The Role of the online learner: onsite students becoming online learners

As universities are offering tuition through online learning environments, “onsite students” in higher education are increasingly becoming “online learners”. Since the medium for learning (and teaching) online is a digital environment, and at a distance, the role taken by students and teaching staff is different to the one these are used to in onsite, traditional settings. Therefore the Role of the Online Learner, presented in this paper, is key to onsite students who are to become online learners. This role consists of five competences: Operational, Cognitive, Collaborative, Self-directing, Course-specific. These five competences integrate the various skills, strategies, attitudes and awareness that make up the role of online learner, which learners use to perform efficiently online. They also make up the basis of a tutorial for would-be online learners, going over the Role of the Online Learner by means of concepts, examples and reflective activities. This tutorial, available to students in the author’s website, is also helpful to teaching and counselling staff in guiding their students to become online learners

Semi-online neural-Q_leaming for real-time robot learning

Reinforcement learning (RL) is a very suitable technique for robot learning, as it can learn in unknown environments and in real-time computation. The main difficulties in adapting classic RL algorithms to robotic systems are the generalization problem and the correct observation of the Markovian state. This paper attempts to solve the generalization problem by proposing the semi-online neural-Q_learning algorithm (SONQL). The algorithm uses the classic Q_learning technique with two modifications. First, a neural network (NN) approximates the Q_function allowing the use of continuous states and actions. Second, a database of the most representative learning samples accelerates and stabilizes the convergence. The term semi-online is referred to the fact that the algorithm uses the current but also past learning samples. However, the algorithm is able to learn in real-time while the robot is interacting with the environment. The paper shows simulated results with the "mountain-car" benchmark and, also, real results with an underwater robot in a target following behavior