Multi-Agent Systems

Dit vak wordt in het Engels aangeboden. Omschrijvingen kunnen daardoor mogelijk alleen in het Engels worden weergegeven.

Doel vak

After successfully completing this course, the student

- has a solid understanding of concepts from elementary and intermediate
game theory,
such as minimax regret, Nash and correlated equilibria, and the Shapley
- understands various principled approaches to balance exploration and
- has a solid understanding of the tabular solution methods for (single
agent) reinforcement learning;
- is able to explore and digest current research on deep reinforcement
learning and multi-agent reinforcement learning.

Dublin descriptors:
1 Knowledge and Understanding,
2. Applying Knowledge and Understanding:

Inhoud vak

In Multi-agent systems (MAS) one studies collections of interacting,
intelligent agents.
These agents typically can sense both other agents and their
environment, reason about what they perceive, and plan and carry out
actions to achieve specific goals. In this course we introduce a number
of fundamental scientific and engineering concepts that underpin the
theoretical study of such multi-agent systems. In particular, we will
cover the following topics:

- Beliefs, desires, and intentions (BDI)
- Introduction to non-cooperative game theory
- Introduction to coalitional game theory for teams of selfish agents
- Principles of Mechanism Design
- Exploration versus Exploitation
- Markov Decision Processes
- Reinforcement learning for a single agent
- Introduction to multi-agent reinforcement learning


Two lectures (1h45) and one recitation class (1h45) per week.


There will be weekly homework assignments that will be graded. In
addition, there will be a final exam that will test the student's
ability to apply the course material to new and concrete problems.
The final grade will be a weighted average of the grades for the
homeworks (30%) and the final exam (70%).


Recommended reading:

Yoav Shoham, Kevin Leyton-Brown: Multiagent Systems
Publisher: Cambridge University Press (15 Dec. 2008)
ISBN-10: 0521899435
ISBN-13: 978-0521899437

R.S. Sutton, A.G. Barto, F. Bach: Reinforcement Learning: An
Publisher: MIT Press; second edition edition (23 Nov. 2018)
Language: English
ISBN-10: 0262039249
ISBN-13: 978-0262039246

Aanbevolen voorkennis

Basic probability theory and linear algebra. Fluency in a programming

Algemene informatie

Vakcode XM_0052
Studiepunten 6 EC
Periode P2
Vakniveau 400
Onderwijstaal Engels
Faculteit Faculteit der Bètawetenschappen
Vakcoördinator dr. E.J.E. Pauwels
Examinator dr. E.J.E. Pauwels
Docenten dr. M.C.A. Klein
dr. E.J.E. Pauwels

Praktische informatie

Voor dit vak moet je zelf intekenen.

Voor dit vak kun je last-minute intekenen.

Werkvormen Werkcollege, Hoorcollege

Dit vak is ook toegankelijk als: