Institut für Grundlagen der Informationsverarbeitung
Assoc. Prof. Dr. Robert Legenstein
Office hours: by appointment (via e-mail)
In this seminar, we will cover deep reinforcement learning (RL), which covers a class of learning methods that have achieved impressive results in recent years. We will start by introducing the general reinforcement learning framework and its most important algorithms before moving to the modern approach of deep reinforcement using neural networks as a basis. No prior knowledge in reinforcement learning is assumed. However, we assume that students are familiar with general machine learning concepts as well as with neural networks (at least its basics).
The general introductory talks will be based on the book “Reinforcement Learning: An Introduction, Second edition”, by RS Sutton and AG Barto (abbreviated as SB below). Later talks will be based on recent papers on deep reinforcement learning.
Notes about key concepts that should be discussed in the specific talks: PDF.
Use this guide to help you prepare your talk successfully.
Talks should be no longer than 35 minutes, and they should be be clear,
interesting and informative, rather than a reprint of the material.
Select what parts of the material you want to present, and what not, and
then present the selected material well (including definitions not given
in the material: look them up on the web or if that is not successful,
ask the seminar organizers). Often diagrams or figures are useful for a
talk. on the other hand, giving in the talk numbers of references that
are listed at the end is a no-no (a talk is an online process, not meant
to be read). For the same reasons you can also quickly repeat earlier
definitions or so if you suspect that the audience may not remember it.
Talks will be assigned at the first seminar meeting. Students are requested to have a quick glance at the topics prior to this meeting in order to determine their preferences. Note that the number of participants for this seminar will be limited.
|Date||#||Topic / paper title||Presenter||Presentation|
|29.10.2019||1||SB Ch 1,2||Kulmer Marvin Jonathan|
|29.10.2019||2||SB Ch 3||FeichtnerJohannes|
|5.11.2019||3||SB Ch 4||Schögler Christoph|
|5.11.2019||4||SB Ch 5||Wachter Alexander|
|12.11.2019||5||SB Ch 6||Ziegler Dominik|
|12.11.2019||6||SB Ch 9||Fuchs Alexander|
|26.11.2019||7||Human-level control through deep reinforcement learning.||Baronig Maximilian|
|26.11.2019||8||Deep reinforcement learning with double q-learning.||Trapp Martin|
|03.12.2019||9||SB Ch 13||Koschatko Katharina|
|03.12.2019||10||Policy Gradient Methods for Reinforcement Learning with Function Approximation||Ek Hanna Kristin|
|10.12.2019||11||Asynchronous methods for deep reinforcement learning.||Khodachenko Ian|
|10.12.2019||12||Deterministic policy gradient algorithms.||Weinrauch Alexander|
|10.12.2020||13||Proximal policy optimization algorithms.||Toth Christian|
|07.01.2020||15||End-to-end training of deep visuomotor policies. Part 1||Nguyen Thi Kim Truc|
|07.01.2020||16||End-to-end training of deep visuomotor policies. Part 2||Rohr Benjamin|
|14.01.2020||14||Learning dexterous in-hand manipulation.||Novak Markus|
|14.01.2020||17||Imagination-augmented agents for deep reinforcement learning.||Lazaro Garcia Ernesto|
|21.01.2020||18||Combined reinforcement learning via abstract representations.||Kumar Chetan Srinivasa|
|21.01.2020||19||Unsupervised State Representation Learning in Atari.||Maiti Shalini||PDF
|28.01.2020||20||SB Ch8||Simic Ilija|
|28.01.2020||21||Mastering the game of Go with deep neural networks and tree search.||Muelleder Thoma|