Sciweavers

202 search results - page 29 / 41
» Dynamic modelling and control of variable stiffness actuator...
Sort
View
ICML
1994
IEEE
13 years 11 months ago
A Modular Q-Learning Architecture for Manipulator Task Decomposition
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...
Chen K. Tham, Richard W. Prager
VW
2000
Springer
215views Virtual Reality» more  VW 2000»
13 years 11 months ago
A 3-D Biomechanical Model of the Salamander
This article describes a 3D biomechanical simulation of a salamander to be used in experiments in computational neuroethology. The physically-based simulation represents the salama...
Auke Jan Ijspeert
SIGMETRICS
2009
ACM
126views Hardware» more  SIGMETRICS 2009»
14 years 1 months ago
Self-adaptive admission control policies for resource-sharing systems
We consider the problem of admission control in resource sharing systems, such as web servers and transaction processing systems, when the job size distribution has high variabili...
Varun Gupta, Mor Harchol-Balter
CP
2004
Springer
14 years 25 days ago
Controllability of Soft Temporal Constraint Problems
In real-life temporal scenarios, uncertainty and preferences are often essential, coexisting aspects. We present a formalism where temporal constraints with both preferences and un...
Francesca Rossi, Kristen Brent Venable, Neil Yorke...
NN
2002
Springer
208views Neural Networks» more  NN 2002»
13 years 7 months ago
A spiking neuron model: applications and learning
This paper presents a biologically-inspired, hardware-realisable spiking neuron model, which we call the Temporal Noisy-Leaky Integrator (TNLI). The dynamic applications of the mo...
Chris Christodoulou, Guido Bugmann, Trevor G. Clar...