The goal of this paper is to show the use of learning technology standards for mobile scenarios, identifying potentials and requirements for the next generation of standards. Within the conception and development process of M-Learning scenarios, learning technology standards are often neglected because they do not take new M-Learning opportunities into account. E-Learning Standards support -amo...

We consider scenarios from the real-time strategy game StarCraft as benchmarks for reinforcement learning algorithms. We focus on micromanagement, that is, the short-term, low-level control of team members during a battle. We propose several scenarios that are challenging for reinforcement learning algorithms because the stateaction space is very large, and there is no obvious feature represent...

Real-time strategy games have been an important field of game artificial intelligence in recent years. This paper presents a reinforcement learning and curriculum transfer learning method to control multiple units in StarCraft micromanagement. We define an efficient state representation, which breaks down the complexity caused by the large state space in the game environment. Then a parameter s...

In the Norwegian DoCTA and DoCTA NSS projects we aimed to bring a theoretical perspective to the design of ICT-mediated learning environments that support the sociocultural aspects of human interaction and to evaluate their use. By taking a sociocultural perspective on learning activity focussing on the interpersonal social interaction in collaborative learning settings we contribute to knowled...

The aim of this article is to discuss possible user scenarios for " intelligent " Learning Management Systems (iLMS) and challenges for implementing them. We focus on those scenarios in which Machine Learning (ML) can be used to enhance general purpose web-based Learning Management Systems. We will propose a software engineering framework for the design and implementation of an iLMS.

The present study thoroughly evaluates the most common blocking challenges faced by federated learning (FL) ecosystem and analyzes existing state-of-the-art solutions. A system adaptation pipeline is designed to enable integration of different AI-based tools in FL system, while training conducted under realistic conditions using a distributed hardware infrastructure. suggested system’s robustne...