We will work "hands on" with the following topics:
• Implementing reinforcement learning agents with PyTorch
• Designing states, actions, and reward functions for puzzle environments
• Training Deep Q-Learning agents
• Applying exploration strategies such as ε-greedy policies and decay schedules
• Using replay buffers and target networks
• Evaluating and comparing RL agents
• Performing systematic hyperparameter optimization
Required primary knowledge: Python and some basic understanding of machine learning methods
Instructor: Alexandra Moringen, alexandra.moringenuni-greifswaldde
Date: Monday, 21.09.2026 - Friday, 25.09.2026 [12:00 am – 17:00 pm]
Location: Room 1.26 in URZ
Maximal no. of participants: 10
Equipment needed: A laptop with a browser and Internet access for programming.
You need an account at University of Greifswald. The course will be in English.
To participate, please register for the lecture series.
Contact
Graduiertenakademie der Universität Greifswald
Domstraße 11, Eingang 4, Raum 3.24, 17489 Greifswald
Telefon +49 3834 420 1618
graduiertenakademieuni-greifswaldde