ERLARS 2010 - 3rd International Workshop on
Evolutionary and Reinforcement Learning for Autonomous Robot Systems
Call for Papers
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
Submission Dates
- May 16 2010 (extended!): Paper submissions due
- June 7 2010: Notification of paper acceptance
- June 24 2010: Camera ready paper submission
- August 16: Workshop takes place
The initial paper submission deadline is on Sunday May 16 2010 at 23:59 UTC (GMT).
Paper format
All articles will be published both on CD-ROM/DVD and in a proceedings book with an ISSN. Please see the authors' section for formatting instructions.
Springer Book Chapter
Authors of the best articles accepted at ERLARS 2010 will be invited to submit an extended version of their article as a book chapter in an edited book in the Springer Studies in Computational Intelligence. This has already been confirmed by the series editor. More details will be given later.
Author of these pages: Nils T Siebel.
Last modified on Fri Aug 13 2010.
Last modified on Fri Aug 13 2010.
