HAPPY HOLIDAYS: Get a special discount on Apress Access! Subscribe today >>

Motivated Reinforcement Learning

Curious Characters for Multiuser Games

Authors: Merrick, Kathryn E., Maher, Mary Lou

  • Motivated reinforcement learning agents are applied as a novel approach to designing dynamic, adaptive characters for multiuser, online games

Buy this book

eBook $109.00
price for USA
  • ISBN 978-3-540-89187-1
  • Digitally watermarked, DRM-free
  • Included format: PDF
  • ebooks can be used on all reading devices
  • Download immediately after purchase
Hardcover $149.00
price for USA
  • ISBN 978-3-540-89186-4
  • Free shipping for individuals worldwide
  • Online orders shipping within 2-3 days.
Softcover $149.00
price for USA
  • ISBN 978-3-642-10035-2
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
About this book

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.

Table of contents (10 chapters)

  • Non-Player Characters in Multiuser Games

    Merrick, Kathryn E. (et al.)

    Pages 3-16

  • Motivation in Natural and Artificial Agents

    Merrick, Kathryn E. (et al.)

    Pages 17-43

  • Towards Motivated Reinforcement Learning

    Merrick, Kathryn E. (et al.)

    Pages 45-70

  • Comparing the Behaviour of Learning Agents

    Merrick, Kathryn E. (et al.)

    Pages 71-88

  • Curiosity, Motivation and Attention Focus

    Merrick, Kathryn E. (et al.)

    Pages 91-120

Buy this book

eBook $109.00
price for USA
  • ISBN 978-3-540-89187-1
  • Digitally watermarked, DRM-free
  • Included format: PDF
  • ebooks can be used on all reading devices
  • Download immediately after purchase
Hardcover $149.00
price for USA
  • ISBN 978-3-540-89186-4
  • Free shipping for individuals worldwide
  • Online orders shipping within 2-3 days.
Softcover $149.00
price for USA
  • ISBN 978-3-642-10035-2
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.

Services for this book

Loading...

Bibliographic Information

Bibliographic Information
Book Title
Motivated Reinforcement Learning
Book Subtitle
Curious Characters for Multiuser Games
Authors
Copyright
2009
Publisher
Springer-Verlag Berlin Heidelberg
Copyright Holder
Springer-Verlag Berlin Heidelberg
eBook ISBN
978-3-540-89187-1
DOI
10.1007/978-3-540-89187-1
Hardcover ISBN
978-3-540-89186-4
Softcover ISBN
978-3-642-10035-2
Edition Number
1
Number of Pages
XIV, 206
Number of Illustrations and Tables
86 b/w illustrations, 32 illustrations in colour
Topics