Supervision

I have supervised over 20 bachelor's and 6 master's theses, primarily in Reinforcement Learning, with projects also touching on Deep Learning, Large Language Models, and cybersecurity applications. Several of these projects led to publications at international venues, including ECAI 2025 workshops and the NLDL 2025 conference. Master and bachelor supervisions are listed separately in the tables below.

Master Thesis Supervision — 6 Students

Date Student Thesis Research Output
Aug 2025 Thomas Vos
Master in AI
Learning the optimal policy for Hanabi using deep reinforcement learning with quantized PWLC
Co-supervised with Jilles Dibangoye and Matthia Sabatelli
Mar 2025 Hugo Kolste
Master in AI
Scaling Up Centralized Multi-Agent Reinforcement Learning with Agent-by-Agent Optimization
Co-supervised with Jilles Dibangoye
Feb 2025 Fatemeh Ziad Alizadeh
Master in AI
Don't Focus on your Weakness, Use your Strengths: A Multi-Agent Approach for Multi-Hop Question-Answering Tasks for Large Language Models
Co-supervised with Tsegaye Tashu
Jan 2025 Luca Mueller
Master in AI
Formalizing Coverage-guided Greybox Fuzzing with Deep Reinforcement Learning
Co-supervised with Fatih Turkmen
ECAI 2025 (SPAIML)
Dec 2024 Davide Rigone
Master in CS
Collaborative Reinforcement Learning for Cyber Defense: Analysis of Environments, Strategies, and Policies
Co-supervised with Fatih Turkmen
ECAI 2025 (SPAIML)
Nov 2022 Lars T. G. Mulder
Master in IEM
Applying Fast Multi-agent Reinforcement Learning with Generalized Policy Updates
Co-supervised with Ming Cao


Bachelor Thesis Supervision — 20 Students

Date Student Thesis Research Output
Sep 2025 Kristaps Melbardis
Bachelor in AI
Enhancing Long-Context Understanding in Language Models via Titans Neural Long-Term Memory: A Case Study with Qwen, and the Babilong Dataset
Sep 2025 Manos Savvides
Bachelor in CS
Multi-Agent Reinforcement Learning for Cyber Defence
Co-supervised with Fatih Turkmen
Aug 2025 Benediktus Firstian Pradipta
Bachelor in AI
Shaping Reasoning Through Rewards: Investigating Reward Structures in Post-Training LLMs with Pure Reinforcement Learning
Aug 2025 Ravindra A. Tarunokusumo
Bachelor in AI
Boosting Accuracy and Efficiency of Budget Forcing in LLMs via Reinforcement Learning for Mathematical Reasoning
Co-supervised with T.M. Tashu
ECAI 2025 (sLLM)
Aug 2025 Andjela Matic
Bachelor in AI
Outperforming the Baseline: Transfer Learning in Atari via Parallelized Q-Networks
Jul 2025 Stan Ferguson
Bachelor in AI
Exploring One-Step Fixed Horizon Q-learning in Tabular Stochastic Environments
Jun 2025 Quinten Steringa
Bachelor in AI
No Supervision, No Problem: Pure Reinforcement Learning Improves Mathematical Reasoning in Small Language Models ECAI 2025 (sLLM)
Apr 2025 Rares Stefan Stoian
Bachelor in AI
Accelerating Model Based Reinforcement Learning Using GPU Through Parallelization of Dyna-Q Architecture
Co-supervised with Matthia Sabatelli
Feb 2025 Leon Tanis
Bachelor in AI
Bridging Faithfulness of Explanations and Deep Reinforcement Learning: A Grad-CAM Analysis of Space Invaders
Co-supervised with Marco Zullich
FDG 2025
Jan 2025 Catalin Zaharia
Bachelor in AI
Transfer Learning in Reinforcement Learning: When Task-Specific Adaptation Outperforms Generalization
Co-supervised with Matthia Sabatelli
Aug 2024 Andre van Dommele
Bachelor in AI
Enhancing Football Simulation Performance in Deep Reinforcement Learning Through Analytics-based Dense Reward Shaping
Aug 2024 Niclas Müller-Horf
Bachelor in AI
Improving Efficiency of a Hierarchical Reinforcement Learning Algorithm
Aug 2024 Jeremias Lino Ferrao
Bachelor in AI
World Model Agents with Changed-Based Intrinsic Motivation NLDL 2025
Aug 2024 Diana-Maria Arapu
Bachelor in AI
Sparse Rewards Reinforcement Learning: Addressing Vanishing Intrinsic Rewards in Change-Based Exploration Transfer
Jul 2024 Matej Priesol
Bachelor in AI
Forecasting Carbon Intensity and Solar Generation in the Building Sector
Co-supervised with J.D. Cardenas Cartagena
Mar 2024 Peter van den Bempt
Bachelor in AI
Investigating Mode-Switching and Reward Stream Separation in Hard-Exploration Problems
Co-supervised with Matthia Sabatelli
Jul 2021 Bo T. Kroezen
Bachelor in IEM
Stochastic Stability Analysis of Selection-Mutation Processes and Signaling Games
Co-supervised with Ming Cao
Feb 2021 Tautas Hoedtke
Bachelor in IEM
Safe Reinforcement Learning
Co-supervised with Ming Cao
Jul 2020 Muhammad Aqil Prasetyo
Bachelor in IEM
Using Reinforcement Learning to Design a State Feedback Controller
Co-supervised with Ming Cao
Feb 2020 Martijn van Dis
Bachelor in IEM
The Performance of Reinforcement Learning with Application for Adaptive Traffic Signal Controllers
Co-supervised with Ming Cao