Inhalt

[ 536MLPEREIK19 ] KV (*)Reinforcement Learning

Versionsauswahl
(*) Leider ist diese Information in Deutsch nicht verfügbar.
Workload Ausbildungslevel Studienfachbereich VerantwortlicheR Semesterstunden Anbietende Uni
4,5 ECTS B3 - Bachelor 3. Jahr Informatik Gerhard Widmer 3 SSt Johannes Kepler Universität Linz
Detailinformationen
Quellcurriculum Bachelorstudium Artificial Intelligence 2019W
Ziele (*)Introduction to basic principles and techniques of Reinforcement Learning.
Lehrinhalte (*)Defining the Reinforcement Learning problem relative to supervised and unsupervised machine learning. Defining k-armed Bandits, contextual bandits, and finally the Markov Decision Process (MDP). Formalizing the RL problem. Basic table-based algorithms to explore the space of possible solution methods. Introduction of more useful, advanced, but approximate solution methods. Examples of state-of-the-art methods, including deep Reinforcement Learning.
Beurteilungskriterien (*)Multiple programming exercises in Python throughout the semester. Written exam at the end of the semester.
Lehrmethoden (*)Slide presentation, discussion of common problems during the exercise.
Abhaltungssprache Englisch
Literatur (*)Slides used in the lecture will be made available via Moodle.
Lehrinhalte wechselnd? Nein
Sonstige Informationen (*)R. Sutton and A. Barto (2018). Reinforcement Learning: An Introduction. (Second Edition). Cambridge, MA: The MIT Press.
Präsenzlehrveranstaltung
Teilungsziffer -
Zuteilungsverfahren Direktzuteilung