direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Course: Introduction to Reinforcement Learning

Description

This course takes place during the first half of the semester. It is held in the conventional frontal teaching form. During this part, basic models and concepts of reinforcement learning are introduced.

Content

1. Markov Decision Processes

  • Bellman Equation, Value iteration, policy iteration
  • Dynamic Programming
  • Algorithmic Solutions
  • Partially-Observable Setting
  • Q-Learning
  • The Multi-Agent Setting

2. Multi-Armed Bandits

  • Basics
  • Stochastic Bandits
  • Adversarial Bandits
  • Markovian Bandits
  • The Multi-Agent Setting

Recommended Literature

  • R. S. Sutton and A. Barto, Reinforcement Learning: An Introduction, MIT Press, 1998
  • C. Szepevri, Algorithms for Reinforcement Learning, Morgan and Claypool, 2010
  • N. Cesa-Bianchi and S. Bubeck, Regret Analysis of Stochastic and Non-Stochastic Multi-Armed Bandit Problems, Foundations and Trends in Machine Learning-Now Publishing, 2012

Registration Procedure

Please write an e-mail to: teaching@ccan.tu-berlin.de until April 10.
Please provide the following information in your e-mail:

  • your name,
  • your study program,
  • your current semester count.
Course Data
Course number
34332400 L 004
Course type
lecture
Teaching language
English
Day
Tuesday and Thursday
Time
10-12
Room
MAR 0.003
Duration
First half of summer semester
SWS
2
ECTS
3

Zusatzinformationen / Extras

Direktzugang

Schnellnavigation zur Seite über Nummerneingabe