We present a new algorithm, GM-Sarsa(0), for finding approximate solutions to multiple-goal reinforcement learning problems that are modeled as composite Markov decision processe...
Nonnegative matrix factorization (NMF) is a widely-used tool for obtaining low-rank approximations of nonnegative data such as digital images, audio signals, textual data, financ...
One of the most important applications of the Asymmetric Hamiltonian Path Problem is in scheduling. In this paper we describe a variant of this problem, and develop both a mathemat...
The implementation of collapsed Gibbs samplers for non-parametric Bayesian models is non-trivial, requiring considerable book-keeping. Goldwater et al. (2006a) presented an approx...
Phil Blunsom, Trevor Cohn, Sharon Goldwater, Mark ...
We develop a new mathematical model for describing a dynamical system at limited resolution (or finite scale), and we give precise meaning to the notion of a dynamical system havi...