![]() |
Stefan Heidekrüger |
|
Department of Informatics (I18)
Technical University of Munich
|
||
|
||
E-Mail: | stefan heidekrueger tum de . @ . |
|
Office: |
Room 01.10.056
Boltzmannstr. 3
85748 München, Germany
|
|
Phone: | +49 (0) 89 289 - 17530 | |
Hours: | by arrangement | |
|
I'm a PhD student at the DSS chair supervised by Prof. Bichler. My research focusses on computation of equilibria in incomplete information games, especially markets and auctions and using multi-agent reinforcement learning methods.
Short Bio
Education
- Since 2018 Research Associate, Decision Sciences & Systems, TUM
- 2016 - 2018 Data Scientist, Business Analytics and Artificial Intelligence, Telefónica Germany
- 2014 - 2016 M.Sc. Mathematics in Operations Research, Technische Universität München
- 2014 Erasmus+ student at KTH Royal Institute of Technology (Stockholm, Sweden)
- 2013 - 2016 internships at a.hartrodt (2013) and zeb.rolfes.schierenbeck.associates (2015)
working student positions at a.hartrodt (2013-14), Telefónica Germany (2016), and SAP (2016)
student research assistant positions at TUM (2014, 2015) and HelmholtzZentrum München (2015-16) - 2012 - 2013 Visiting Student at The Hong Kong University of Science and Technology
- 2010 - 2014 B.Sc. Mathematics, TUM
Publications
S. Heidekrüger, P. Sutterer, N. Kohring, M. Fichtl, and M. Bichler: Equilibrium Learning in Combinatorial Auctions: Computing Approximate Bayesian Nash Equilibria via Pseudogradient Dynamics, in Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021), 2021 (forthcoming).
[Previous versions have been presented at the 2020 Workshop on Information Technology and Systems (WITS20), and the 2021 AAAI Workshop on Reinforcement Learning in Games (AAAI-RLG-21)]
S. Heidekrüger, P. Sutterer, N. Kohring, and M. Bichler: Multiagent Learning for Equilibrium Computation in Auction Markets, AAAI Spring Symposium on Challenges and Opportunities for Multi-Agent Reinforcement Learning (COMARL-21), March 2021 (forthcoming)
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
S. Heidekrüger, P. Sutterer, and M. Bichler. Computing approximate bayes-nash equilibria through neural self-play. In Workshop on Information Technology and Systems (WITS19), Munich, Germany, 2019.
Teaching
Courses
- Business Analytics, Teaching Assistant (Winter Term 2018/19, 2019/20, 20/21)
- Seminar on Data Mining, TA (Summer Term 2019, 2020)
- Seminar ITUB - "IT and Management Consulting", TA (Winter Term 2019/20, 20/21)
Completed Student Projects
-
Daniel Schroter Reinforcement Learning in the MIT Beer Distribution Game, BSc Thesis, Informatics (2020) Markus Ewert Efficient Query Strategies in Preference Elicitation via Deep Learning, MSc Thesis, Information Systems (2020) Anne Christopher Fast Solvers for Batched Constrained Optimization Problems, MSc Thesis, Mathematics in Data Science (2020) Lukas Feye Confidence-Moderated Policy Advice in Multi-Agent Reinforcement Learning, BSc Thesis, Information Systems (2020) Florian Ziesche Human Interpretable Machine Learning: A Machine Learning Approach for Risk Scoring, MSc Thesis, Mgmt & Technlogy (2019) Sebastian Rief Detection of anomalies in large-scale accounting data using unsupervised machine learning, MSc Thesis, Mgmt & Tech. (2019) Kevin D. Falkenstein Learning Equilibrium Strategies in Auctions via Deep Neural Networks, MSc Thesis, Information Systems (2018)