Implementing a Videoconferencing Studio in Cape Verde to Support a Blended Learning Education System

In 2004, the Calouste Gulbenkian Foundation invited the University of Aveiro to develop an education and training program in advanced topics of ICT for Cape Verde. The focus should be on technologies to support the development of distance education. Two years later, when the program was started, the University of Aveiro had a high-performance videoconferencing Studio installed by the Foundation for National Scientific Computing. However, the investment to duplicate this high quality structure and operating costs were not compatible neither with the project’s budget nor with the technological options available in Cape Verde. This paper demonstrates the decision-making process by an economically viable option to meet the needs and local peculiarities.

Techniques for batch reinforcement learning in robotics

This thesis addresses the Batch Reinforcement Learning methods in Robotics. This sub-class of Reinforcement Learning has shown promising results and has been the focus of recent research. Three contributions are proposed that aim to extend the state-of-art methods allowing for a faster and more stable learning process, such as required for learning in Robotics. The Q-learning update-rule is widely applied, since it allows to learn without the presence of a model of the environment. However, this update-rule is transition-based and does not take advantage of the underlying episodic structure of collected batch of interactions. The Q-Batch update-rule is proposed in this thesis, to process experiencies along the trajectories collected in the interaction phase. This allows a faster propagation of obtained rewards and penalties, resulting in faster and more robust learning. Non-parametric function approximations are explored, such as Gaussian Processes. This type of approximators allows to encode prior knowledge about the latent function, in the form of kernels, providing a higher level of exibility and accuracy. The application of Gaussian Processes in Batch Reinforcement Learning presented a higher performance in learning tasks than other function approximations used in the literature. Lastly, in order to extract more information from the experiences collected by the agent, model-learning techniques are incorporated to learn the system dynamics. In this way, it is possible to augment the set of collected experiences with experiences generated through planning using the learned models. Experiments were carried out mainly in simulation, with some tests carried out in a physical robotic platform. The obtained results show that the proposed approaches are able to outperform the classical Fitted Q Iteration.