direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Advanced Topics in Reinforcement Learning

Lupe

General information

  • The lecture and tutorials are held in English.
  • The course is open to TU students as well as exchange students and visiting students.
  • No formal registration is required to attend the course or even possible. The registration is only relevant for the exam.
  • The exam registration procedure is announced in the first lecture. Prior registration/reservation is not possible.
  • Each student has to present at least one paper on a state of the art algorithm in RL (A list of papers will be uploaded soon).
  • Students can form groups and apply at least one of the algorithms to the toy-model of their choice.

 

Topics

  • Partial observability on Reinforcement learning.
  • RL methods for training multiple-agents.
  • RL and meta learning

Prerequisites

  • Solid mathematical knowledge: analysis, linear algebra, probability calculus and statistics.
  • Basic programming skills, preferably Python

 

List of Papers

Conceptual Approaches:

 Technical Approaches:

 Misc:

 

ISIS page!

For further information please consult Vaios Laschos (lecturer, in charge).

 

 

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions

Seminar

Advanced Topics in Reinforcement Learning
Seminar

Lecturer: Vaios Laschos

Period:
16.10.2019 to 19.02.2019

We 14:00 - 16:00 o'clock

Location: MAR 5.060