Motivated Reinforcement Learning Curious Characters for Multiuser Games /

• Main Authors: Merrick, Kathryn (Author), Maher, Mary Lou (Author)
• Corporate Author: SpringerLink (Online service)
• Format: Electronic eBook
• Language: English
• Published: Berlin, Heidelberg : Springer Berlin Heidelberg, 2009.
• Subjects: Computer science.; User interfaces (Computer systems).; Artificial intelligence.; Computer graphics.; Computer-aided engineering.; Computer Science.; Artificial Intelligence (incl. Robotics).; User Interfaces and Human Computer Interaction.; Computer Graphics.; Computer Imaging, Vision, Pattern Recognition and Graphics.; Computer-Aided Engineering (CAD, CAE) and Design.

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 an...

Table of Contents:

• 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.