3274 search results - page 507 / 655 » Using Learning in a Control Agent |
NIPS
2001
13 years 10 months ago
2001
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
ICSTM
2000
13 years 10 months ago
2000
System Dynamics has had a tough time breaking into High Schools. Like all good ideas the most difficult part is convincing those who would most benefit that this new approach is i...
ML
2002
ACM
13 years 9 months ago
2002
ACM
We present a general approach to model selection and regularization that exploits unlabeled data to adaptively control hypothesis complexity in supervised learning tasks. The idea ...
ISCA
2007
IEEE
13 years 9 months ago
2007
IEEE
Hyperspectral sensors represent the most advanced instruments currently available for remote sensing of the Earth. The high spatial and spectral resolution of the images supplied ...
IJDSN
2006
13 years 9 months ago
2006
Abstract-- We present a novel formulation of the problem of energy misbehavior and develop an analytical framework for quantifying its impact on other nodes. Specifically, we formu...