General information

• The lecture and tutorials are held in English.
• The course is open to TU students as well as exchange students and visiting students.
• The exam registration procedure is announced in the first lecture. Prior registration/reservation is not possible.
• Each student will present one state-of-the-art paper of their choice and apply the method in a coding project.

Topics

• Distributional Reinforcement Learning

• Safe Exploration in Reinforcement Learning

• Verifiably Safe Exploration

Prerequisites

• Literature research and scientific presentation.
• Students should already be familiar with artificial intelligence (comparable to the topics covered in Machine Intelligence I + II).
• Programming skills (e.g., python, pytorch, github).

Exam

• Portfolio: Literature review (20%) + Coding (50%) + Presentation (30%)

Course page ISIS

For further information please consult Rong Guo (lecturer, in charge).