Sciweavers

3047 search results - page 328 / 610
» Randomized Parallel Selection
Sort
View
129
Voted
NN
2002
Springer
113views Neural Networks» more  NN 2002»
15 years 2 months ago
Control of exploitation-exploration meta-parameter in reinforcement learning
In reinforcement learning (RL), the duality between exploitation and exploration has long been an important issue. This paper presents a new method that controls the balance betwe...
Shin Ishii, Wako Yoshida, Junichiro Yoshimoto
113
Voted
TIT
2002
102views more  TIT 2002»
15 years 2 months ago
Asymptotic efficiency of two-stage disjunctive testing
Abstract--We adapt methods originally developed in information and coding theory to solve some testing problems. The efficiency of two-stage pool testing of items is characterized ...
Toby Berger, Vladimir I. Levenshtein
ICIP
2010
IEEE
15 years 18 days ago
A no-reference image content metric and its application to denoising
A no-reference image metric based on the singular value decomposition of local image gradients is proposed in this paper. This metric provides a quantitative measure of true image...
Xiang Zhu, Peyman Milanfar
118
Voted
ICRA
2009
IEEE
100views Robotics» more  ICRA 2009»
15 years 11 days ago
Multi-robot plan adaptation by constrained minimal distortion feature mapping
We propose a novel method for multi-robot plan adaptation which can be used for adapting existing spatial plans of robotic teams to new environments or imitating collaborative spat...
Bálint Takács, Yiannis Demiris
121
Voted
ICTAI
2009
IEEE
15 years 11 days ago
Stochastic Offline Programming
We propose a framework which we call stochastic offline programming (SOP). The idea is to embed the development of combinatorial algorithms in an off-line learning environment whi...
Yuri Malitsky, Meinolf Sellmann