Sciweavers

2100 search results - page 143 / 420
» Observation Can Be as Effective as Action in Problem Solving
Sort
View
ICRA
2009
IEEE
143views Robotics» more  ICRA 2009»
16 years 1 months ago
Least absolute policy iteration for robust value function approximation
Abstract— Least-squares policy iteration is a useful reinforcement learning method in robotics due to its computational efficiency. However, it tends to be sensitive to outliers...
Masashi Sugiyama, Hirotaka Hachiya, Hisashi Kashim...
CEC
2008
IEEE
16 years 28 days ago
Direction matters in high-dimensional optimisation
Abstract— Directional biases are evident in many benchmarking problems for real-valued global optimisation, as well as many of the evolutionary and allied algorithms that have be...
Cara MacNish, Xin Yao
ICIP
2009
IEEE
16 years 7 months ago
2d-3d Registration Of Deformable Shapes With Manifold Projection
We present an algorithm able to register a known 3D deformable model to a set of 2D matched points extracted from a single image. Unlike previous approaches, the problem is solved...
CVIU
2007
137views more  CVIU 2007»
15 years 6 months ago
Visual learning of texture descriptors for facial expression recognition in thermal imagery
Facial expression recognition is an active research area that finds a potential application in human emotion analysis. This work presents an illumination independent approach for...
Benjamín Hernández, Gustavo Olague, ...
CDC
2008
IEEE
215views Control Systems» more  CDC 2008»
16 years 28 days ago
A coverage algorithm for a class of non-convex regions
— The paper describes a framework for solving the coverage problem for a class of non-convex domains. In [1] we have shown how a diffeomorphism can be used to transform a non-con...
Carlos H. Caicedo-Nunez, Milos Zefran