Jedes Modul umfasst 3 ECTS. Sie wählen insgesamt 10 Module/30 ECTS in den folgenden Modulkategorien:
- 12-15 ECTS in Technisch-wissenschaftlichen Modulen (TSM)
TSM-Module vermitteln Ihnen profilspezifische Fachkompetenz und ergänzen die dezentralen Vertiefungsmodule. - 9-12 ECTS in Erweiterten theoretischen Grundlagen (FTP)
FTP-Module behandeln theoretische Grundlagen wie die höhere Mathematik, Physik, Informationstheorie, Chemie usw. Sie erweitern Ihre abstrakte, wissenschaftliche Tiefe und tragen dazu bei, den für die Innovation wichtigen Bogen zwischen Abstraktion und Anwendung spannen zu können. - 6-9 ECTS in Kontextmodulen (CM)
CM-Module vermitteln Ihnen Zusatzkompetenzen aus Bereichen wie Technologiemanagement, Betriebswirtschaft, Kommunikation, Projektmanagement, Patentrecht, Vertragsrecht usw.
In der Modulbeschreibung (siehe: Herunterladen der vollständigen Modulbeschreibung) finden Sie die kompletten Sprachangaben je Modul, unterteilt in die folgenden Kategorien:
- Unterricht
- Dokumentation
- Prüfung
Natural, social, and engineered complex systems can be modelled as being composed of agents interacting with one another and their environment. This course introduces students to the theory, tools and techniques for understanding and solving problems related to such systems.
The course is composed of two parts. In the first one, both cooperative and selfish agents and interactions between them will be discussed. The methodological support will be provided by game theory.
In the second part, the focus will be on the study and analysis of models of systems in the aim of understanding the conditions under which certain properties can emerge and agent might learn certain strategies or behaviours by interacting with the environment and themselves.
Throughout the course, several application areas such as cooperation and competition, social influence and reinforcement learning will be discussed.
Eintrittskompetenzen
Basic knowledge of probability, algebra, calculus and differential equations. Basics of procedural programming and ability to implement small programs in an arbitrary language, e.g. Python, Matlab, R, Java, C#, C++, C, etc.
Lernziele
A successful participant of this course is able to
- understand the rationale of multi-agent systems and their modelling.
- model scenarios with multiple interacting agents in the language of game theory
- evaluate the feasibility of achieving goals with agents using game theory
- understand the basic approaches to multi-agent learning, their peculiarities and their differences
- learn to choose the appropriate class of models with agents to characterise different complex systems
- implement in an efficient way a model of a system, then understand and analyse the corresponding outputs
Modulinhalt
- Review of single-agent decision making and learning
- Multi-agent interaction:
- games in normal form, dominant strategies,
- Nash equilibria, Pareto optimality,
- partial observability,
- cooperative and coalition games, Shapley value,
- repeated games,
- Multi-agent learning:
- model based approaches: fictitious and rational learning
- model-free approaches: no regret and reinforcement learning
Lehr- und Lernmethoden
- Lectures
- Exercises and homework
- Practical work with appropriate tools
- Literature studies
Bibliografie
- A Concise Introduction to Multi-Agent Systems and Distributed Artificial Intelligence. Nikos Vlassis. Morgan & Claypool Publishers, 2007.
- Introduction to Multi-Agent Systems - 2nd Edition. Michael Wooldridge. John Wiley & Sons, 2009.
- Multi-Agent Systems. Yoav Shoham and Kevin Leyton-Brown. Cambridge University Press, 2009.
- Artificial Intelligence, A Modern Approach (4th Edition). Stuart Russell and Peter Norvig. Pearson. 2021
Vollständige Modulbeschreibung herunterladen
Zurück