3274 search results - page 534 / 655 » Using Learning in a Control Agent |
ICANN
2010
Springer
13 years 10 months ago
2010
Springer
Visual recognition faces the difficult problem of recognizing objects despite the multitude of their appearances. Ample neuroscientific evidence shows that the cortex uses a topogr...
TNN
1998
13 years 8 months ago
1998
: A novel approach to artificial neural networks is presented. The philosophy of this approach is based on two aspects: the design of task-specific networks, and a new neuron model...
CDC
2010
IEEE
13 years 4 months ago
2010
IEEE
Abstract-- We consider reinforcement learning, and in particular, the Q-learning algorithm in large state and action spaces. In order to cope with the size of the spaces, a functio...
PLDI
2006
ACM
14 years 3 months ago
2006
ACM
On-line transducers are an important class of computational agent; we construct and compose together many software systems using them, such as stream processors, layered network p...
CDC
2009
IEEE
14 years 1 months ago
2009
IEEE
Abstract— Many problems associated with networked systems can be formulated as network utility maximization (NUM) problems. NUM problems maximize a global separable measure of ne...