Research Seminar in Deep Reinforcement Learning (FIM)

What it is about

In small groups you work on a current research problem in the field of Deep Reinforcement Learning. Either you reproduce and analyze a newer research paper (possibly with methodological extension) or you formulate and examine an application task as a sequential decision problem. In the end you can conduct an independent, scientific, methodological, and reproducible research project and critically interpret the results.

What you will be able to do

• Formulate and contextualize a scientific question
• Systematically search, evaluate and synthesize scholarly literature
• Choose suitable models, algorithms and tools and implement them technically
• Design, carry out and critically evaluate reproducible computer experiments
• Draw scientifically grounded conclusions and delimit research questions
• Present and defend results in writing (seminar paper) and orally

What the module consists of

• SeminarprojektCore of the module: literature review, modeling, implementation and evaluation in small groups
• PräsentationPresentation and discussion of the project results in the seminar

Teaching method

• Betreutes Forschungsprojektstructured, autonomous research process with milestones and feedback
• Inverted Classroom / PräsentationenDiscussion, conveyance of content and scientific standards