Motivated Reinforcement Learning

Curious Characters for Multiuser Games
2009
ISBN: 978-3-540-89186-4
Verlag: Springer Berlin Heidelberg

Buch, Englisch, 206 Seiten, Format (B × H): 160 mm x 241 mm, Gewicht: 540 g

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.

Zielgruppe

Research

Autoren/Hrsg.

Maher, Mary Lou

Merrick, Kathryn E.

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
• Mathematik | Informatik EDV | Informatik Programmierung | Softwareentwicklung Spiele-Programmierung, Rendering, Animation

Inhaltsverzeichnis

Non-Player Characters and Reinforcement Learning.- Non-Player Characters in Multiuser Games.- Motivation in Natural and Artificial Agents.- Towards Motivated Reinforcement Learning.- Comparing the Behaviour of Learning Agents.- Developing Curious Characters Using Motivated Reinforcement Learning.- Curiosity, Motivation and Attention Focus.- Motivated Reinforcement Learning Agents.- Curious Characters in Games.- Curious Characters for Multiuser Games.- Curious Characters for Games in Complex, Dynamic Environments.- Curious Characters for Games in Second Life.- Future.- Towards the Future.