1997 search results - page 27 / 400 » On the convergence of Hill's method |
ECML
2004
Springer
14 years 1 months ago
2004
Springer
Although tabular reinforcement learning (RL) methods have been proved to converge to an optimal policy, the combination of particular conventional reinforcement learning techniques...
ICASSP
2011
IEEE
13 years 6 days ago
2011
IEEE
In the independent component analysis, polynomial functions of higher order statistics are often used as cost functions. However, such cost functions usually have many local minim...
MOC
2000
13 years 8 months ago
2000
This paper proposes an additive Schwarz method for variational inequalities and their approximations by finite element methods. The Schwarz domain decomposition method is proved to...
IJIT
2004
13 years 9 months ago
2004
Since the presentation of the backpropagation algorithm, a vast variety of improvements of the technique for training a feed forward neural networks have been proposed. This articl...
ICRA
2010
IEEE
13 years 7 months ago
2010
IEEE
— The priorities of a climbing legged robot are to maintain a grasp on its climbing surface and to climb efficiently against the force of gravity. These priorities profoundly co...