This paper develops a generalized apprenticeship learning protocol for reinforcementlearning agents with access to a teacher who provides policy traces (transition and reward obse...
Thomas J. Walsh, Kaushik Subramanian, Michael L. L...
We present a simple, agnostic active learning algorithm that works for any hypothesis class of bounded VC dimension, and any data distribution. Our algorithm extends a scheme of C...
Abstract. We investigate the generalization behavior of sequential prediction (online) algorithms, when data are generated from a probability distribution. Using some newly develop...
We present an improvement of Noviko 's perceptron convergence theorem. Reinterpreting this mistakebound as a margindependent sparsity guarantee allows us to give a PAC{style ...
Thore Graepel, Ralf Herbrich, Robert C. Williamson
In this paper we eliminate the need for parameter estimation associated with the set covering machine (SCM) by directly minimizing generalization error bounds. Firstly, we consider...