News

Currently, no news are available

Reinforcement Learning

Reinforcement learning is an area of machine learning where the goal is to develop (near-)optimal policies for solving sequential decision-making problems. The policy is typically represented by an agent who learns to achieve a goal by interacting with the environment. RL is often seen as the third area of machine learning (in addition to supervised and unsupervised areas) in which training samples are generated as a result of the agent's actions and interaction with the environment. In recent years, there have been remarkable successes in reinforcement learning research in both theoretical and applied fields. These successes are mostly the result of a new development in the field: representing policies by artificial neural networks allows us to solve much more complex decision problems.

 

Course Content

This course provides a broad introduction to reinforcement learning and its applications. You will learn about Markov Decision Processes as the underlying formal framework for decision-making problems, as well as popular reinforcement learning algorithms such as Monte-Carlo methods, temporal difference methods, and different "deep" reinforcement learning approaches. We will consider the open-source Python library Gymnasium to train RL agents in different pre-built environments.

We recommend as prerequisites for this lecture the succesful attendance in Programming 1, Programming 2 and basic knowledge of probability theory as taught for example in Mathematics for Computer Scientists 3.

 

Course Modalities

The course is a 6 ECTS Advanced Lecture, consisting out of weekly lectures, bi-weekly assignment sheets and a final exam.

Additionally, we will offer Tutorials and Office Hours. The exact dates and locations will be announced in the coming weeks.
 

Lecture: every Monday at 14:15 in Bld E13, HS II, Start: Oct 20th

Assignment Sheets: bi-weekly, containing theoretical & programming exercises

The admission to the final exam does not depend on the points you achieve on the exercise sheets.
In order to be admitted to the final exam, you must pass a mid-term exam.

The mid-term exam will take place on Monday, the 8th of December.

Literature

Reinforcement Learning: An Introduction, Richard S. Sutton and Andrew G. Barto

Algorithms for Reinforcement Learning, Csaba Szepesvári

Privacy Policy | Legal Notice
If you encounter technical problems, please contact the administrators.