Fabian Raoul Pieroth
E-Mail: fabian.pieroth at tum.de
Phone: +49 (0) 89 289 - 17532
Office: Room 01.10.056
Boltzmannstr. 3
85748 Munich, Germany
Hours: by arrangement
Short Bio
I am a Ph.D. student supervised by Prof. Bichler. My research focus lies in finding descriptive properties of Multi-Agent Systems, e.g., equilibrium-computation, or quantification of cooperation, through the use of multi-agent reinforcement learning.
Education:
- 10/2017 - 01/2021: Master in Mathematics (M. Sc.), Technical University Munich
- 10/2013 - 10/2016: Bachelor in Mathematics (B. Sc.), Ludwig-Maximilians-University Munich
Working Experience:
- 08/2018 - 05/2021: Data Science Intern, MaibornWolff
- 09/2017 - 08/2018: Data Science Intern, Horvath&Partners
- 10/2016 - 01/2017: Intern in Credit Risk and Methodology, Bayern LB
Publications
Journal Publications
Learning Equilibrium in Bilateral Bargaining Games
Martin Bichler, Nils Kohring, Matthias Oberlechner, Fabian R. Pieroth
European Journal of Operational Research (EJOR), Dec 2022
Peer-Reviewed Conference and Workshop Papers
Alpha-Rank-Collections: Analyzing Expected Strategic Behavior with Uncertain Utilities
Fabian R. Pieroth, Martin Bichler
Accepted at the 25th ACM Conference on Economics and Computation (EC), 2024
Detecting Influence Structures in Multi-Agent Reinforcement Learning
Fabian R. Pieroth, Katherine Fitch, Lenz Belzner
Accepted at the 41st International Conference on Machine Learning (ICML), 2024
Enabling First-Order Gradient-Based Learning for Equilibrium Computation in Markets
Nils Kohring, Fabian R. Pieroth, Martin Bichler
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17327-17342, 2023.
Detecting Influence Structures in Multi-Agent Reinforcement Learning Systems
Fabian R. Pieroth, Katherine Fitch, Lenz Belzner
Accepted at the 2022 AAAI Workshop on Reinforcement Learning in Games (AAAI-RLG-22)
On Learning Stable Cooperation in the Iterated Prisoner's Dilemma with Paid Incentives
Xiyue Sun, Fabian R. Pieroth, Kyrill Schmid, Martin Wirsing, Lenz Belzner
Accepted at the 2022 DISCOLI Workshop on Distributed Collective Intelligence (DISCOLI 2022)
Academic Activities
- Program Committee Member, Uncertainty in Artificial Intelligence (UAI), 2021
Teaching
For available theses topics, check out this page.
Courses
-
Operations Research (SS21, SS22, SS23)
-
Learning in Games Seminar (SS22, SS23)
-
Seminar ITUB - "IT and Management Consulting" (WS 21/22, WS22/23)
-
Auction Theory and Market Design (WS21/22, WS22/23)
Supervised Theses
Duc Tien Nguyen, Comparison of Deterministic and Distributional Reinforcement Learning Algorithms in Continous Auction Games, B.Sc. Informatics (2023)
Michal Cizevskij, A Comparison Between the Use of Unlabeled and Weakly Labeled Data in Active Learning for a Text Classification Problem, B.Sc. Informatics (2023) in cooperation with MaibornWolff
Ferdinand Brinker, Approximating Equilibrium Strategies in Sequential Colonel Blotto Games with Multi-Agent Reinforcement Learning, M.Sc. Informatics (2022)
Matija Novakovic, Analyzing Learning Dynamics in Finite N-Player Normal-Form Games with Varying Degrees of Cooperation, B.Sc. Information Systems (2022)
Felix Sittenauer, Imitation Learning for Robust Strategies in Multi-Agent Reinforcement Learning, M.Sc. Informatics (2022)
Julian Riß, Measuring Interdependencies in Multi-Agent Reinforcement Learning Systems in the Discounted Reward Setting, B.Sc. Informatics (2021)
Abyaad Rafid. Exploring Influence Structures in Multi-Agent Reinforcement Learning Systems, Guided Research B.Sc. Informatics (2021)
Korbinian Hainz. Learning Dynamics in Two-sided Matching Markets, B.Sc. Information Systems (2021)