[Amdnl] Last CFP: ERLARS 2013 @ ECAL 2013: Evolutionary and Reinforcement Learning for Autonomous Robot Systems

[Nils T Siebel, ERLARS Workshop]

[Apologies if you receive this more than once]

Dear Colleagues,

This is just a reminder that the submission deadline is approaching fast:

  Friday, June 14 2013.

The submission is open at http://www.erlars.org/2013/papers/

ERLARS 2013, the 6th International Workshop on Evolutionary and Reinforcement
Learning for Autonomous Robot Systems will this year take place in Taormina,
Italy on September 2 2013 in conjunction with the 12th European Conference on
Artificial Life (ECAL 2013).

We are looking forward to your contributions in the research areas given below.

Kind regards,

Nils T Siebel
ERLARS 2013 Chair

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

ERLARS 2013

6th INTERNATIONAL WORKSHOP ON
EVOLUTIONARY AND REINFORCEMENT LEARNING FOR AUTONOMOUS ROBOT SYSTEMS

Taormina, Italy, September 2 2013

Submission deadline: June 14 2013

http://www.erlars.org/2013/

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

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 reinforcement and evolutionary 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:

  * 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
  * Combining modelling and parameter estimation by reinforcement learning
  * Combining evolutionary and reinforcement learning (Hybrid approaches)
  * Cascaded and hierarchical learning architectures
  * Knowledge-based reinforcement learning
  * Learning through imitation and transfer learning
  * Balancing exploration and exploitation of acquired knowledge
  * Simulated environments for autonomous robot learning scenarios
  * Minimising the simulation reality gap
  * Developmental and epigenetic robotics

*** Important Dates ***

  * June 14 2013: Paper submissions due
  * June 29 2013: Notification of paper acceptance
  * July 10 2013: Camera ready paper submission
  * September 2 2013: Workshop takes place

*** Workshop Chair ***

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

*** Programme Committee (tentative) ***

Andrew Barto (University of Massachusetts Amherst, USA)
Peter Dürr (EPFL Lausanne, Switzerland)
Christian Igel (Ruhr-Universität Bochum, Germany)
Takanori Koga (Yamaguchi University, Japan)
Tim Kovacs (University of Bristol, UK)
Jun Ota (University of Tokyo, Japan)
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)
Marc Toussaint (TU Berlin, Germany)
Jeremy Wyatt (University of Birmingham, UK)

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

More information on the workshop website: http://www.erlars.org/2013/

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