47 search results - page 6 / 10 » Norm optimal Cross-Coupled Iterative Learning Control |
ICONIP
2009
14 years 7 months ago
2009
Reinforcement learning induces non-stationarity at several levels. Adaptation to non-stationary environments is of course a desired feature of a fair RL algorithm. Yet, even if the...
ICML
1996
IEEE
15 years 10 months ago
1996
IEEE
Some of the most successful recent applications of reinforcement learning have used neural networks and the TD algorithm to learn evaluation functions. In this paper, we examine t...
83
Voted
CORR
2011
Springer
14 years 1 months ago
2011
Springer
Abstract—Coping with outliers contaminating dynamical processes is of major importance in various applications because mismatches from nominal models are not uncommon in practice...
ICML
2007
IEEE
15 years 10 months ago
2007
IEEE
We propose a method for the classification of matrices. We use a linear classifier with a novel regularization scheme based on the spectral 1-norm of its coefficient matrix. The s...
ESSMAC
2003
Springer
15 years 2 months ago
2003
Springer
Abstract. We consider a linear system, such as an estimator or a controller, in which several signals are transmitted over wireless communication channels. With the coding and medi...