LZI - Schloss Dagstuhl - Dagstuhl Reports Submission System for Dagstuhl Seminar 13321
 Collector buttons: 

Dagstuhl Reports Submission System - Dagstuhl Seminar 13321
Reinforcement Learning

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

The submission is closed. No further documentation entries can be added. In case of question, please contact the editorial office via reports@dagstuhl.de.


Seminar Wide Documents (executive summary, reports from working groups, reports from panel discussions, reports from open problem sessions, ...)


Peter Auer , Montan-Universität Leoben

Manuel Blum , Universität Freiburg

Robert Busa-Fekete , Universität Marburg
 Preference-based Evolutionary Direct Policy Search
Entry: txt


Yann Chevaleyre , University of Paris North

Marc Deisenroth , TU Darmstadt

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


Christos Dimitrakakis , EPFL - Lausanne
 ABC and Cover Tree Reinforcement Learning
Entry: txt


Lutz Frommberger , Universität Bremen
 Some thoughts on Transfer Learning in Reinforcement Learning: on States and Representation
Entry: txt


Jens Garstka , FernUniversität in Hagen

Mohammad Ghavamzadeh , INRIA - Lille
 Actor-Critic Algorithms for Risk-Sensitive MDPs
Entry: txt

 Statistical Learning Theory in Reinforcement Learning and Approximate Dynamic Programming
Entry: txt


Marcus Hutter , Australian National University
 Universal Reinforcement Learning
Entry: txt


Rico Jonschkowski , TU Berlin
 Temporal Abstraction by Sparsifying Proximity Statistics
Entry: txt

 State Representation Learning in Robotics
Entry: txt


Petar Kormushev , Italian Institute of Technology - Genova

Tor Lattimore , Australian National University

Alessandro Lazaric , INRIA - Lille

Timothy Mann , Technion - Haifa
 Theoretical Analysis of Planning with Options
Entry: txt


Jan Hendrik Metzen , Universität Bremen
 Learning Skill Templates for Parameterized Tasks
Entry: txt


Gerhard Neumann , TU Darmstadt

Gergely Neu , Budapest University of Technology & Economics
 Online learning in Markov decision processes
Entry: txt


Ann Nowe , Free University of Brussels
 Multi-Objective Reinforcement Learning
Entry: txt


Laurent Orseau , AgroParisTech - Paris
 Knowledge-Seeking Agents
Entry: txt

 Toward a more realistic framework for general reinforcement learning
Entry: txt


Ronald Ortner , Montan-Universität Leoben
 Colored MDPs, Restless Bandits, and Continuous State Reinforcement Learning
Entry: txt


Joelle Pineau , McGill University
 Reinforcement Learning using Kernel-Based Stochastic Factorization
Entry: txt

 A POMDP Tutorial
Entry: txt


Doina Precup , McGill University
 Methods for Bellman Error Basis Function construction
Entry: txt


Mark B. Ring , IDSIA - Manno

Manuela Ruiz-Montiel , University of Malaga
 Multi-objective Reinforcement Learning
Entry: txt


Scott Sanner , NICTA - Canberra
 Recent Advances in Symbolic Dynamic Programming for Hybrid MDPs and POMDPs
Entry: txt


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

David Silver , University College London

Orhan Soenmez , Bogaziçi University - Istanbul
 Sequentially Interacting Markov Chain Monte Carlo Based Policy Iteration
Entry: txt


Peter Sunehag , Australian National University
 Exploration versus Exploitation in Reinforcement Learning
Entry: txt


Richard S. Sutton , University of Alberta

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
 Relations between Reinforcement Learning, Visual Input, Perception and Action
Entry: txt

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