A Qualitative Representation of Structural Spatial Knowledge for Robot Navigation with Reinforcement Learning
Type of publication: | Inproceedings |
Citation: | cosy:frommberger:grlpr-icml2006 |
Booktitle: | Proceedings of the ICML-06 Workshop on Structural Knowledge Transfer for Machine Learning |
Year: | 2006 |
Abstract: | In robot navigation tasks, the representation of knowledge of the surrounding world plays an important role, especially in reinforcement learning approaches. This work presents a qualitative representation of space that empowers an agent to learn a goal-directed navigation strategy based on structural knowledge of the world that leads to a generally sensible navigation behavior that can be transferred to completely unknown environments. |
Userfields: | pdfurl={http://www.aussagekraft.de/files/frommberger-icml06.pdf}, project={R3-QShape}, status={Reviewed}, |
Keywords: | |
Authors | |
Attachments
|
|
Notes
|
|
|
|
Topics
|
|