Generalization and Transfer Learning in Noise-Affected Robot Navigation Tasks
Type of publication: | Inproceedings |
Citation: | cosy:Frommberger-epia07 |
Booktitle: | Progress in Artificial Intelligence: EPIA 2007 |
Series: | Lecture Notes in Computer Science |
Volume: | 4874 |
Year: | 2007 |
Pages: | 508-519 |
Publisher: | Springer-Verlag Berlin Heidelberg |
Abstract: | When a robot learns to solve a goal-directed navigation task with reinforcement learning, the acquired strategy can usually exclusively be applied to the task that has been learned. Knowledge transfer to other tasks and environments is a great challenge, and the transfer learning ability crucially depends on the chosen state space representation. This work shows how an agent-centered qualitative spatial representation can be used for generalization and knowledge transfer in a simulated robot navigation scenario. Learned strategies using this representation are very robust to environmental noise and imprecise world knowledge and can easily be applied to new scenarios, offering a good foundation for further learning tasks and application of the learned policy in different contexts. |
Userfields: | pdfurl={http://www.aussagekraft.de/files/Frommberger-EPIA07.pdf}, project={R3-QShape}, status={Reviewed}, |
Keywords: | |
Authors | |
Editors | |
Attachments
|
|
Notes
|
|
|
|
Topics
|
|