Qualitative Spatial Abstraction in Reinforcement Learning

By Lutz Frommberger

Qualitative Spatial Abstraction in Reinforcement Learning Cover Image

Reinforcement learning has evolved to tackle domains that are yet to be fully understood, or are too complex for a closed description. In this book the author investigates whether suitable abstraction methods can overcome the discipline’s deficiencies.

Full Description

  • ISBN13: 978-3-6421-6589-4
  • 196 Pages
  • User Level: Science
  • Publication Date: December 13, 2010
  • Available eBook Formats: PDF
  • eBook Price: $99.00
Buy eBook Buy Print Book Add to Wishlist

Related Titles

Full Description
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. 
Table of Contents

Table of Contents

  1. Introduction.
  2. Foundations of Reinforcement Learning.
  3. Abstraction and Knowledge Transfer in Reinforcement Learning.
  4. Qualitative State Space Abstraction.
  5. Generalization and Transfer Learning with Qualitative Spatial Abstraction.
  6. RLPR – An Aspectualizable State Space Representation.
  7. Empirical Evaluation.
  8. Summary and Outlook.
  9. References.
  10. Index.
Errata

Please Login to submit errata.

No errata are currently published