Sciweavers

730 search results - page 43 / 146
» Learning for control from multiple demonstrations
Sort
View
BMCBI
2010
132views more  BMCBI 2010»
14 years 9 months ago
Parallel multiplicity and error discovery rate (EDR) in microarray experiments
Background: In microarray gene expression profiling experiments, differentially expressed genes (DEGs) are detected from among tens of thousands of genes on an array using statist...
Wayne Wenzhong Xu, Clay J. Carter
FBIT
2007
IEEE
15 years 4 months ago
Learning to Drive a Real Car in 20 Minutes
The paper describes our first experiments on Reinforcement Learning to steer a real robot car. The applied method, Neural Fitted Q Iteration (NFQ) is purely data-driven based on ...
Martin Riedmiller, Michael Montemerlo, Hendrik Dah...
76
Voted
ICRA
2010
IEEE
128views Robotics» more  ICRA 2010»
14 years 8 months ago
A game-theoretic procedure for learning hierarchically structured strategies
— This paper addresses the problem of acquiring a hierarchically structured robotic skill in a nonstationary environment. This is achieved through a combination of learning primi...
Benjamin Rosman, Subramanian Ramamoorthy
ICALT
2010
IEEE
14 years 8 months ago
Reusing Adaptation Strategies in Adaptive Educational Hypermedia Systems
—Due to the difficulty and thus effort and expenses involved in creating them, personalization strategies in learning environments have to demonstrate a higher returnon-investmen...
Joshua Scotton, Alexandra I. Cristea
ICRA
2005
IEEE
106views Robotics» more  ICRA 2005»
15 years 3 months ago
Goal-Directed Imitation in a Humanoid Robot
Abstract— Our work aims at developing a robust discriminant controller for robot programming by demonstration. It addresses two core issues of imitation learning, namely “what to...
Sylvain Calinon, Florent Guenter, Aude Billard