Qualitative Spatial Abstraction in Reinforcement Learning

  • Lutz Frommberger
Part of the Cognitive Technologies book series (COGTECH)

Table of contents

  1. Front Matter
    Pages i-xvii
  2. Lutz Frommberger
    Pages 1-8
  3. Lutz Frommberger
    Pages 9-21
  4. Lutz Frommberger
    Pages 43-65
  5. Lutz Frommberger
    Pages 123-154
  6. Lutz Frommberger
    Pages 155-159
  7. Back Matter
    Pages 161-174

About this book

Introduction

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.

 

Keywords

Spatial Abstraction State Space Representation Temporal Abstraction Transfer Learni artificial intelligence cognition cognitive science intelligence knowledge knowledge representation learning reinforcement learning robot robotics simulation

Authors and affiliations

  • Lutz Frommberger
    • 1
  1. 1.Cognitive Systems Group, Department of MathematicsUniversity of BremenBremenGermany

Bibliographic information

  • DOI https://doi.org/10.1007/978-3-642-16590-0
  • Copyright Information Springer-Verlag Berlin Heidelberg 2010
  • Publisher Name Springer, Berlin, Heidelberg
  • eBook Packages Computer Science
  • Print ISBN 978-3-642-16589-4
  • Online ISBN 978-3-642-16590-0
  • Series Print ISSN 1611-2482
  • About this book