2711 search results - page 406 / 543 » Convergence of the Wake-Sleep Algorithm |
NIPS
2004
14 years 11 months ago
2004
Successful application of reinforcement learning algorithms often involves considerable hand-crafting of the necessary non-linear features to reduce the complexity of the value fu...
103
click to vote
NIPS
2001
14 years 11 months ago
2001
We consider the problem of learning to attain multiple goals in a dynamic environment, which is initially unknown. In addition, the environment may contain arbitrarily varying ele...
CEC
2010
IEEE
14 years 11 months ago
2010
IEEE
The best evolutionary approach can be a difficult problem. In this work we have investigated two evolutionary representations to evolve non-photorealistic renderings: a variable-le...
102
click to vote
CDC
2009
IEEE
14 years 11 months ago
2009
IEEE
In this paper, the formation flight of multiple Unmanned Helicopter (UH) systems is researched and a new decentralized receding horizon formation control algorithm is supposed. The...
AMC
2008
14 years 10 months ago
2008
This paper discusses the infinite horizon stochastic Nash games with state-dependent noise. After establishing the asymptotic structure along with the positive semidefiniteness for...