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 ...
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...
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...
Jacob Goldberger, Sam T. Roweis, Geoffrey E. Hinto...
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...
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...