Modulbeschreibung

Deep Reinforcement Learning

Kürzel:
M_DRL
Durchführungszeitraum:
FS/22
ECTS-Punkte:
2
Arbeitsaufwand:
60
Lernziele:

n this module, we introduce the foundations of deep reinforcement learning and will apply different algorithms to solve concrete problems in robotics and/or games. 

After successful completion of this module the students:

  • know how to apply deep reinforcement learning (RL) to solve problems in robotics and automation.
  • know how to implement RL in Python using state-of-the-art libraries (for example TensorFlow, Keras)
  • know how to formally describe a task as an RL problem
  • understand what a computational-graph is and how it is used by neural networks
  • understand the link between RL and Deep Learning
  • know the limitations of RL
  • understand the role of simulators and know how to use a robotics simulator (for example openAI-Gym)
  • know how to qualitatively and quantitatively describe the progress of the training process.
Verantwortliche Person:
Prof. Dr. Lehmann Marco
Telefon/EMail:
+41 58 257 3189
/ marco.lehmann@ost.ch
Standort (angeboten):
Buchs, Waldau St.Gallen
Fachbereiche:
Informatik
Empfohlene Module:
Vorausgesetzte Module:
Zusätzlich vorausgesetzte Kenntnisse:

Ebenfalls vorausgesetzt sind die Module Elektrotechnik und Lineare Algebra I und II sowie Informatik.

Modultyp:
Standard-Modul für Systemtechnik BB STD_05(Empfohlenes Semester: 5)
Standard-Modul für Systemtechnik VZ STD_05(Empfohlenes Semester: 5)
Bemerkungen:

This module is taught in English. Most of the AI-literature is in English. An intermediate level is recommended. The students are free to write reports in German or English. For the oral exam, students can choose between English and German

Kurse in diesem Modul