Sciweavers

74 search results - page 4 / 15
» Formalizing Multi-state Learning Dynamics
Sort
View
ICML
2005
IEEE
14 years 11 months ago
Bounded real-time dynamic programming: RTDP with monotone upper bounds and performance guarantees
MDPs are an attractive formalization for planning, but realistic problems often have intractably large state spaces. When we only need a partial policy to get from a fixed start s...
H. Brendan McMahan, Maxim Likhachev, Geoffrey J. G...
ICRA
2007
IEEE
189views Robotics» more  ICRA 2007»
14 years 4 months ago
Context Estimation and Learning Control through Latent Variable Extraction: From discrete to continuous contexts
— Recent advances in machine learning and adaptive motor control have enabled efficient techniques for online learning of stationary plant dynamics and it’s use for robust pre...
Georgios Petkos, Sethu Vijayakumar
ICML
1996
IEEE
14 years 2 months ago
A Convergent Reinforcement Learning Algorithm in the Continuous Case: The Finite-Element Reinforcement Learning
This paper presents a direct reinforcement learning algorithm, called Finite-Element Reinforcement Learning, in the continuous case, i.e. continuous state-space and time. The eval...
Rémi Munos
FOIS
2006
13 years 11 months ago
A Dynamic Theory of Ontology
Natural languages are easy to learn by infants, they can express any thought that any adult might ever conceive, and they accommodate the limitations of human breathing rates and s...
John F. Sowa
TNN
2008
106views more  TNN 2008»
13 years 10 months ago
Unsupervised Segmentation With Dynamical Units
In this paper, we present a novel network to separate mixtures of inputs that have been previously learned. A significant capability of the network is that it segments the componen...
A. Ravishankar Rao, Guillermo A. Cecchi, Charles C...