Technical Note: \cal Q-Learning
Machine Learning
Representation and processing of spatial expressions
A Taxonomy of Granular Partitions
COSIT 2001 Proceedings of the International Conference on Spatial Information Theory: Foundations of Geographic Information Science
Generalizing Graphs Using Amalgamation and Selection
SSD '99 Proceedings of the 6th International Symposium on Advances in Spatial Databases
Consistent Queries over Cardinal Directions Across Different Levels of Detail
DEXA '00 Proceedings of the 11th International Workshop on Database and Expert Systems Applications
Cross-domain transfer for reinforcement learning
Proceedings of the 24th international conference on Machine learning
Journal of Artificial Intelligence Research
IJCAI'85 Proceedings of the 9th international joint conference on Artificial intelligence - Volume 1
Building portable options: skill transfer in reinforcement learning
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Generalization and transfer learning in noise-affected robot navigation tasks
EPIA'07 Proceedings of the aritficial intelligence 13th Portuguese conference on Progress in artificial intelligence
Skill acquisition via transfer learning and advice taking
ECML'06 Proceedings of the 17th European conference on Machine Learning
Generating adaptive route instructions using hierarchical reinforcement learning
SC'10 Proceedings of the 7th international conference on Spatial cognition
Qualitative distances and qualitative image descriptions for representing indoor scenes in robotics
Pattern Recognition Letters
Safety and Precision of Spatial Context Models for Autonomous Systems
Electronic Notes in Theoretical Computer Science (ENTCS)
| Hi-index | 0.00 |
Spatial abstraction empowers complex agent control processes. We propose a formal definition of spatial abstraction and classify it by its three facets, namely aspectualization, coarsening, and conceptual classification. Their characteristics are essentially shaped by the representation on which abstraction is performed. We argue for the use of so-called aspectualizable representations which enable knowledge transfer in agent control tasks. In a case study we demonstrate that aspectualizable spatial knowledge learned in a simplified simulation empowers strategy transfer to a real robotics platform.