The course will outline the main methods of machine learning on examples of their use in game theory problems. At the same time, the basics of game theory and setting game problems will be explained from scratch. The application of machine learning in game theory will be demonstrated using Python programs. The course will be useful to anyone who is interested in what game theory is, how it is applied in practice, and how machine learning is used to solve game theory problems.

Course program

1. Basic concepts of game theory.
2. Review of machine learning methods for game theory problems.
3. Antagonistic games: genetic algorithms.
4. Antagonistic games: reinforcement learning.
5. Non-cooperative games. Nash equilibrium.
6. Neural networks: algorithms and tasks to be solved.
7. Neural networks: learning to play games.
8. Artificial intelligence and multi-agent games.
9. Dynamic games based on machine learning.
10. Mechanism design.

Lecturer
Shamin Roman Vyacheslavovich

Financial support
The course is supported by the Ministry of Science and Higher Education of the Russian Federation (the grant to the Steklov International Mathematical Center, Agreement no. 075-15-2022-265).

Institutions
Steklov Mathematical Institute of Russian Academy of Sciences, Moscow
Steklov International Mathematical Center