We introduce the controlled predictive linearGaussian model (cPLG), a model that uses predictive state to model discrete-time dynamical systems with real-valued observations and v...
Abstract. Considering one-dimensional continuum-armed bandit problems, we propose an improvement of an algorithm of Kleinberg and a new set of conditions which give rise to improve...
In this report, we consider the problem of real-time transmission scheduling over time-varying channels. We first formulate the transmission scheduling problem as a Markov decisio...
We present a novel semi-supervised training algorithm for learning dependency parsers. By combining a supervised large margin loss with an unsupervised least squares loss, a discr...
Recent developments in the area of reinforcement learning have yielded a number of new algorithms for the prediction and control of Markovian environments. These algorithms,includ...
Tommi Jaakkola, Michael I. Jordan, Satinder P. Sin...