ERLARS 2008 - 1st International Workshop on
Evolutionary and Reinforcement Learning for Autonomous Robot Systems
Please note: This page is about a past workshop. Please look at our main page for information on current and upcoming events.
About this Workshop
Evolutionary and Reinforcement Learning methods are important learning
approaches for neural networks and other knowledge representations. They are
inspired by nature and known to be used extensively in biological
systems. However, so far their use in artificial cognitive systems,
e.g. autonomous robot systems, is limited. This is mainly due to the large
number of necessary robot actions and/or learning cycles before an acceptable
mapping from perceptions to actions is found. Autonomous robots are becoming
more and more common even in non-industrial settings, an example area being toys
like Sony's Aibo robotic dog and the new Pleo toy dinosaur. However, they tend
to have very limited learning capabilities. These are usually restricted to
adjusting a few parameters in an otherwise fixed control strategy that
determines how the robot interacts with the environment.
In recent years, fast computers have made evolutionary and reinforcement
learning more feasible from a computational point of view. Therefore research
in these areas has attracted more attention. A number of new and efficient
algorithms have shown promising results, albeit many of these still rely on
training in simulated environments or in combinations of offline and online
learning.
The main goal of this workshop is to bring together researchers and promote
work on evolutionary and reinforcement learning methods with a focus on their
(future) application in autonomous robot systems. We believe that in order to
achieve this a great deal of fundamental research, e.g. on the efficiency of
algorithms, is just as important as their practical applications. Therefore
contributions are invited both on theoretical and practical results in this
area.
Topics
The workshop topics include, but are 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
- Balancing exploration and exploitation of acquired knowledge
- Simulated environments for autonomous robot learning scenarios
Location and Dates
The first ERLARS workshop was held in Patras, Greece on July 22 2008 in conjunction with The 18th European Conference on Artificial Intelligence, ECAI 2008.
Schedule
- April 13 2008: Paper submission deadline
- May 10 2008: Notification of paper acceptance
- May 26 2008: Camera ready paper submission
- May 30 2008: Workshop registration for presenting author
- July 22 2008: Workshop takes place
Organisers
|
Nils T Siebel Cognitive Systems Group Institute of Computer Science Christian-Albrechts-University of Kiel Kiel, Germany |
Josef Pauli Intelligent Systems Group Department of Computer Science University of Duisburg-Essen Duisburg, Germany |
Contact
Author of these pages: Nils T Siebel.
Last modified on Tue Mar 15 2011.
Last modified on Tue Mar 15 2011.
