Student Theses

You can find all student theses that I mentored as primary advising assistant below. The complete list of co-mentored student theses can be found here.

Master Theses

2023

• A Spatial Social Dilemma Environment for Multi-Agent Reinforcement Learning (A. Perzl)
• Generalization in Multi-Agent Reinforcement Learning using Minimax Learning (A. Feimer)
• Generalizing Agents in the Starcraft Multi-Agent Challenge (B. Schüss)
• Hidden Attacks in Multi-Agent Reinforcement Learning (A. Unterauer)

2022

• Classification of Classical and Quantum Algorithms with Artificial Neural Networks (N. Kraus)
• Adaptive Resilient Multi-Agent Reinforcement Learning (N. Czogalla)

2021

• Learning Trust in Multi-Agent Systems (F. Sommer)
• Evaluating Resilience in Antagonist-based Multi-Agent Reinforcement Learning (K. Blanz)
• Neural Architecture Search using Upside Down Reinforcement Learning (S. Cronjaeger)

2020

• Uncorrelated and Prioritized Reservoir Sampling for RL with Restricted Memory over Arbitrary Time-Spans (F. Cuevas)
• Assembly of Multi-Agent Formations using Reinforcement Learning (M. Peters)

2018

• Reinforcement Learning with Graph-Convolutional Neural Networks (D. Gehring)

Bachelor Theses

2022

• Finding Dominant Strategies and Equilibria in Minority Games Using Reinforcement Learning (C. Göhring)
• Evaluation of Aggregation Mechanisms for Federated Reinforcement Learning (P. Seipl)
• Multi-Agent Reinforcement Learning with Transformer-Based Policies (W. Maniszewska)
• Predicting the Optimal Approximation Level for Quantum Annealing (M. Börner)
• Evolutionary Subgoal-Discovery for Temporal Abstract Planning (H. An)

2021

• Pretraining of Reinforcement Learning Models for Federated Learning (C. Reinig)

2020

• Hexar.io as a Challenging Benchmark for Multi-Agent Reinforcement Learning (D. Hansmair)
• Stackelberg Routing with Fairness Considerations (M. Fischer)
• Adversarial Planning for Pursuit-Evasion Scenarios (M. Philip)
• Learning to Play Pommerman with Emergent Communication (P. Gschoßmann)

2019

• Multi-Step Deep Q-Networks with Stacked Target Networks (E. Terzieva)
• Pooling of Target Networks in Deep Reinforcement Learning (S. Geffert)

Project Work

2021

• Complex Value-based Deep Learning and Applications to Reinforcement Learning (F. Cuevas)

2020

• GRABZero (D. Ratke)
• Development of a Predator-Prey Domain for Multi-Agent Reinforcement Learning (S. Cronjaeger)
• Implementation of a Testbed for Adversarial Multi-Agent Reinforcement Learning (K. Blanz)
• Enhancing Value-based Reinforcement Learning with Tree Search (M. Kessler, 2020)