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.

2019S, VU, 4.0h, 6.0EC

Properties

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

Aim of course

Understanding the theory and the most important algorithms of reinforcement learning as well as the ability to implement them in order to solve realistic problems.

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.

Lecturers

Institute

Course dates

DayTimeDateLocationDescription
Wed13:00 - 14:0006.03.2019 Freihaus, grüner Turm, 3.St. DA 03 C22Vorbesprech. Reinforc. Learning
Thu12:00 - 14:0007.03.2019 - 13.06.2019 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Wed12:00 - 13:3013.03.2019 - 26.06.2019 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
AKNUM Reinforcement Learning - Single appointments
DayDateTimeLocationDescription
Wed06.03.201913:00 - 14:00 Freihaus, grüner Turm, 3.St. DA 03 C22Vorbesprech. Reinforc. Learning
Thu07.03.201912:00 - 14:00 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Wed13.03.201912:00 - 13:30 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Thu14.03.201912:00 - 14:00 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Wed20.03.201912:00 - 13:30 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Thu21.03.201912:00 - 14:00 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Wed27.03.201912:00 - 13:30 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Thu28.03.201912:00 - 14:00 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Wed03.04.201912:00 - 13:30 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Thu04.04.201912:00 - 14:00 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Wed10.04.201912:00 - 13:30 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Thu11.04.201912:00 - 14:00 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Thu02.05.201912:00 - 14:00 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Wed08.05.201912:00 - 13:30 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Thu09.05.201912:00 - 14:00 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Wed15.05.201912:00 - 13:30 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Thu16.05.201912:00 - 14:00 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Wed22.05.201912:00 - 13:30 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Thu23.05.201912:00 - 14:00 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning
Wed29.05.201912:00 - 13:30 Freihaus, grüner Turm, 3.St. DA 03 C22Reininforcement Learning

Examination modalities

Two tests, tutorial, and participation.

Course registration

Begin End Deregistration end
04.03.2019 00:00 10.04.2019 00:00 10.04.2019 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.

Language

if required in English