Motivated Reinforcement Learning

Curious Characters for Multiuser Games

  • Kathryn Merrick
  • Mary Lou Maher

Table of contents

  1. Front Matter
    Pages i-xiv
  2. Non-Player Characters and Reinforcement Learning

    1. Front Matter
      Pages 1-1
    2. Kathryn E. Merrick, Mary Lou Maher
      Pages 3-16
    3. Kathryn E. Merrick, Mary Lou Maher
      Pages 17-43
    4. Kathryn E. Merrick, Mary Lou Maher
      Pages 45-70
    5. Kathryn E. Merrick, Mary Lou Maher
      Pages 71-88
  3. Developing Curious Characters Using Motivated Reinforcement Learning

    1. Front Matter
      Pages 89-89
    2. Kathryn E. Merrick, Mary Lou Maher
      Pages 91-120
    3. Kathryn E. Merrick, Mary Lou Maher
      Pages 121-134
  4. Curious Characters in Games

    1. Front Matter
      Pages 135-135
    2. Kathryn E. Merrick, Mary Lou Maher
      Pages 137-149
    3. Kathryn E. Merrick, Mary Lou Maher
      Pages 151-170
    4. Kathryn E. Merrick, Mary Lou Maher
      Pages 171-189
  5. Future

    1. Front Matter
      Pages 191-191
    2. Kathryn E. Merrick, Mary Lou Maher
      Pages 193-199
  6. Back Matter
    Pages 201-206

About this book

Introduction

Motivated learning is an emerging research field in artificial intelligence and cognitive modelling. Computational models of motivation extend reinforcement learning to adaptive, multitask learning in complex, dynamic environments – the goal being to understand how machines can develop new skills and achieve goals that were not predefined by human engineers. In particular, this book describes how motivated reinforcement learning agents can be used in computer games for the design of non-player characters that can adapt their behaviour in response to unexpected changes in their environment.

This book covers the design, application and evaluation of computational models of motivation in reinforcement learning. The authors start with overviews of motivation and reinforcement learning, then describe models for motivated reinforcement learning. The performance of these models is demonstrated by applications in simulated game scenarios and a live, open-ended virtual world.

Researchers in artificial intelligence, machine learning and artificial life will benefit from this book, as will practitioners working on complex, dynamic systems – in particular multiuser, online games.

Keywords

Agents Artificial life Cognition Computer games Design Games Learning Motivated learning Multiuser games Online games Second Life artificial intelligence intelligence machine learning modeling

Authors and affiliations

  • Kathryn Merrick
    • 1
  • Mary Lou Maher
    • 2
  1. 1.Australian Defence Force Academy, School of Information Technology &University of New South WalesCanberraAustralia
  2. 2.Fac. Architecture, Dept. Design ComputingUniversity of SydneySydneyAustralia

Bibliographic information

  • DOI https://doi.org/10.1007/978-3-540-89187-1
  • Copyright Information Springer-Verlag Berlin Heidelberg 2009
  • Publisher Name Springer, Berlin, Heidelberg
  • eBook Packages Computer Science
  • Print ISBN 978-3-540-89186-4
  • Online ISBN 978-3-540-89187-1
  • Buy this book on publisher's site