Skip to content
Technische Universität Berlin Deutsch
Course catalog and module transfer system

Advanced topics in Reinforcement Learning II: Multi-Agent Systems and Hierarchical LearningModule description #41002 / Version 1

← Module page Deutsche Fassung
This module description is not valid in the current semester (Winter semester 2026/27).
Module / Version#41002 / #1
ValiditySummer semester 2020 – Summer semester 2022
Available language(s)English
Credit points6
Person responsible for the moduleObermayer, Klaus
GradingGraded
Exam formatPortfolio examination
Language(s) of instructionEnglish

Affiliation

FacultyFakultät IV
InstituteInstitut für Softwaretechnik und Theoretische Informatik
Academic chair34351300 FG Neuronale Informationsverarbeitung

Contact

OfficeMAR 5-6
Contact personLaschos, Vaios
E-mail addresssekr@ni.tu-berlin.de
WebsiteNot specified

Learning outcomes

After successful completion, participants are able to apply at least one state-of-the-art technique in Reinforcement Learning (more specifically in topics related to hierarchical learning or/and multi agent system) and present their results to other students. They will be able to reproduce and present scientific research.

Content

Participants will search the recent literature on Reinforcement Learning (more specifically in topics related to hierarchical learning or/and multi agent system), present one state-of-the-art method of their choice and then apply it on a toy example.

Module components

Compulsory area

The following courses are mandatory for this module:

CoursesTypeNumberFrequencyLanguageHours per weekCourse catalog
Advanced topics in Reinforcement Learning II: Multi-Agent Systems and Hierarchical LearningSeminar3435 L 10633 Summer semester[en]4 ISIS

Workload and credit points

Advanced topics in Reinforcement Learning II: Multi-Agent Systems and Hierarchical Learning (Seminar)

Workload descriptionMultiplierHoursTotal
Attendance154 h60 h
Pre/post processing158 h120 h
180 h

The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.

Description of teaching and learning methods

Participants will research the current relevant literature and prepare a presentation of a new method in Reinforcement Learning to the other students. In the sequel they will apply their method to one of the toy examples and present the results. Language of the module is English.

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

Required skills include: literature research, presentation of researched articles, basic understanding of metacognition
Participants are expected to have background knowledge comparable to the topics covered in Machine Intelligence I + II .

Mandatory requirements for the module examination registration:

This module has no examination requirements.

Completion of the module

GradingGraded
Exam formatPortfolio examination
Type of portfolio examination100 points in total
LanguageEnglish

Test elements

NamePoints/WeightCategoryDuration/Extent
(Deliverable assessment) Code30practical30 hours
(Deliverable assessment) Presentation70practical40 minutes

Duration of the module

The following number of semesters is estimated for taking and completing the module: 1 semester(s).

This module can be started in the following semesters: Summer semester.

Maximum number of participants

The maximum capacity of participants is 30.

Registration procedures

Way of registration is not established yet. It is going to be either via yellow sheet from the examination board or electronic; exam takes place in English language
sekr@ni.tu-berlin.de

Recommended reading, lecture notes

Lecture notes

unavailable

Electronic lecture notes

unavailable

Recommended literature

No recommended literature given

Assigned programs

This module is not used in any program.

Miscellaneous

Not specified