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.

2020S, VU, 4.0h, 6.0EC
TUWEL

Properties

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

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

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

Lecturers

Institute

Course dates

DayTimeDateLocationDescription
Wed14:30 - 16:0004.03.2020 Institutsbibliothek, DA 06 G14Reinforcement Learning
Thu10:00 - 11:0005.03.2020 - 12.03.2020Sem.R. DA grün 03 A - mündl. Prüfungsraum Mathematik Reinforcement Learning
Thu10:00 - 11:3005.03.2020 - 25.06.2020 Sem.R. DA grün 03CReinforcement Learning
Thu12:00 - 14:0005.03.2020 - 12.03.2020Sem.R. DB gelb 03 Reinforcement Learning
Wed14:00 - 16:0011.03.2020FH Hörsaal 6 - TPH Reinforcement Learning
Wed14:30 - 16:0011.03.2020 - 24.06.2020 Sem.R. DA grün 03CReinforcement Learning
AKNUM Reinforcement Learning - Single appointments
DayDateTimeLocationDescription
Wed04.03.202014:30 - 16:00 Institutsbibliothek, DA 06 G14Reinforcement Learning
Thu05.03.202010:00 - 11:00Sem.R. DA grün 03 A - mündl. Prüfungsraum Mathematik Reinforcement Learning
Thu05.03.202010:00 - 11:30 Sem.R. DA grün 03CReinforcement Learning
Thu05.03.202012:00 - 14:00Sem.R. DB gelb 03 Reinforcement Learning
Wed11.03.202014:00 - 16:00FH Hörsaal 6 - TPH Reinforcement Learning
Wed11.03.202014:30 - 16:00 Sem.R. DA grün 03CReinforcement Learning
Thu12.03.202010:00 - 11:00Sem.R. DA grün 03 A - mündl. Prüfungsraum Mathematik Reinforcement Learning
Thu12.03.202010:00 - 11:30 Sem.R. DA grün 03CReinforcement Learning
Thu12.03.202012:00 - 14:00Sem.R. DB gelb 03 Reinforcement Learning
Wed18.03.202014:30 - 16:00 Sem.R. DA grün 03CReinforcement Learning
Thu19.03.202010:00 - 11:30 Sem.R. DA grün 03CReinforcement Learning
Wed25.03.202014:30 - 16:00 Sem.R. DA grün 03CReinforcement Learning
Thu26.03.202010:00 - 11:30 Sem.R. DA grün 03CReinforcement Learning
Wed01.04.202014:30 - 16:00 Sem.R. DA grün 03CReinforcement Learning
Thu02.04.202010:00 - 11:30 Sem.R. DA grün 03CReinforcement Learning
Wed22.04.202014:30 - 16:00 Sem.R. DA grün 03CReinforcement Learning
Thu23.04.202010:00 - 11:30 Sem.R. DA grün 03CReinforcement Learning
Wed29.04.202014:30 - 16:00 Sem.R. DA grün 03CReinforcement Learning
Thu30.04.202010:00 - 11:30 Sem.R. DA grün 03CReinforcement Learning
Wed06.05.202014:30 - 16:00 Sem.R. DA grün 03CReinforcement Learning

Examination modalities

Continuously in tutorials; written tests.

Course registration

Begin End Deregistration end
02.03.2020 00:00 08.04.2020 00:00 08.04.2020 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