Kies de Nederlandse taal
Course module: INFOMAA
Multi-agent learning
Course infoSchedule
Course codeINFOMAA
ECTS Credits7.5
Category / LevelM (M (Master))
Course typeCourse
Language of instructionEnglish
Offered byFaculty of Science; Graduate School of Natural Sciences; Graduate School of Natural Sciences;
Contact persondr. G.A.W. Vreeswijk
Telephone+31 30 2534094
dr. G.A.W. Vreeswijk
Feedback and availability
Other courses by this lecturer
Course contact
dr. G.A.W. Vreeswijk
Other courses by this lecturer
Teaching period
4  (24/04/2023 to 07/07/2023)
Teaching period in which the course begins
Time slotC: C (MON-afternoon, TUE-aftern,THU-morn)
Study mode
Enrolment periodfrom 30/01/2023 up to and including 24/02/2023
Course application processadministratie onderwijsinstituut
Additional informationYou will be enrolled for this course by administration of the programme of this course.
Enrolling through OSIRISYes
Enrolment open to students taking subsidiary coursesYes
Post-registration openfrom 03/04/2023 up to and including 04/04/2023
Waiting listYes
Course placement processadministratie onderwijsinstituut
Course goals
  • To acquire an adequate impression of state-of-the-art research in multi-agent learning, including topics such as learning and teaching, fictitious play, rational learning, no-regret learning, targeted learning, multi-agent reinforcement learning, evolutionary learning.
  • To write a short and organized scientific paper summaries on specific topics in MAL
  • To be able to deal with technical questions in MAL and be able to formulate written answers
  • To write a small thesis on a specialized topic in MAL, and present it to an audience
  • To participate in a scientific discussion, according to social scientific standards.

Two exams, each 50% of the final mark.

A retake requires at least a 4 for the original test.

This course discusses algorithms for machine learning that typically occur in multi-agent systems, such as: reinforcement learning, no-regret learning, fictitious play, satisficing play, Bayesian learning, learning and teaching, and evolutionary learning (replicator dynamic).

Multi-agent learning (MAL) studies agents that learn and adapt to the behavior of other agents that themselves learn and adapt.
The presence of other learning agents complicates learning, which makes the environment non-stationary (a situation of learning a moving target) and non-Markovian (a situation where not only experiences from the immediate past but also earlier experiences are relevant).
It becomes less beneficent to only adapt to the behavior of other agents, on the pain of being exploited by more steadfast agents that do not follow but instead impose their strategy on others. Important topics of MAL include (evolutionary) game theory, fictitious play, gradient dynamics, no-regret learning, multi-agent reinforcement learning (MinMax-Q, Nash-Q), leader (teacher) vs. follower (learner) adaptation, and the emergence of social conventions.
Examples of domains that need robust MAL algorithms include manufacturing systems (managers of a factory coordinate to maximize their profit), distributed sensor networks (multiple sensors collaborate to perform a large-scale sensing task under strict power constraints), robo-soccer, disaster rescue (robots must safely find victims as fast as possible after an earthquake) and recreational games of imperfect information such as poker. Indeed, poker and simplified forms of poker are an important topics of research in multi-agent learning.

The course assumes knowledge of probability theory and game theory. Knowledge of game theory can be acquired through the period 3 multi-agent systems course INFOMAS.

Course form

Available on the course site.
Entry requirements
You must meet the following requirements
  • Assigned study entrance permit for the master
Prerequisite knowledge
Intelligent Agents of vergelijkbare basiskennis over agents
Required materials
Instructional formats

General remarks
Studenten krijgen een aantal huiswerkopdrachten te maken en krijgen wat oefening tijdens college.

Final result
Test weight100
Minimum grade-

Kies de Nederlandse taal