Introduction to Reinforcement Learning with Engineering ApplicationsModule description #40919 / Version 2
- 6 CP
- Portfolio examination
- Graded
- Summer semester
- English
This module description is not valid in the current semester (Winter semester 2026/27).
| Module / Version | #40919 / #2 |
|---|---|
| Validity | Summer semester 2020 – Summer semester 2020 |
| Available language(s) | English |
| Credit points | 6 |
| Person responsible for the module | Maghsudi, Setareh |
| Grading | Graded |
| Exam format | Portfolio examination |
| Language(s) of instruction | English |
Affiliation
| Faculty | Fakultät IV |
|---|---|
| Institute | Institut für Telekommunikationssysteme |
| Academic chair | 34332400 FG Control of Convergent Access Networks |
Contact
| Office | EN 17 |
|---|---|
| Contact person | Maghsudi, Setareh |
| E-mail address | teaching@ccan.tu-berlin.de |
| Website | https://www.ccan.tu-berlin.de/menue/teaching/ |
Learning outcomes
After successful completion of the module, students are able to apply the concept of reinforcement learning to solve practical tasks in various fields of technology. They can analyze application fields to select, implement, evaluate and optimize appropriate decision making methods based on reinforcement learning.
Content
A. Theory:
1. Markov Decision Processes
• Bellman Equation, Value iteration, policy iteration
• Dynamic Programming
• Algorithmic Solutions
• Partially-Observable Setting
• Q-Learning
• The Multi-Agent Setting
2. Multi-Armed Bandits
• Basics
• Stochastic Bandits
• Adversarial Bandits
• Markovian Bandits
•The Multi-Agent Setting
B. Application:
1. Data Analytics
2. Image/Speech Processing
3. Radio Resource Allocation
4. Load Balancing
5. Security
6. Internet of Things
1. Markov Decision Processes
• Bellman Equation, Value iteration, policy iteration
• Dynamic Programming
• Algorithmic Solutions
• Partially-Observable Setting
• Q-Learning
• The Multi-Agent Setting
2. Multi-Armed Bandits
• Basics
• Stochastic Bandits
• Adversarial Bandits
• Markovian Bandits
•The Multi-Agent Setting
B. Application:
1. Data Analytics
2. Image/Speech Processing
3. Radio Resource Allocation
4. Load Balancing
5. Security
6. Internet of Things
Module components
Compulsory area
The following courses are mandatory for this module:
Workload and credit points
Introduction to Reinforcement Learning (Lecture)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre- and Post-processing | 1 | 20 h | 20 h |
| Take-home Problem Set | 1 | 20 h | 20 h |
| Exam Preparation | 1 | 20 h | 20 h |
| 90 h | |||
Applications of Reinforcement Learning in Engineering (Integrated course)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.
Description of teaching and learning methods
The module is developed to provide an introduction to reinforcement learning, with an emphasis on applications in engineering. It consists of two courses in sequence. The first course, which takes place during the first half of the semester, is held in the conventional frontal teaching form. During this part, basic models and concepts of reinforcement learning are introduced. The second course, which takes place in the second half of the semester, is in the form of seminar or mini-project. Each student defines some mini-project, in which some engineering problem is addressed by using reinforcement learning. The projects are in the form of research and/or computer implementation. The progress and results are presented and discussed in the class during the semester.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
Prerequisites to attend the module are calculus, probability theory and random processes at the level of MSc students in engineering.
Mandatory requirements for the module examination registration:
This module has no examination requirements.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Portfolio examination |
| Type of portfolio examination | 100 points in total |
| Language | English |
Test elements
| Name | Points/Weight | Category | Duration/Extent |
|---|---|---|---|
| (Deliverable Assessment) Take-home Problem Set | 20 | written | One problem set |
| (Examination) Oral test/discussion | 30 | oral | 20 Minuten |
| (Deliverable Assessment) Seminar Presentation | 20 | oral | 30 Minuten |
| (Deliverable Assessment) Mini-Project | 30 | flexibel |
Exam description
The grading consists of 4 parts:
(i) Take-home problem set: The students receive a set of problems (10-20 questions) with a due date near the end of the lecture.
(ii) Oral test: The test is organized for each student individually and the questions concern the theoretical and fundamental topics of the lecture.
(iii) Report: Each student (or each team) provides a written description of the selected mini-project, the novelty of the mini-project, the findings/results, and the ideas for future work. If the project includes computer simulation, the supplementary materials (such as the data set and the code, if applicable) shall accompany the report.
(iv) Presentation: Each student (or each team) presents his/her mini-project together with the findings and results as well as the ideas for future work.
(i) Take-home problem set: The students receive a set of problems (10-20 questions) with a due date near the end of the lecture.
(ii) Oral test: The test is organized for each student individually and the questions concern the theoretical and fundamental topics of the lecture.
(iii) Report: Each student (or each team) provides a written description of the selected mini-project, the novelty of the mini-project, the findings/results, and the ideas for future work. If the project includes computer simulation, the supplementary materials (such as the data set and the code, if applicable) shall accompany the report.
(iv) Presentation: Each student (or each team) presents his/her mini-project together with the findings and results as well as the ideas for future work.
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 20.
Registration procedures
How to sign in: Please write an e-mail to: teaching@ccan.tu-berlin.de until April 10.
Please provide the following information in your e-mail:
- your name,
- your study program,
- your current semester count.
Please provide the following information in your e-mail:
- your name,
- your study program,
- your current semester count.
Recommended reading, lecture notes
Lecture notes
available
Electronic lecture notes
unavailable
Recommended literature
- R. S. Sutton and A. Barto, Reinforcement Learning: An Introduction, MIT Press, 1998
- C. Szepevri, Algorithms for Reinforcement Learning, Morgan and Claypool, 2010
- N. Cesa-Bianchi and S. Bubeck, Regret Analysis of Stochastic and Non-Stochastic Multi-Armed Bandit Problems, Foundations and Trends in Machine Learning-Now Publishing, 2012
Assigned programs
This module is not used in any program.
Miscellaneous
Not specified