Most realistic environments are complex, partially observable and impose real-time
constraints on agents operating within them. This paper describes a framework that allows …

Extensive research in case-base maintenance has studied methods for achieving compact,
competent case bases. This work has examined how to achieve good solution performance …

Learning by observation allows a software agent to learn an expert's behaviour, by
examining the actions the expert performs in response to inputs, without the expert having to …

A primary advantage of learning by observation is that it allows non-technical experts to
transfer their skills to an agent. However, this requires a general-purpose learning agent that …

Learning by observation allows domain experts with no programming skills to train a
software agent or robot by moving the burden of knowledge transfer from the ex pert to the …

Human and AI collaboration has evolved drastically over the past decade. Most of the tasks
are now partly handled by machines and partly by humans, resulting in human and AI …

Keeping a player within the flow in a game is a central goal for game designers, making the
game neither too easy nor too hard. Dynamic Difficulty adjustment seeks to fulfill this goal by …

Due to its high potential and encouraging results, project-based learning emerges as a
highly interesting paradigm in the education systems worldwide. Moreover, robotics is an …

The environments an agent is situated in or the behaviours it is required to perform may
change over time. Ideally, an agent should be able to move to a new domain without …

Robots are becoming increasingly common in home, industrial and medical environments.
Their end users may know what they want the robots to do but lack the required technical …