VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.

227-0559-00L 2 Credits DR , MSC D-ITET , D-INFK

You're viewing possible stale or outdated data. Please check the latest semester for more up-to-date information.

Seminar in Deep Reinforcement Learning

Lecturers & Examiners: Prof. Dr. Roger Wattenhofer, Dr. Oliver Richter

Number of participants limited to 25.

VVZ CR 3.0

Last Updated: 2026-02-05 15:41:29

Abstract

In this seminar participating students present and discuss recent research papers in the area of deep reinforcement learning. The seminar starts with two introductory lessons introducing the basic concepts. Alongside the seminar a programming challenge is posed in which students can take part to improve their grade.

Objective

Since Google Deepmind presented the Deep Q-Network (DQN) algorithm in 2015 that could play Atari-2600 games at a superhuman level, the field of deep reinforcement learning gained a lot of traction. It sparked media attention with AlphaGo and AlphaZero and is one of the most prominent research areas. Yet many research papers in the area come from one of two sources: Google Deepmind or OpenAI. In this seminar we aim at giving the students an in depth view on the current advances in the area by discussing recent papers as well as discussing current issues and difficulties surrounding deep reinforcement learning.

Content

Two introductory courses introducing Q-learning and policy gradient methods. Afterwards participating students present recent papers. For details see: www.disco.ethz.ch/courses.html

Resources

Lecture Notes

Slides of presentations will be made available.

Literature

OpenAI course ( https://spinningup.openai.com/en/latest/ ) plus selected papers. The paper selection can be found on www.disco.ethz.ch/courses.html .

Learning Materials (Links)

Main link
Information

General Information

Language: English
Levels: DR , MSC
Frequency: Yearly recurring

Examination

Type: graded semester performance

Registration & Places

Signup End: 11.02.2020

Course Components

Type	Title	Time & Place	Hours
seminar	Seminar in Deep Reinforcement Learning	Tue 10:15-12:00 (ETZ G 91)	2 h weekly

Offered In

Computer Science Master
- Focus Courses
  - Focus Courses in Distributed Systems
    - Seminar in Distributed Systems
  - Focus Courses General Studies
    - Seminar in General Studies
Electrical Engineering and Information Technology Master
- Master Studies (Programme Regulations 2018)
  - Computers and Networks (The core courses and specialization courses below are a selection for students who wish to specialize in the area of "Computers and Networks", see . The individual study plan is subject to the tutor's approval.)
    - Specialization Courses (These specialization courses are particularly recommended for the area of "Computers and Networks", but you are free to choose courses from any other field in agreement with your tutor. A minimum of 40 credits must be obtained from specialization courses during the Master's Programme.)
- Master Studies (Programme Regulations 2008)
  - Major Courses (A total of 42 CP must be achieved form courses during the Master Program. The individual study plan is subject to the tutor's approval.)
    - Computers and Networks
      - Recommended Subjects (These courses are recommended, but you are free to choose courses from any other special field. Please consult your tutor.)
Doctoral Dep. of Information Technology and Electrical Engineering (More Information at: )
- Doctoral and Post-Doctoral Courses (A minimum of 12 ECTS credit points must be obtained during doctoral studies. The courses on offer below are but a small selection out of a much larger available number of courses. Please discuss your course selection with your PhD supervisor.)