Browsing by Author "Celaya Llover, Enric"

A competitive strategy for function approximation in Qlearning
Agostini, Alejandro Gabriel; Celaya Llover, Enric (2011)
Conference report
Open AccessIn this work we propose an approach for generalization in continuous domain Reinforcement Learning that, instead of using a single function approximator, tries many different function approximators in parallel, each one ... 
A relational positioning methodology for robot task specification and execution
Rodríguez Tsouroukdissian, Adolfo; Basañez Villaluenga, Luis; Celaya Llover, Enric (IEEE, 2008)
Article
Open AccessThis paper presents a relational positioning methodology that allows to restrict totally or partially the movements of an object by specifying its allowed positions in terms of a set of intuitive geometric constraints. In ... 
Action rule induction from causeeffect pairs learned through robotteacher interaction
Agostini, Alejandro Gabriel; Celaya Llover, Enric; Torras, Carme; Wörgötter, Florentin (2008)
Conference report
Open AccessIn this work we propose a decisionmaking system that efficiently learns behaviors in the form of rules using natural human instructions about causeeffect relations in currently observed situations, avoiding complicated ... 
Action rule induction from causeeffect pairs learned through robotteacher interaction
Agostini, Alejandro Gabriel; Celaya Llover, Enric; Torras, Carme; Wörgötter, Florentin (University of Karlsruhe, 2008)
Conference report
Open AccessIn this work we propose a decisionmaking system that efficiently learns behaviors in the form of rules using natural human instructions about causeeffect relations in currently observed situations, avoiding complicated ... 
Competitive function approximation for reinforcement learning
Agostini, Alejandro Gabriel; Celaya Llover, Enric (2014)
External research report
Open AccessThe application of reinforcement learning to problems with continuous domains requires representing the value function by means of function approximation. We identify two aspects of reinforcement learning that make the ... 
Description of a roboticsoriented relational positioning methodology
Rodríguez Tsouroukdissian, Adolfo; Basañez Villaluenga, Luis; Celaya Llover, Enric (200709)
External research report
Open AccessThis paper presents a relational positioning methodology for flexibly and intuitively specifying offline programmed robot tasks, as well as for assisting the execution of teleoperated tasks demanding precise movements. In ... 
Exact interval propagation for the efficient solution of planar linkages
Celaya Llover, Enric; Creemers, Tom Lambert; Ros Giralt, Lluís (ASME, 2007)
Conference report
Open AccessThis paper presents an interval propagation algorithm for variables in singleloop linkages. Given allowed intervals of values for all variables, the algorithm provides, for every variable, the exact interval of values for ... 
Exact interval propagation for the efficient solution of position analysis problems on planar linkages
Celaya Llover, Enric; Creemers, Tom Lambert; Ros Giralt, Lluís (2012)
Article
Open AccessThis paper presents an interval propagation algorithm for variables in planar singleloop linkages. Given intervals of allowed values for all variables, the algorithm provides, for every variable, the whole set of values, ... 
Learning rules from causeeffects explanations
Agostini, Alejandro Gabriel; Celaya Llover, Enric; Torras, Carme; Wörgötter, Florentin (2008)
External research report
Open AccessIn this work we propose a learning system to learn online an action policy coded in rules using natural human instructions about causeeffect relations in currently observed situations. The instructions only on currently ... 
Natural landmark detection for visuallyguided robot navigation
Celaya Llover, Enric; Albarral, José L.; Jimenez Schlegl, Pablo; Torras, Carme (Springer, 2007)
Part of book or chapter of book
Open AccessThe main difficulty to attain fully autonomous robot navigation outdoors is the fast detection of reliable visual references, and their subsequent characterization as landmarks for immediate and unambiguous recognition. ... 
Online learning of macro planning operators using probabilistic estimations of causeeffects
Agostini, Alejandro Gabriel; Wörgötter, Florentin; Celaya Llover, Enric; Torras, Carme (2008)
External research report
Open AccessIn this work we propose an online learning method for learning action rules for planning. The system uses a probabilistic approach of a constructive induction method that combines a beam search with an examplebased search ... 
Online EM with weightbased forgetting
Celaya Llover, Enric; Agostini, Alejandro Gabriel (2015)
Article
Open AccessIn the online version of the EM algorithm introduced by Sato and Ishii (2000), a timedependent discount factor is introduced for forgetting the effect of the old posterior values obtained with an earlier, inaccurate ... 
Probability density estimation of the Q Function for reinforcement learning
Agostini, Alejandro Gabriel; Celaya Llover, Enric (2009)
External research report
Open AccessPerforming QLearning in continuous stateaction spaces is a problem still unsolved for many complex applications. The Q function may be rather complex and can not be expected to fit into a predefined parametric model. In ... 
Reinforcement learning for robot control using probability density estimations
Agostini, Alejandro Gabriel; Celaya Llover, Enric (INSTICC Press. Institute for Systems and Technologies of Information, Control and Communication, 2010)
Conference report
Restricted access  publisher's policyThe successful application of Reinforcement Learning (RL) techniques to robot control is limited by the fact that, in most robotic tasks, the state and action spaces are continuous, multidimensional, and in essence, too ... 
Reinforcement learning with a Gaussian mixture model
Agostini, Alejandro Gabriel; Celaya Llover, Enric (2010)
Conference report
Open AccessRecent approaches to Reinforcement Learning (RL) with function approximation include Neural Fitted Q Iteration and the use of Gaussian Processes. They belong to the class of fitted value iteration algorithms, which use a ... 
Robot task specification and execution through relational positioning
Rodríguez Tsouroukdissian, Adolfo; Basañez Villaluenga, Luis; Celaya Llover, Enric (IFAC, 2007)
Conference report
Open AccessThis paper presents a relational positioning methodology for flexibly and intuitively specifying offline programmed robot tasks, and for assisting the execution of teleoperated tasks featuring precise or repetitive movements. ... 
Stochastic approximations of average values using proportions of samples
Agostini, Alejandro Gabriel; Celaya Llover, Enric (2011)
External research report
Open AccessIn this work we explain how the stochastic approximation of the average of a random variable is carried out when the observations used in the updates consist in proportion of samples rather than complete samples. 
Visuallyguided robot navigation: From artificial to natural landmarks
Celaya Llover, Enric; Albarral, José L.; Jimenez Schlegl, Pablo; Torras, Carme (Springer, 2007)
Part of book or chapter of book
Open AccessLandmarkbased navigation in unknown unstructured environments is far from solved. The bottleneck nowadays seems to be the fast detection of reliable visual references in the image stream as the robot moves. In our research, ...