Informationssystem der Friedrich-Alexander-Universität Erlangen-Nürnberg © Config eG 
FAU Logo
  Sammlung/Stundenplan    Modulbelegung Home  |  Rechtliches  |  Kontakt  |  Hilfe    
Suche:      Semester:   

 Außerdem im UnivIS
Vorlesungs- und Modulverzeichnis nach Studiengängen





Advanced Signal Processing & Communications Engineering (Master of Science) >>

  Reinforcement Learning (RL)

Dr.-Ing. Christopher Mutschler

2 SWS, benoteter Schein, ECTS-Studium, ECTS-Credits: 2,5, Sprache Englisch
Zeit: Do 8:30 - 10:00, Zoom-Meeting

Studienfächer / Studienrichtungen
WF ASC-MA ab 1 (ECTS-Credits: 2,5)
WF INF-MA ab 1 (ECTS-Credits: 2,5)
WF CE-MA-TA-MT ab 1 (ECTS-Credits: 2,5)
WF MT-MA ab 1 (ECTS-Credits: 2,5)
WF ME-MA ab 1 (ECTS-Credits: 2,5)
WF CME-MA ab 1 (ECTS-Credits: 2,5)
WF ICT-MA ab 1 (ECTS-Credits: 2,5)

Reinforcement Learning (RL) is an area of Machine Learning that has recently made large advances and has been publicly visible by reaching and surpassing human skill levels in games like Go and Starcraft. These successes show that RL has the potential to transform many areas of research and industry by automatizing the development of processes that once needed to be engineered explicitly.

In contrast to other machine learning paradigms, which require the presence of (labeled or unlabeled) data, RL considers an agent that takes actions in an environment and learns from resulting feedback. The agent tries to maximize a reward signal that it receives for desirable outcomes, while at the same time trying to explore the world in which it operates to find yet unknown, potentially more rewarding action sequences–a dilemma known as the exploration-exploitation tradeoff. Recent advances in machine learning based on deep learning have made RL methods particularly powerful since they allow for agents with particularly well performing models of the world.

The lecture will start with introductory lectures to RL where we cover the foundations of RL (i.e., Markov decision processes and dynamic programming techniques) before we go to model-free prediction and control algorithms such as TD-learning, SARSA and Q-learning. We will also get the general idea behind value function approximation techniques such as Deep Q-Networks (DQN) and study advanced policy-gradient and actor-critic methods including TRPO and PPO.

We will end with focus sessions on advanced topics such as model-based RL, offline RL, explainable RL, and exploration-exploitation.

Empfohlene Literatur
While there is particular literature given in the slides of the videos the following list serves as a general basis to get into the topic but also to go deeper at particular points.
  • Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction. A Bradford Book, Cambridge, MA, USA.

  • Bellman, R.E. 1957. Dynamic Programming. Princeton University Press, Princeton, NJ. Republished 2003: Dover, ISBN 0-486-42809-5.

  • Csaba Szepesvari and Ronald Brachman and Thomas Dietterich. 2010. Algorithms for Reinforcement Learning. Morgan and Claypool Publishers.

  • Warren B. Powell. 2011. Approximate Dynamic Programming. Wiley.

  • Maxim Lapan. 2020. Deep Reinforcement Learning Hands-On: Apply modern RL methods to practical problems of chatbots, robotics, discrete optimization, web automation, and more, 2nd Edition. Packt Publishing.

  • Dimitri P. Bertsekas. 2017. Dynamic Programming and Optimal Control. Athena Scientific.

  • Miguel Morales. 2020. grokking Deep Reinforcement Learning. Manning.

  • Laura Graesser and Keng Wah Loon. 2019. Foundations of Deep Reinforcement Learning: Theory and Practice in Python. Addison-Wesley Data & Analytics.

Reinforcement Learning

Credits: 2,5

Zusätzliche Informationen
Erwartete Teilnehmerzahl: 30, Maximale Teilnehmerzahl: 50
www: https://www.studon.fau.de/studon/goto.php?target=crs_3727282

Zugeordnete Lehrveranstaltungen
UE ([online]):Reinforcement Learning Übung
Dozent/in: Dr.-Ing. Christopher Mutschler
Zeit: Mo 10:15 - 11:45, Zoom-Meeting

Verwendung in folgenden UnivIS-Modulen
Startsemester SS 2021:
Reinforcement Learning (RL)

Institution: Lehrstuhl für Maschinelles Lernen und Datenanalytik
UnivIS ist ein Produkt der Config eG, Buckenhof