190 search results - page 34 / 38 » Abstraction and Generalization in Reinforcement Learning: A ... |
ICASSP
2007
IEEE
14 years 3 months ago
2007
IEEE
Abstract— This work considers a combination classificationregression based framework with the proposal of using learned kernels in modified support vector regression to provide...
ICRA
2003
IEEE
14 years 2 months ago
2003
IEEE
Existing task allocation algorithms generally do not consider the effects of task interaction, such as interference, but instead assume that tasks are independent. That assumptio...
GECCO
2010
Springer
13 years 9 months ago
2010
Springer
To complement standard fitness functions, we propose "Fitness Importance" (FI) as a novel meta-heuristic for online learning systems. We define FI and show how it can be...
HUMO
2007
Springer
14 years 3 months ago
2007
Springer
Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
ESANN
2007
13 years 11 months ago
2007
Uncertainty is a popular phenomenon in machine learning and a variety of methods to model uncertainty at different levels has been developed. The aim of this paper is to motivate ...