Reinforcement Learning

AY2025/2026 Semester 1

This course will introduce the framework of reinforcement learning including some theoretical aspects and practical algorithms. The course will start with special cases such as multi-armed bandits before moving on to Markov decision processes and the corresponding planning and online reinforcement learning problems. If you want to build a solid understanding of the principles and fundamental results backing reinforcement learning, as well as develop some intuition about the methodology and practical challenges of this approach, then this course is meant for you. This course will equip you with a practical understanding of reinforcement learning, hence allowing you to apply this type of methods in machine-learning-related jobs. The theoretical insights gained in this course will also help you adapt to future developments in the field.