We are seeking motivated students with a passion for AI and energy systems to join the cutting-edge research project ADAPT on electricity market simulations with multi-agent reinforcement learning (RL).

Background:

Electricity markets are shaped by parameters stemming from policy and regulation such as network tariffs, levies, or subsidies. At the same time, market participants continuously adapt their strategies to these conditions. Inspired by The AI Economist [1] for taxation policy design, ASSUME [2] is currently being extended to test and derive mechanisms with two-level reinforcement learning (RL) for energy market and policy design. Foundations are based on game theory, as problems are commonly Stackelberg-type games. These games can be formulated as bilevel optimization problems that have been extensively researched in the past [3], serving as a starting point to develop small-scale use cases for market design challenges with two-level RL.

Objectives:

The Master's thesis project will have the following objectives:

• Identify suitable cases for two-level RL stemming from current discussions on electricity market design.
• Conceptualize and implement the derived problem in the simulation framework.
• Evaluate results from (two-level) RL with expected outcomes based on game theory and optimization.

Requirements:

• Interest in electricity markets and market mechanisms
• Prior knowledge in game theory and/or optimization
• Strong Python coding skills, experience with reinforcement learning is a plus

Formalities:

The thesis can be written in German or English. Please apply with a short letter of motivation (max. ½ page), your CV, and a current grade transcript. Work can commence immediately.

Relevant introductory literature:

[1] Zheng, Stephan, Alexander Trott, Sunil Srinivasa, David C. Parkes, and Richard Socher. 2022. “The AI Economist: Taxation Policy Design via Two-Level Deep Multiagent Reinforcement Learning.” Science Advances 8 (18): eabk2607. https://doi.org/10.1126/sciadv.abk2607.

[2] Harder, Nick, Kim K. Miskiw, Manish Khanra, et al. 2025. “ASSUME: An agent-based simulation framework for exploring electricity market dynamics with reinforcement learning.” SoftwareX 30: 102176. https://doi.org/10.1016/j.softx.2025.102176.

[3] Wogrin, Sonja, Salvador Pineda, and Diego A. Tejada-Arango. 2020. “Applications of Bilevel Optimization in Energy and Electricity Markets.” In Bilevel Optimization, edited by Stephan Dempe and Alain Zemkoho, vol. 161. Springer Optimization and Its Applications. Springer International Publishing. https://doi.org/10.1007/978-3-030-52119-6_5.