[robotics-worldwide] ECAI Workshop on Evolutionary and Reinforcement Learning for Autonomous Robot Systems (ERLARS 2010)

Yohannes Kassahun kassahun at informatik.uni-bremen.de
Mon Feb 8 11:50:19 PST 2010


[Apologies if you receive this more than once!]

************************************************************************

ERLARS 2010

3rd INTERNATIONAL WORKSHOP ON EVOLUTIONARY AND REINFORCEMENT LEARNING
FOR AUTONOMOUS ROBOT SYSTEMS

Held in conjunction with the 19th European Conference on Artificial
Intelligence (ECAI 2010) in Lisbon, Portugal on August 16, 2010.

Submission deadline: May 7, 2010.

http://www.erlars.org/2010/

************************************************************************

CALL FOR PAPERS

Objectives

Learning is essential for an autonomous robot system. The range of
unexpected situations it can handle while performing its task depends
on its ability to adapt. Recent developments have taken autonomous
robots beyond industrial settings, for example at home as toys and
cleaners.

However, production models usually interact with their environment
following a fixed control strategy, which limits their range of
application. More adaptable robots require control strategies that
learn more and better from interactions with their environment.  The
ERLARS workshop addresses the challenge to develop efficient and
versatile learning architectures for autonomous robot systems, with
the main focus on adequate evolutionary and reinforcement learning
algorithms.

Relevant Topics

Papers are invited on all aspects of learning methods for the control
of autonomous robot systems, including, but not limited to:

* Model-free visual servoing
* Mobile robot navigation by means of reinforcement learning
* Combining offline- and online learning methods for robot control
* Reinforcement learning by evolutionary algorithms of neural network-based
and other robot controllers
* Hybrid systems that combine modelling and parameter estimation by
reinforcement learning
* Learning from scratch and cascaded learning architectures
* Developmental and epigenetic robotics
* Balancing exploration and exploitation of acquired knowledge
* Simulated environments for autonomous robot learning scenarios

Important Dates

* May 7 2010: Paper submissions due
* June 7 2010: Notification of paper acceptance
* June 24 2010: Camera ready paper submission
* August 16 or 17 2010 (TBA): Workshop takes place


Workshop Chairs

Nils T Siebel
Building Automation Lab, Department of Engineering 1,
HTW University of Applied Sciences Berlin, Berlin, Germany

Josef Pauli
Intelligent Systems Group, Department of Computer Science,
University of Duisburg-Essen Duisburg, Germany

Yohannes Kassahun
Research Group Robotics, Robotics Innovation Center,
University of Bremen, Bremen, Germany


Programme Committee

Andrew Barto (University of Massachusetts Amherst, USA)
Peter Dürr (EPFL Lausanne, Switzerland)
Christian Igel (Ruhr-Universität Bochum, Germany)
Yohannes Kassahun (University of Bremen, Germany)
Takanori Koga (Yamaguchi University, Japan)
Tim Kovacs (University of Bristol, UK)
Jun Ota (University of Tokyo, Japan)
Josef Pauli (University of Duisburg-Essen, Germany)
Jan Peters (MPI for Biological Cybernetics, Tübingen, Germany)
Daniel Polani (University of Hertfordshire, Hatfield, UK)
Marcello Restelli (Politecnico di Milano, Italy)
Stefan Schiffer (RWTH Aachen University, Germany)
Juergen Schmidhuber (Swiss AI Lab IDSIA, Lugano, Switzerland)
Marc Toussaint (TU Berlin, Germany)
Nils T Siebel (HTW University of Applied Sciences, Germany)
Jeremy Wyatt (University of Birmingham, UK)

************************************************************************

More information on the workshop website: http://www.erlars.org/2010/

************************************************************************


More information about the robotics-worldwide mailing list