Seminar Learning in Games

(IN2107, IN0014, IN2396)

Supervision: Prof. Dr. Martin Bichler, Stefan Heidekrüger, Nils Kohring.

 

Game Theory concerns itself with the strategic interactions of multiple decision-makers. In this seminar, we will explore the subfield of Learning in Games, where these decision-makers are agents that learn to adapt their strategies in order to maximize their own expected utility. As such, this topic is located at the intersection of Game Theory and Machine Learning, particularly Multi-Agent Learning. In recent years, there have been renewed interest as well as big breakthroughs in this field, fueled by the advent of more powerful computation and deep learning on the one hand, as well as the increasing deployment of autonomous systems (bots) in the economy. Particular topics explored in this seminar may range from theory (e.g. Equilibria and Game Dynamics, Complexity, Evaluation of Agent Strength), algorithms (e.g. Counterfactual Regret Minimization, AlphaZero), and applications (e.g. superhuman AI for Board Games; economical applications such as Automated Mechanism Design, or Equilibrium Computation in Auctions).

Credit: Stock picture, pexels.com

Previous knowledge expected

Basic knowledge of Game Theory (e.g. from IN2239 Algorithmic Game Theory), machine learning (e.g. IN2028 Business Analytics & Machine Learning, or IN2064 Machine Learning). Students will also need a firm grasp of mathematical foundations like calculus (MA0902 / MA0001), and probability theory (IN0018, MA0009 / MA1109).

Objective

  • IN2107 (Master-Seminar in the Master program Informatik).
  • IN0014 (Seminar in the Bachelor programs Informatik, Wirtschaftsinformatik).
  • For all other programs: Please check first whether this seminar fits in your curriculum.

Teaching and learning method

The emphasis in this seminar lies on the independent study of classic papers, as well as recent new results in the fields of Algorithmic Game Theory and Multi-Agent Learning. Each student will be assigned an individual topic and prepare a presentation as well as a short summary paper. We will have biweekly presentation meetings throughout the semester with two topics being presented in each meeting. Attendance of all meetings is mandatory, and interaction with the other students' work is expected.

Course Criteria and Registration

The seminar is primarily aimed at MSc students in Computer Science and adjacent degree programs such as Information Systems, Data Science, or Mathematics. In case there is remaining capacity available, applications from BSc students will also be considered.

All students must apply for the seminar via email (see below) AND via the Informatics Department's  matching system  in the "Seminars SS2022" matching instance. Registration for the matching will be open from 10.02.2022 until 15.02.2022 (Additional information here.)

Note: An earlier version of this website stated that only Informatics and Information Systems students need to use the matching system. This was incorrect, please also use the matching system if you are a student of a different department. We apologize for any confusion.

Additionally, please send a current transcript of records to Nils Kohring via email no later than February 15th, 2022. If you want to let us know anything else,  feel free to let us know in the email (e.g. your motivation to participate in this seminar, any experience relevant to the seminar outside of university courses, relevant classes in WS21/22 that aren't listed on your ToR.)

Recommended Reading

Recommended reading will be assigned individually.

Note

The slides from the kick-off meeting (Vorbesprechung) on February 4th can be found here.