Computational Game Theory

6 ECTS credits
150 h study time

Offer 2 with catalog number 4013088ENR for all students in the 1st semester at a (E) Master - advanced level.

Semester

1st semester

Enrollment based on exam contract

Impossible

Grading method

Grading (scale from 0 to 20)

Can retake in second session

Yes

Taught in

English

Partnership Agreement

Under agreement for exchange of courses

Faculty

Faculty of Sciences and Bioengineering Sciences

Department

Computer Science

Educational team

Ann Nowe (course titular)
Tom Lenaerts

Activities and contact hours

26 contact hours Lecture
26 contact hours Seminar, Exercises or Practicals
150 contact hours Independent or External Form of Study

Course Content

The aim of the course is to introduce the students to the field of Multi-agent learning and learning in populations of agents.

He or she will learn the basic principles of both domains, the mathematical and computational methods and the typical problems they are trying to solve.

The students will also obtain a basic understanding of (evolutionary) game theory which will allow them to understand the standard literature in that field and the relevance of this domain to learning in general.

The students will obtain the skills to address independently problems within these fields.

In addition, they will be capable of presenting their work to an audience of specialists and non-specialists.

The course addresses two general areas of research : individual-based learning and social learning in populations.

The first part provides an introduction to the principles of learning by imitation, modeled through evolutionary dynamics. It will explain what evolution is and how games can be used to model interactions between individuals in a population. For this purpose basic concepts of Game Theory are introduced. It will show how these models can be used to study the evolution of cooperation in social dilemmas, the evolution of conventions like language or even the dynamics of cancer.

The second part focusses on learning through experience, of which reinforcement learning is the standard example. We start from a reacp of simple single agent reinforcement learning (stateless RL) which we extent to deal with the interplay of multiple learning agents in the same environment.

The course concludes with a project where students in small teams have to reproduce the reults of a scientific paper, discus and extend the results.

Course material

Digital course material (Required) : http://como.vub.ac.be/doku.php?id=teaching:mals, http://www.ulb.ac.be/di/map/tlenaert/Home_Tom_Lenaerts/INFO-F-409.html
Digital course material (Required) : Reinforcement Learning, An Introduction by Sutton and Barto Copies of papers and chapters of books will be available via the website.

Additional info

Course schedule, course material and information on assignments and project: http://www.ulb.ac.be/di/map/tlenaert/Home_Tom_Lenaerts/INFO-F-409.html

Learning Outcomes

Algemene competenties

Knowledge and insight
The student knows different Reinforcement Learning (RL) techniques. The student can judge different exploration strategies, is knowledgeable about the exploration/exploration trade off. The student has insight in the dynamics of multiagent systems and reinforcement learning and the relevancy of the basic concepts of Game Theory in this context.

Application of knowledge and insight
The student can solve and avaluate a concrete problem using a multiagent reinforcement learning technique or evolutionary game theory and its dynamics.

Judgment ability
The student can give arguments why a given problem is suited or not to be apporached through RL and evolutionary dynamics.

Communication
The students must complete 3 written assignments and 1 project in a team of 3 ot 4 students that needs to be presented.

Skills
The student will be prepared to read autonomously the literature In this research domain. The students will obtain the skills to address independently problems within these fields. In addition, they will be capable of presenting their work to an audience of specialists and non-specialists.

Grading

The final grade is composed based on the following categories:
PRAC Practical Assignment determines 50% of the final mark.
SELF Paper determines 50% of the final mark.

Within the PRAC Practical Assignment category, the following assignments need to be completed:

Lab assignment with a relative weight of 1 which comprises 50% of the final mark.

Within the SELF Paper category, the following assignments need to be completed:

Assignment with a relative weight of 1 which comprises 50% of the final mark.

Additional info regarding evaluation

The final score will be based on the active participation of the student during the lectures and in particular the efforts and results delivered for the assignments (including assignments on game theory and the discussion of a paper). The assignments need to be completed during the semester of teaching.

Allowed unsatisfactory mark

The supplementary Teaching and Examination Regulations of your faculty stipulate whether an allowed unsatisfactory mark for this programme unit is permitted.

Academic context