730 search results - page 7 / 146 » Learning for control from multiple demonstrations |
ECCV
2004
Springer
15 years 11 months ago
2004
Springer
Abstract. We present a method for learning feature descriptors using multiple images, motivated by the problems of mobile robot navigation and localization. The technique uses the ...
ICRA
2009
IEEE
15 years 4 months ago
2009
IEEE
Abstract— Continuous action sets are used in many reinforcement learning (RL) applications in robot control since the control input is continuous. However, discrete action sets a...
GECCO
2005
Springer
15 years 3 months ago
2005
Springer
In neuroevolution, a genetic algorithm is used to evolve a neural network to perform a particular task. The standard approach is to evolve a population over a number of generation...
66
Voted
GLOBECOM
2010
IEEE
14 years 7 months ago
2010
IEEE
We use Delay-Tolerant Networking (DTN) to break control loops between space-ground communication links and ground-ground communication links to increase overall file delivery effic...
HYBRID
1998
Springer
15 years 1 months ago
1998
Springer
We look at distributed representation of structure with variable binding, that is natural for neural nets and allows traditional symbolic representation and processing. The repres...