Reinforcement learning (RL) is thought to be an appropriate paradigm for acquiring control polici... more Reinforcement learning (RL) is thought to be an appropriate paradigm for acquiring control policies in mobile robotics. However, in its standard formulation (tabula rasa) RL must explore and learn everything from scratch, which is neither realistic nor effective in real-world tasks. In this article we propose a new strategy, called Supervised Reinforcement Learning (SRL), for taking advantage of external knowledge within this type of learning and validate it in a wall-following behaviour.
The design of fuzzy controllers for the implementation of behaviors in mobile robotics is a compl... more The design of fuzzy controllers for the implementation of behaviors in mobile robotics is a complex and highly time-consuming task. The use of machine learning techniques, such as evolutionary algorithms or artificial neural networks for the learning of these controllers allows to automate the design process. In this paper, the automated design of a fuzzy controller using genetic algorithms for the implementation of the wall-following behavior in a mobile robot is described. The algorithm is based on the Iterative Rule Learning (IRL) approach, and a parameter (δ) is defined with the aim of selecting the relation between the number of rules and the quality and accuracy of the controller. The designer has to define the universe of discourse and the precision of each variable, and also the scoring function. No restrictions are placed neither in the number of linguistic labels nor in the values that define the membership functions.
International Conference on Advanced Learning Technologies, 2003
In this paper we present a teacher interface for a computer supported educational system that we ... more In this paper we present a teacher interface for a computer supported educational system that we are developing. This interface was developed over a PDA with wireless network connectivity to be carried by the teacher into the classroom.
The paper analyzes why traditional returns-based tests of market timing ability suggest that mutu... more The paper analyzes why traditional returns-based tests of market timing ability suggest that mutual fund managers possess no timing (or even perverse) ability. Our explanation is based on asymmetric correlation, which establishes that asset correlations are less strong in bull markets than in bear markets. This variation in stock correlations could mechanically lead to a variation in measured stock (and hence portfolio) betas in down versus up markets. For a portfolio of stocks whose betas increase (decrease) in down (up) markets, the estimated timing coefficient would be negative (positive). The paper investigates the sources of the mechanical variation in betas that would potentially result in spurious inference about timing ability.
The paper analyzes why traditional returns-based tests of market timing ability suggest that mutu... more The paper analyzes why traditional returns-based tests of market timing ability suggest that mutual fund managers possess no timing (or even perverse) ability. Our explanation is based on asymmetric correlation, which establishes that asset correlations are less strong in bull markets than in bear markets. This variation in stock correlations could mechanically lead to a variation in measured stock (and hence portfolio) betas in down versus up markets. For a portfolio of stocks whose betas increase (decrease) in down (up) markets, the estimated timing coefficient would be negative (positive). The paper investigates the sources of the mechanical variation in betas that would potentially result in spurious inference about timing ability.
Uploads
Papers by David Moreno