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

Evaluación de la competencia comunicativa académica en semi-presencialidad

En la E.U. de Magisterio de Donostia de la Universidad del País Vasco (UPV/EHU), este curso 2010/2011 ha comenzado la oferta semi-presencial para aquellos estudiantes que no pueden matricularse a todas las asignaturas de primer curso. Dentro de esta experiencia piloto se ha impartido la asignatura "Desarrollo de la competencia comunicativa I" en el Grado de Educación Primaria, centrada en la competencia comunicativa académica. El diseño de esta asignatura se ha apoyado en investigaciones relacionadas con el desarrollo de esta competencia en entornos virtuales y ha contado con actividades diversas que han permitido a los estudiantes su autoevaluación y también la coevaluación