News
Correction Time & Date Tutoral on Probability TheoryWritten on 27.10.25 by Yannic Muskalla Hi everyone, since there was some contradicting information about the time and date of the tutorial on probability theory: The tutorial will take place on Wednesday, 29.10., 14:15 - 15:45, E 1.3 lecture room 1. Cheers, Yannic |
Reminder: RL lecture at 14:15Written on 27.10.25 by Verena Wolf Dear all,
For the lecture today at 14:15, we use the same Zoom link as last week:
Kind regards, Verena Wolf. |
Additional Training Sheet and Tutorial on Probability TheoryWritten on 21.10.25 (last change on 21.10.25) by Yannic Muskalla Hello everyone! To better prepare you for some theoretical parts of the lecture, we have just published an additional training sheet that covers important basics of probability theory. You can find it under Information --> Materials. Although the training sheet is, as all exercise sheets in this… Read more Hello everyone! To better prepare you for some theoretical parts of the lecture, we have just published an additional training sheet that covers important basics of probability theory. You can find it under Information --> Materials. Although the training sheet is, as all exercise sheets in this course, completely optional, we highly recommend you to make sure you understand the concepts as they will be important as the lecture progresses. We also offer a tutorial, where we will discuss the training sheet. It will take place in E 1.3, lecture room 1, on Wednesday, October 29, 14:15 - 15:45. Have a nice evening! |
Welcome to the Reinforcement Learning Course (Zoom link for Monday)Written on 18.10.25 by Verena Wolf Dear participants, You are registered for the UdS course “Reinforcement Learning.” If you prefer to join online, please use the following Zoom link: Dear participants, You are registered for the UdS course “Reinforcement Learning.” If you prefer to join online, please use the following Zoom link: https://cs-uni-saarland-de.zoom.us/j/85446731707?pwd=MmRS3K37DepIrMaVE6d4tjw5c0KZiS.1 I look forward to meeting you all on Monday. Kind regards, |
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 (no lecture on Oct 13th)
Assignment Sheets: bi-weekly, containing theoretical & programming exercises
Submission is voluntary. If you hand in the exercise sheets, they will be corrected.
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