Sciweavers

191 search results - page 30 / 39
» Firefly Algorithm for Continuous Constrained Optimization Ta...
Sort
View
ICRA
2005
IEEE
124views Robotics» more  ICRA 2005»
15 years 8 months ago
Physical Path Planning Using the GNATs
— We continue our investigation into the application of pervasive, embedded networks to support multi-robot tasks. In this work we use a new a hardware platform, the GNATs, to ai...
Keith J. O'Hara, Victor Bigio, Eric R. Dodson, Ary...
NIPS
2008
15 years 3 months ago
Fitted Q-iteration by Advantage Weighted Regression
Recently, fitted Q-iteration (FQI) based methods have become more popular due to their increased sample efficiency, a more stable learning process and the higher quality of the re...
Gerhard Neumann, Jan Peters
JMLR
2010
206views more  JMLR 2010»
14 years 9 months ago
Learning Translation Invariant Kernels for Classification
Appropriate selection of the kernel function, which implicitly defines the feature space of an algorithm, has a crucial role in the success of kernel methods. In this paper, we co...
Sayed Kamaledin Ghiasi Shirazi, Reza Safabakhsh, M...
128
Voted
NIPS
1998
15 years 3 months ago
Risk Sensitive Reinforcement Learning
In this paper, we consider Markov Decision Processes (MDPs) with error states. Error states are those states entering which is undesirable or dangerous. We define the risk with re...
Ralph Neuneier, Oliver Mihatsch
109
Voted
ICIP
2009
IEEE
15 years 1 days ago
New image processing challenges for jointly designed electro-optical imaging systems
Still-image processing algorithms are tailored to and depend crucially upon the properties of the class of images to which they are applied, for instance natural images in consumer...
M. Dirk Robinson, David G. Stork