FH Wedel LMS

Titel: Advanced Topics in Reinforcement Learning

Seminar Facilitator: Hendrik Annuth, Marco Pawlowski

Description: Reinforcement Learning (RL) is revolutionizing decision-making and automation in engineering and production. This seminar explores how RL enables systems to learn optimal strategies through interaction and feedback.

Language: The scientific literature and the scientific field of data science is vastly represented in the English language. Therefore, the written version of the presentation and the presentation material must be written in English language. However, the presentation itself can be done in German language, even so, English is preferred. The English skill set of participants will not influence the evaluation of the lecture. Participants are expected to prepare their presentations, thus, if the presentation content is hard to understand, due to ill-prepared presenters, this will influence the evaluation of the lecture for obvious reasons, however.

Expectations: Every participant is expected to do a  presentation with a maximum length of 45 min followed by a discussion on their topic and create a 10-page written version of their lecture. All presentations in the seminar are held under compulsory attendance (Anwesenheitspflicht).  Participants are expected to communicate with one another to avoid overlapping topics and discuss who will present which topic. The submission date for the written submissions one week before your presentation. The document needs to adhere with the PDF file standard.

Naming convention for the written version:

Seminar_[Topic number with leading zero]_[Semester/Year]_[Surname]_[Title].pdf

Example: Seminar_04_SS24_Schmidt_Plasma Converter.pdf

The written submission is a preparation for the master’s thesis and is thus expected to aim for scientific standards. Texts should be easy to understand and properly illustrated. Participants are expected to name important sources and authors, and quote publications. Participants are expected to use source material that meets scientific standards, such as scientific literature and other forms of scientific publications. The written submission cannot exceed 10-page length, it can have less than 10 pages. Any type and form of page is counted, including pages such as flyleafs or tables of content . The evaluation of participants' lectures is not only based on their expressed knowledgeability in their given field, but also on their didactical preparation of their presentation and written material. Thus, participants are expected to have their explanations of content, representations, and illustrations ready and practiced. The focus of the evaluation is on the presentation. It is important to remember that the written version and the oral version may differ in terms of content. This is particularly useful if you deepen topics in the presentation to make them easier to understand and when use additional examples.

LaTeX  Template: There is a LaTeX template available for creating the written submission. Layout-specific changes should not be made to the document. In the header, please adjust only the semester but not the header text itself.

Schedule: The seminar has 5 ECTS points and thus an expected workload of 150 working hours. To honor each individual work, there will be a maximum of two presentations a day—possibly three, given special circumstances—leading to 6 expected appointments. Thus, the appointments for the presentations might already start on the first day of the semester! Participants have to be aware of this, especially when choosing one of the first topics. When you know you will not be giving  your presentation, please inform us as early as possible, so no participants will drive to the seminar to learn that it is not taking place.

Feedback: The seminar is a preparation for the master’s thesis. Thus, we would like to give you feedback on both your presentation and your written work. We believe that the learning effect is maximized, when everyone participates in this process. If this, for whatever reason, is inacceptable to you, please inform us before your presentation.

Available Topics:

1. Deep Reinforcement Learning (DRL): How neural networks are used in RL to address complex tasks with high-dimensional inputs.
2. Multi-Agent Reinforcement Learning (MARL): The study of interactions and learning processes among multiple agents in shared environments.
3. Hierarchical Reinforcement Learning (HRL): Approaches to simplify problem-solving by dividing tasks into smaller, manageable subtasks.
4. Meta-Reinforcement Learning (Meta-RL): Techniques enabling RL systems to adapt to new tasks using previous learning experiences.
5. Inverse Reinforcement Learning (IRL): Methods to deduce the underlying reward structure from observed expert behavior.
6. Offline Reinforcement Learning: Training RL models on fixed datasets without additional data from live interactions.
7. Safe Reinforcement Learning: Strategies to reduce risks and ensure safe decision-making during learning and deployment.
8. Proximal Policy Optimization (PPO): A practical and effective algorithm for improving RL policy training stability.
9. Curiosity-Driven Exploration: Techniques that encourage agents to explore new states by rewarding novelty.
10. Sim-to-Real Transfer in RL: Addressing challenges in adapting models trained in simulated environments to the real world.
11. Continuous Control in Reinforcement Learning: Approaches for handling tasks that require smooth and precise control, such as robotics.
12. RL for Natural Language Processing (NLP): Using RL to enhance applications like text generation and conversational agents.

Distribution of Topics: 09.01.2025 12:30-13:45 in SR06