945 search results - page 50 / 189 » Dialog Convergence and Learning |
COLT
2008
Springer
14 years 11 months ago
2008
Springer
Standard no-internal-regret (NIR) algorithms compute a fixed point of a matrix, and hence typically require O(n3 ) run time per round of learning, where n is the dimensionality of...
ICML
2008
IEEE
15 years 10 months ago
2008
IEEE
We consider the task of reinforcement learning in an environment in which rare significant events occur independently of the actions selected by the controlling agent. If these ev...
ISCIS
2003
Springer
15 years 2 months ago
2003
Springer
In this paper, we study an adaptive random search method based on continuous action-set learning automaton for solving stochastic optimization problems in which only the noisecorr...
NIPS
1996
14 years 11 months ago
1996
This paper compares three penalty terms with respect to the efficiency of supervised learning, by using first- and second-order learning algorithms. Our experiments showed that fo...
TSMC
1998
14 years 9 months ago
1998
— Parallel algorithms are presented for modules of learning automata with the objective of improving their speed of convergence without compromising accuracy. A general procedure...