-2021 DSS All Rights Reserved
Impressum, Privacy Policy, Copyright Information and Disclaimer

We use cookies on our website. Some of them are essential for the operation of the site, while others help us to improve this site and the user experience (tracking cookies). You can decide for yourself whether you want to allow cookies or not. Please note that if you reject them, you may not be able to use all the functionalities of the site.