908 search results - page 102 / 182 » Stochastic Finite Learning |
130
click to vote
ICML
2010
IEEE
15 years 3 months ago
2010
IEEE
We present the first temporal-difference learning algorithm for off-policy control with unrestricted linear function approximation whose per-time-step complexity is linear in the ...
129
click to vote
ICDM
2007
IEEE
15 years 4 months ago
2007
IEEE
For applications with consecutive incoming training examples, on-line learning has the potential to achieve a likelihood as high as off-line learning without scanning all availabl...
110
click to vote
NIPS
2004
15 years 4 months ago
2004
In this paper we propose a novel method for learning a Mahalanobis distance measure to be used in the KNN classification algorithm. The algorithm directly maximizes a stochastic v...
129
click to vote
IJCAI
2003
15 years 4 months ago
2003
We investigate the problem of non-covariant behavior of policy gradient reinforcement learning algorithms. The policy gradient approach is amenable to analysis by information geom...
127
click to vote
CVPR
2008
IEEE
16 years 4 months ago
2008
IEEE
Given a finite number of data points sampled from a low-dimensional manifold embedded in a high dimensional space together with the parameter vectors for a subset of the data poin...