Cognitive Technologies

Qualitative Spatial Abstraction in Reinforcement Learning

Authors: Frommberger, Lutz

  • Introduces many original ideas
  • A significant contribution to the field of reinforcement learning
  • Offers pointers to future research
see more benefits

Buy this book

eBook $109.00
price for USA
  • ISBN 978-3-642-16590-0
  • Digitally watermarked, DRM-free
  • Included format: PDF
  • ebooks can be used on all reading devices
  • Download immediately after purchase
Hardcover $139.00
price for USA
  • ISBN 978-3-642-16589-4
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Softcover $139.00
price for USA
  • ISBN 978-3-642-26600-3
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
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.

 

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.

 

The book is suitable for researchers working in artificial intelligence, in particular knowledge representation, learning, spatial cognition, and robotics.

 

About the authors

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.

Table of contents (8 chapters)

  • Introduction

    Frommberger, Lutz

    Pages 1-8

  • Foundations of Reinforcement Learning

    Frommberger, Lutz

    Pages 9-21

  • Abstraction and Knowledge Transfer in Reinforcement Learning

    Frommberger, Lutz

    Pages 23-41

  • Qualitative State Space Abstraction

    Frommberger, Lutz

    Pages 43-65

  • Generalization and Transfer Learning with Qualitative Spatial Abstraction

    Frommberger, Lutz

    Pages 67-92

Buy this book

eBook $109.00
price for USA
  • ISBN 978-3-642-16590-0
  • Digitally watermarked, DRM-free
  • Included format: PDF
  • ebooks can be used on all reading devices
  • Download immediately after purchase
Hardcover $139.00
price for USA
  • ISBN 978-3-642-16589-4
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Softcover $139.00
price for USA
  • ISBN 978-3-642-26600-3
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Loading...

Bibliographic Information

Bibliographic Information
Book Title
Qualitative Spatial Abstraction in Reinforcement Learning
Authors
Series Title
Cognitive Technologies
Copyright
2010
Publisher
Springer-Verlag Berlin Heidelberg
Copyright Holder
Springer-Verlag Berlin Heidelberg
eBook ISBN
978-3-642-16590-0
DOI
10.1007/978-3-642-16590-0
Hardcover ISBN
978-3-642-16589-4
Softcover ISBN
978-3-642-26600-3
Series ISSN
1611-2482
Edition Number
1
Number of Pages
XVII, 174
Topics