Recently, model-free reinforcement learning algorithms have been shown to solve challenging problems by learning from extensive interaction with the environment. A significant issue with transferring this success to the robotics domain is that interaction with the real world is costly, but training on limited experience is prone to overfitting. We present a method for learning to navigate, to a...

This article presents a virtual environment of cooperative Web-based learning to support the teaching of Music, specifically Musical Harmony. Such environment offers support to both semi-distant learning courses and strict distant learning using Internet/Web. The aim of this work is to integrate artificial and human agents in an interactive environment endowed with access to several high qualit...

This paper is an experience report describing the Learn@WU learning environment, which to our knowledge is one of the largest operational learning environments in higher education. The platform, which is entirely based on open source components, enjoys heavy usage by about 4,000 WU freshmen each year. At present, the learning environment supports 18 high-enrollment courses and contains more tha...

Web interactive multimedia technology (WIMT), which is an information and communication system, was introduced in a large metropolitan university. Its features are outlined in this paper, from simply textbased to more complex. The system incorporates several interactive and multimedia features, such as chat, audio, video, polling, whiteboard and desktop sharing. This system provides real time c...

An online interactive learning environment which offers immediate feedback to student learning SQL was constructed. This has supported the gathering of interesting statistics on student behaviour. Changes to the environment targeted at improving student behaviour can be made, and the impact of these changes measured statistically on real students. This paper considers a cycle through measuring ...

We address the problem of imitation learning in interactive robots which learn from task demonstrations. Many current approaches to interactive robot learning are performed over a set of demonstrations, where the robot observes several demonstrations of the same task and then creates a generalized model. In contrast, we aim to enable a robot to learn from individual demonstrations, each of whic...

The core problem we address in this paper is how to take a declarative conceptual representation of a complex system and produce an agent-based simulation of that model. In particular, we describe a computational technique that takes Structure-Behavior-Function models of complex systems and simulates the behavior of the modeled system in NetLogo, an agent-based programming and simulation enviro...

Access to the laboratory component of a class is limited by resources, while lab training is not currently possible for distance learning. To overcome the problem a solution is proposed to enable hands-on, interactive, objectively scored and appropriately mentored learning in a widely accessible environment. The proposed solution is the Virtual-Reality Motor-Skills trainer to teach basic fine-m...

We have developed a new computer based learning environment to teach adaptive systems in the EE undergraduate curriculum. The learning environment is based upon an electronic book containing a hypertext document linked with a software simulator which runs interactive examples on-line, and is fully controlled by the student. This paper presents the concepts behind the project, its implementation...