101.789 AKNUM Reinforcement Learning
This course is in all assigned curricula part of the STEOP.
This course is in at least 1 assigned curriculum part of the STEOP.

2022S, VU, 4.0h, 6.0EC
TUWEL

Properties

  • Semester hours: 4.0
  • Credits: 6.0
  • Type: VU Lecture and Exercise
  • Format: Hybrid

Learning outcomes

After successful completion of the course, students are able to not only understand, to explain and to apply the theory and the methods of reinforcement learning including the latest developments, but also to implement the most important algorithms.

Subject of course

This year (2022) with updated lecture notes!

Reinforcement learning is a field of artificial intelligence and is concerned with the development of strategies that an agent uses to maximize its reward in a random environment in a model-free manner.

Applications include robotics (OpenAI gym), computer vision, games (such as Go, chess, Atari 2600, or Dota 2) at the human level or above and many more.

Theory and algorithms of reinforcement learning:

  • Introduction
  • Bandit problems
  • Markov decision problems
  • Bellman equations
  • Hamilton-Jacobi-Bellman equation
  • Dynamic programming
  • Monte-Carlo learning
  • Temporal-difference learning
  • Tabular methods
  • Function approximation and deep learning
  • On-policy vs. off-policy
  • Eligibility traces
  • Policy gradients and actor-critic
  • Applications

In the tutorial, the theory will be repeated and extended and the algorithms will be implemented.

Teaching methods

Presentation, lecture notes, tutorial.

Mode of examination

Written

Additional information

Time for first meeting will be announced.

The class will be taught in presence, streamed, and recorded.

Lecturers

Institute

Course dates

DayTimeDateLocationDescription
Tue13:00 - 15:0001.03.2022 - 28.06.2022Sem.R. DB gelb 03 Reinforcement Learning
Wed13:00 - 15:0002.03.2022 - 29.06.2022Sem.R. DB gelb 03 Reinforcement Learning
AKNUM Reinforcement Learning - Single appointments
DayDateTimeLocationDescription
Tue01.03.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Wed02.03.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Tue08.03.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Wed09.03.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Tue15.03.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Wed16.03.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Tue22.03.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Wed23.03.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Tue29.03.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Wed30.03.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Tue05.04.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Wed06.04.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Tue26.04.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Wed27.04.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Tue03.05.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Wed04.05.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Tue10.05.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Wed11.05.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Tue17.05.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning
Wed18.05.202213:00 - 15:00Sem.R. DB gelb 03 Reinforcement Learning

Examination modalities

Continuously in tutorials; written tests.

Course registration

Begin End Deregistration end
07.03.2022 00:00 13.04.2022 00:00 13.04.2022 00:00

Curricula

Literature

 Lecture notes (in English) will be handed out.

Previous knowledge

The theoretical aspects will be explained in the lectures in a self-contained manner so that the course can be taken during or after the fourth semester.

Miscellaneous

Language

if required in English