Sciweavers

1907 search results - page 365 / 382
» A Pattern and Dependency Based Approach to the Design of Pro...
Sort
View
ICRA
2010
IEEE
137views Robotics» more  ICRA 2010»
13 years 7 months ago
Robot reinforcement learning using EEG-based reward signals
Abstract— Reinforcement learning algorithms have been successfully applied in robotics to learn how to solve tasks based on reward signals obtained during task execution. These r...
Iñaki Iturrate, Luis Montesano, Javier Ming...
AUTONOMICS
2009
ACM
14 years 3 months ago
Sensor Selection for IT Infrastructure Monitoring
Supervisory control is the main means to assure a high level performance and availability of large IT infrastructures. Applied control theory is used in physical and virtualization...
Gergely János Paljak, Imre Kocsis, Zolt&aac...
ICVS
2003
Springer
14 years 1 months ago
A Framework for Visual Servoing
We consider typical manipulation tasks in terms of a service robot framework. Given a task at hand, such as ”Pick up the cup from the dinner table”, we present a number of diff...
Danica Kragic, Henrik I. Christensen
CORR
2006
Springer
153views Education» more  CORR 2006»
13 years 8 months ago
Genetic Programming, Validation Sets, and Parsimony Pressure
Fitness functions based on test cases are very common in Genetic Programming (GP). This process can be assimilated to a learning task, with the inference of models from a limited n...
Christian Gagné, Marc Schoenauer, Marc Pari...
JMLR
2006
124views more  JMLR 2006»
13 years 8 months ago
Policy Gradient in Continuous Time
Policy search is a method for approximately solving an optimal control problem by performing a parametric optimization search in a given class of parameterized policies. In order ...
Rémi Munos