Sciweavers

437 search results - page 17 / 88
» Policy Gradient Critics
Sort
View
IEEESP
2008
136views more  IEEESP 2008»
13 years 8 months ago
The Crutial Way of Critical Infrastructure Protection
Today, critical infrastructures like the power grid are essentially physical processes controlled by computers connected by networks. They are usually as vulnerable as any other i...
Alysson Neves Bessani, Paulo Sousa, Miguel Correia...
ICML
2010
IEEE
13 years 9 months ago
Toward Off-Policy Learning Control with Function Approximation
We present the first temporal-difference learning algorithm for off-policy control with unrestricted linear function approximation whose per-time-step complexity is linear in the ...
Hamid Reza Maei, Csaba Szepesvári, Shalabh ...
CEC
2011
IEEE
12 years 8 months ago
Stochastic Natural Gradient Descent by estimation of empirical covariances
—Stochastic relaxation aims at finding the minimum of a fitness function by identifying a proper sequence of distributions, in a given model, that minimize the expected value o...
Luigi Malagò, Matteo Matteucci, Giovanni Pi...
INFOCOM
2000
IEEE
14 years 1 months ago
QoS Provisioning and Tracking Fluid Policies in Input Queueing Switches
The concept of tracking ‡uid policies by packetized policies is extended to input queueing switches. It is considered that the speed up of the switch is one. One of the interest...
Vahid Tabatabaee, Leonidas Georgiadis, Leandros Ta...
PCI
2005
Springer
14 years 2 months ago
TSIC: Thermal Scheduling Simulator for Chip Multiprocessors
Abstract. Increased power density, hot-spots, and temperature gradients are severe limiting factors for today’s state-of-the-art microprocessors. However, the flexibility offer...
Kyriakos Stavrou, Pedro Trancoso