Weakly-coupled Markov decision processes can be decomposed into subprocesses that interact only through a small set of bottleneck states. We study a hierarchical reinforcement learning algorithm designed to take advantage of this particular type of decomposability. To test our algorithm, we use a decision-making problem faced by autonomous planetary rovers. In this problem, a Mars rover must de...

This paper examines the potential and the impact of introducing learning capabilities into autonomous agents that make decisions at run-time about which mechanism to exploit in order to coordinate their activities. Specifically, the efficacy of learning is evaluated for making the decisions that are involved in determining when and how to coordinate. Our motivating hypothesis is that to deal wi...

This paper examines the potential and the impact of introducing learning capabilities into autonomous agents that make decisions at run-time about which mechanism to exploit in order to coordinate their activities. Specifically, our motivating hypothesis is that to deal with dynamic and unpredictable environments it is important to have agents that learn the right situations in which to attempt...

This paper proposes several actvites that encourage self-learning in engineering courses. For each actvity, the context and the pedagogical issues addressed are described emphasizing strengths and weaknesses. Specifcally, this work describes and implements fve actvites, which are: questonnaires, conceptual maps, videos, jigsaw and projects. These actvites are applied in seven diferent knowledge...

This study sought to identify the most effective elements required in online professional development to enable teachers to improve their use of Information and Communications Technologies (ICT) in their classrooms. Four schools in Queensland were involved, with twelve classroom teachers participating in a year-long online professional development program over the school year supported by an on...

In this paper, we propose an architecture of ProjectBased Learning Management System (PBLMS). These systems offer learners indicators to support self-regulation in PBL. Indeed, when students are engaged in learning processes with LMS, they are supposed to be autonomous to find information or to organize their activities. Indeed, most of time, few tools are proposed to help them. Our research fo...

Robots are mechanical structures with sensors, effectors and control system. Coupling of sensory inputs to effector outputs requires a robotic control law. Unfortunately, the construction of such control laws is a complicated task. Automatisation of this process requires the incorporation of machine learning techniques. Robots capable of learning are not necessarily synonymous with intelligent ...