back to search

Research Seminar in Deep Reinforcement Learning (FIM)

MGT001534Elective area6 ECTSEnglishwinter semesterStudiengang M.Sc. Finance and Information Management
AI-edited module sheet. Based on the TUMonline module description, edited for readability.Original in TUMonline

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

Dates

SeminarResearch Seminar in Deep Reinforcement Learning (MGT001534, englisch) (FIM)

From the current semester, not binding.

Module ratings

No ratings for this module yet.

Rate this module

Only fill in the categories you can judge – for each one, either stars and text together or nothing at all.

Lecture
Tutorial
Exam

Reviews are automatically checked before they are published.

Official page in TUMonline · Details are not binding.