Hauptseminar Computer Graphics and Visualization (SS 2026)

Information

Registration

Please enroll in the Opal course and in Selma to participate in the seminar!

Schedule

General appointments in the seminar room APB/E009/U are on the following dates:

• 16.04.2026, 09:20 a.m. 
  Kickoff (organization, presentation of topics)
  Slides available in the Opal course.
• 23.04.2026., 09:20 a.m.
  Lecture on good practices in scientific writing and requirements to the full report
  Slides available after lecture.

Motivation

One of the most important aspects of science is to share results with others. In most cases, this is accomplished by publishing a paper in a scientific journal. High-quality scientific writing is therefore crucial for a successful research career. In this seminar, the participants will be introduced to scientific research in general and the essential aspects of literature study. The final goal is to write a review report on one of the topics below which will be presented at the end of the semester.

Topic: Reinforcement learning: explainability and applications

Advances in reinforcement learning (RL) have led to powerful agents capable of solving complex sequential decision-making problems. At the same time, there is a growing need to better understand, interpret, explain and reliably deploy these systems, especially in real-world settings. Research in explainability, model-based approaches, and practical applications of RL is rapidly evolving, offering new tools to analyze agent behavior, improve sample efficiency, and bridge the gap between simulation and reality.

Fot thise seminar each student (or a team of up to three students) must select one specific topic from the list below. Topics are organized into topic groups:

Topic Group 1: Explainable Reinforcement Learning

• Converting NN policies to interpretable formats
• Counterfactual explanations for RL agents
• Trajectory summarization and clustering
• Explainability in multi-agent reinforcement learning
• Visualization techniques for reinforcement learning

Topic Group 2: Real-World Applications of Reinforcement Learning

• Applications of RL in a specific domain (e.g., robotics, video games, simulations, LLM, etc)
• Sim-to-real transfer

Topic Group 3: World Models and Model-Based Reinforcement Learning

• State-of-the-art model-based RL methods
• JEPA-like architectures and their application to RL (e.g., TD-JEPA)
• Model predictive control methods for reinforcement learning

Topic selection

Please choose a topic from the list above in the Opal course of the seminar till 24.04.2026.

Task

Students will write a summary report on one of the given subtopics. Depending on the number of total participants, we will ask you to work in groups of up to 3 people. The report has to be written in English. Successful participation requires:

• A 1-2 page written overview of your topic.
• A graded written review in two-column paper format (approximately 6 pages per group member).
• A graded presentation (10 min per group member + 15 min discussion).