Overview
- Book introduces many original ideas
- Significant contribution to the field of reinforcement learning
- Contains pointers to future research
Part of the book series: Cognitive Technologies (COGTECH)
Access this book
Tax calculation will be finalised at checkout
Other ways to access
Table of contents (8 chapters)
Keywords
About this book
Reinforcement learning has developed as a successful learning approach for domains that are not fully understood and that are too complex to be described in closed form. However, reinforcement learning does not scale well to large and continuous problems. Furthermore, acquired knowledge specific to the learned task, and transfer of knowledge to new tasks is crucial.
Â
In this book the author investigates whether deficiencies of reinforcement learning can be overcome by suitable abstraction methods. He discusses various forms of spatial abstraction, in particular qualitative abstraction, a form of representing knowledge that has been thoroughly investigated and successfully applied in spatial cognition research. With his approach, he exploits spatial structures and structural similarity to support the learning process by abstracting from less important features and stressing the essential ones. The author demonstrates his learning approach and the transferability of knowledge by having his system learn in a virtual robot simulation system and consequently transfer the acquired knowledge to a physical robot. The approach is influenced by findings from cognitive science.
Â
The book is suitable for researchers working in artificial intelligence, in particular knowledge representation, learning, spatial cognition, and robotics.
Â
Authors and Affiliations
About the author
Dr. Frommberger is a researcher in the Cognitive Systems Research Group (SFB/TR 8 Spatial Cognition) of Universität Bremen; his special areas of expertise are spatial abstraction techniques, efficient reinforcement learning, cognitive logistics and qualitative representations of space.
Bibliographic Information
Book Title: Qualitative Spatial Abstraction in Reinforcement Learning
Authors: Lutz Frommberger
Series Title: Cognitive Technologies
DOI: https://doi.org/10.1007/978-3-642-16590-0
Publisher: Springer Berlin, Heidelberg
eBook Packages: Computer Science, Computer Science (R0)
Copyright Information: Springer-Verlag Berlin Heidelberg 2010
Hardcover ISBN: 978-3-642-16589-4Published: 12 November 2010
Softcover ISBN: 978-3-642-26600-3Published: 02 January 2013
eBook ISBN: 978-3-642-16590-0Published: 13 December 2010
Series ISSN: 1611-2482
Series E-ISSN: 2197-6635
Edition Number: 1
Number of Pages: XVII, 174
Topics: Artificial Intelligence, Control, Robotics, Mechatronics