LZI - Schloss Dagstuhl - Talks + Materials of Seminar 13321

Seminar 13321
Reinforcement Learning

Peter Auer (Montan-Universität Leoben, AT), Marcus Hutter (Australian National University - Canberra, AU), Laurent Orseau (AgroParisTech - Paris, FR)

Caveat: Due to caching problems of dynamic webpages, sometimes newly
uploaded files are not shown. Please reload the page accordingly.


Seminar Wide Materials

Peter Auer , Montan-Universität Leoben

Manuel Blum , Universität Freiburg

Robert Busa-Fekete , Universität Marburg
 Preference-based Reinforcement Learning
Slides: pdf


Yann Chevaleyre , University of Paris North

Marc Deisenroth , TU Darmstadt

Thomas G. Dietterich , Oregon State University
 Solving Simulator-Defined MDPs for Natural Resource Management
Abstracts: txt Slides: pdf


Christos Dimitrakakis , EPFL - Lausanne

Lutz Frommberger , Universität Bremen
 Some thoughts on Transfer Learning in RL: on States and Representation
Abstracts: txtpdf Slides: pdf


Jens Garstka , FernUniversität in Hagen

Mohammad Ghavamzadeh , INRIA - Lille

Marcus Hutter , Australian National University

Rico Jonschkowski , TU Berlin

Petar Kormushev , Italian Institute of Technology - Genova
 Self-introduction slides (Reinforcement and Imitation Learning of Robot Motor Skills)
Slides: pdf

 Reinforcement Learning with Heterogeneous Policy Representations
Abstracts: pdf


Tor Lattimore , Australian National University

Alessandro Lazaric , INRIA - Lille
 Tutorial on Finite-Sample Analysis in Reinforcement Learning
Abstracts: txt Slides: pdf


Timothy Mann , Technion - Haifa
 Towards Active Crowdsourcing for Smart Cities
Slides: pdf

 Theoretical Analysis of Planning with Options
Slides: pdf


Jan Hendrik Metzen , Universität Bremen
 Learning Skill Templates for Parameterized Tasks
Slides: pdf


Gerhard Neumann , TU Darmstadt

Gergely Neu , Budapest University of Technology & Economics

Ann Nowe , Free University of Brussels

Laurent Orseau , AgroParisTech - Paris

Ronald Ortner , Montan-Universität Leoben

Joelle Pineau , McGill University

Doina Precup , McGill University

Mark B. Ring , IDSIA - Manno

Manuela Ruiz-Montiel , University of Malaga
 Multi-objective Reinforcement Learning
Abstracts: pdf Slides: pdf


Scott Sanner , NICTA - Canberra

Nils T. Siebel , Hochschule für Technik und Wirtschaft - Berlin

David Silver , University College London
 Deterministic Policy Gradient Algorithms
Abstracts: txt Slides: pdf Paper: pdf


Orhan Soenmez , Bogaziçi University - Istanbul
 Sequentially Interacting Markov Chain Monte Carlo Based Policy Iteration
Abstracts: pdf Slides: pdf


Peter Sunehag , Australian National University

Richard S. Sutton , University of Alberta
 The Quest for the Ultimate TD(lambda) Prediction-Learning Algorithm
Slides: pdf


Csaba Szepesvari , University of Alberta

William Uther , Google - Sydney

Joel Veness , University of Alberta

Jeremy L. Wyatt , University of Birmingham

Martijn van Otterlo , Radboud University Nijmegen


Creative Commons License
This webpage and the material that is made available on this webpage is licensed under a
Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 Unported License.

The CC by-nc-nd license allows you to copy, distribute and transmit the work under the following conditions: