Deep Reinforcement Learning

Winter semester 2025-26:

First lecture: Thuesday 14.10.

First exercise: Friday 17.10.

General Information

Suggested prerequisites: Mathematics I to IV, Neurocomputing, basic knowledge in Python.

Exam: written exam (90 minutes), English & German, 5 ECTS.

Contact: oliver.maith@…

Language: English. The exam is in English & German.

Registration (for receiving emails): OPAL

Registration (for exercise computer pool): OPAL

Content

The course will dive into the field of deep reinforcement learning. It starts with the basics of reinforcement learning (Sutton and Barto, 2017) before explaining modern model-free (DQN, DDPG, PPO) and model-based (I2A, World models, AlphaGo) architectures making use of deep neural networks for function approximation. More "exotic" forms of RL are then presented (successor representations, hierarchical RL, inverse RL, etc).

The different algorithms presented during the lectures will be studied in more details during the exercises, through implementations in Python.

Materials

All materials are available at: https://www.tu-chemnitz.de/informatik/KI/edu/deeprl/notes

Literature

• "Reinforcement Learning : An Introduction", Sutton & Barto