Fast introduction to reinforcement learning

General description

Have you ever wondered about how a machine can learn in a similar way to the human brain?

Are you interested in the idea of adaptive and self-learning algorithms?

Are you curious to experience the Serbian BEST spirit?

If your answers are yes, we challenge you to take part in our course and spend 9 unforgettable days in a city where tradition meets the modern pulse.

In case you accept the challenge, prepare yourself for an adventure in the world of machine learning!

The aim of this course is to familiarize you with the fundamental terminology and methodology of Reinforcement Learning (What is it? Why is it important? What problems does it solve?). The entire course will revolve around a single Use Case, allowing you to understand the scope and limitations of different methodologies.

Get to know reinforcement learning, achieve academic fulfillment and vast knowledge of adaptive algorithms, but also experience Serbian hospitality, savor our delightful cuisine, and, of course, discover the art of rakija!

So, are you ready to face the challenge?

Academic information

Fields of activity:
Automotive Engineering , Computational Sciences , Computer Engineering , Computer Science/Automatic Control/Informatics , Control Engineering/Systems engineering , Electrical/Electromechanical Engineering , Electronic/Electrotechnical Engineering , Machine & Instrument engineering/Design , Mathematics , Mechanical Engineering , Mechatronics , Telecommunications/Electronics
Content and topics:
The course covers an introduction to Reinforcement Learning (RL) along with a brief review of terminology such as Markov Decision Processes, state values, and action-state values. It also provides a brief overview of classical solutions and their deficiencies, including dynamic programming and tabular methods like Monte Carlo and Temporal Difference Learning. Through real-world use cases, the course demonstrates how RL can be applied in practice. At the end of the course, the final examination will be in the form of a case study, where students will apply their acquired knowledge to a concrete problem.
Learning goals and objectives:
The goal of the course is to introduce students to the basic terminology and methodology of Reinforcement Learning (What it is? Why is it important? What problems does it solve?). Training students for theoretical understanding and practical solving of intelligent decision-making problems, and algorithmic implementation of adaptive and self-learning systems for automatic decision-making and decision-making support with special emphasis on systems based on reinforcementĀ learning. The entire course will be organized around a single Use Case through which the students will be able to reflect on the capabilities and limitations of different methodologies.
Examination type:
Case study
ECTS credits issued:

Information for applicants

Selection criteria:
Motivational letter, academic background and answers to 3 questions. Also, we keep diversity between countries and genders in mind.

Practical arrangements

All of the following are covered by the event fee:

Three meals per day, at least one hot.
Taxi, bus, train, feet, provided by organizers.