Курс “Reinforcement Learning”, літо 2018

In this course, the main ideas to get you started in reinforcement learning will be presented. By the end of the course, you should be able to start applying it in practice, and/or follow the latest trends in this born-again field.

Overall course length – 20 classes.

Number of ECTS – 5.

The course starts on 24th of May. The classes go every other week. The last section of the course is on July 12-14.

Course syllabus

Section 1 (May 24)

  • Lecture 1. Introduction to Reinforcement Learning. Problem Formulation
  • Lecture 2. Markov Decision Process and Dynamic Programming
  • Practice 1. Introduction to Open AI Gym. Possible project topics selection

Section 2 (June 7)

  • Lecture 3. Bandit Algorithms
  • Practice 2. Implementation of bandit algorithm
  • Lecture 4. Monte Carlo Methods

Section 3 (June 21-23)

  • Lecture 5. Temporal Difference
  • Lecture 6. TD with Function Approximation
  • Practice 3. TD: Implementation
  • Practice 4. Mid-term project presentations
  • Lecture 7. Policy Gradient and Actor-Critic Methods
  • Practice 5. OpenAI Gym

Section 4 (July 12-14)

  • Lecture 8. Two-player games
  • Lecture 9. Evolutionary Game Theory
  • Practice 6. Game dynamics: fictitious play, self-play, evolutionary game theory
  • Lecture 10. Multi-agent Reinforcement Learning
  • Lecture 11. Games with incomplete information
  • Practice 7. Counterfactual Regret minimization (Kuhn poker)
  • Lecture 12. Combining RL and search
  • Practice 8. Final project presentation

Course instruction language is English.


  • Python programming
  • Statistics
  • Machine Learning (basics)
  • Neural Networks (good to know)

Course enrollment

The participants are enrolled in the course based on the application process. Please fill the following application form: goo.gl/forms/UxSf6PMiAcJYF4u63.

The personal motivation statement and previous background in Statistics, Machine Learning, and Python programming are counted for the participant selection process. The application deadline is 16th of May. The application results will be announced no later than 18th of May.

Please pay attention that the organizers could close the application earlier in case there will be enough requests to fill all free spaces in a class. Also, the organizers could ask for the additional interview with the applicants to clarify the aspects of their application and/or check prerequisites knowledge.

Course fee

The participation fee is 13 900 UAH. The payment should be made in two transactions:

  • 7 900 UAH – until May 23
  • 6 000 UAH – until July 1

The approved candidates must pay the course tuition fee during the period that is defined by the organizers. In case if there will be no payment from the participant side, the organizers may cancel the participant’s registration and free the space for the next candidate. If you have any financial questions please contact the organizers as soon as possible (the contact information is provided below).


The participants may be granted the official certificate of completion in case they gain at least 60% of the maximum grade. The certificate can be used to transfer credits to the participant’s original university if there is such need and the university’s policy allows such transfers.

About lecturers

Tetiana Bogodorova, Ph.D. is a Research Associate at the Faculty of Applied Sciences, Ukrainian Catholic University

Tetiana Bogodorova received the Ph.D. degree in Electrical Systems, School of Electrical Engineering, KTH – Royal Institute of Technology, Stockholm in 2017. She received the B.S. degree in Computerized Systems, Automatics and Control and the M.Sc. degree in Automatic and Control Systems specialized in control theory from the National Technical University of Ukraine – Kyiv Polytechnic Institute. Her experience includes the development of the operations support system for telecommunication industry as a System Engineer with the System Analytics Group, Research, and Development, NetCracker Technology Corporation. Her current research interests lie at the intersection of machine learning and systems analysis, modeling, and validation.

Pablo Maldonado, Ph.D. is an adjunct professor at the Faculty of Information Technology, Czech Technical University in Prague

Besides academia, he provides consulting and training services in applied mathematics and machine learning to different organizations, leveraging math and technology to solve business problems. He has collaborated with global and small companies alike in several industry verticals: telecommunications, financial services, advertising, agriculture and the food industry. He is coauthor of ‘R Deep Learning Projects’, published by Packt in 2018.


E-mail: [email protected]
Facebook: www.facebook.com/ucucsds/