Sciweavers

4544 search results - page 220 / 909
» Reinforcement Learning with Time
Sort
View
ICCS
1993
Springer
14 years 2 months ago
Towards Domain-Independent Machine Intelligence
Adaptive predictive search (APS), is a learning system framework, which given little initial domain knowledge, increases its decision-making abilities in complex problems domains....
Robert Levinson
NIPS
2008
13 years 11 months ago
Signal-to-Noise Ratio Analysis of Policy Gradient Algorithms
Policy gradient (PG) reinforcement learning algorithms have strong (local) convergence guarantees, but their learning performance is typically limited by a large variance in the e...
John W. Roberts, Russ Tedrake
PG
2002
IEEE
14 years 3 months ago
Visualization of Multidimensional, Multivariate Volume Data Using Hardware-Accelerated Non-Photorealistic Rendering Techniques
This paper presents a set of feature enhancement techniques coupled with hardware-accelerated nonphotorealistic rendering for generating more perceptually effective visualizations...
Aleksander Stompel, Eric B. Lum, Kwan-Liu Ma
HICSS
2002
IEEE
97views Biometrics» more  HICSS 2002»
14 years 3 months ago
A Novel Method for Voltage Instability Protection
The growing concern about wide area power system disturbances and their impact on power systems have reinforced interest in the new generation of system protection tools. Their ap...
Miroslav Begovic, Borka Milosevic, Damir Novosel
FLAIRS
2004
13 years 11 months ago
A New Algorithm for Singleton Arc Consistency
Constraint satisfaction technology emerged from AI research. Its practical success is based on integration of sophisticated search with consistency techniques reducing the search ...
Roman Barták, Radek Erben