Efficiently learning linear-linear exponential family predictive representations of state

@inproceedings{Wingate2008EfficientlyLL,
title={Efficiently learning linear-linear exponential family predictive representations of state},
author={David Wingate and Satinder P. Singh},
booktitle={ICML},
year={2008}
}

Exponential Family PSR (EFPSR) models capture stochastic dynamical systems by representing state as the parameters of an exponential family distribution over a shortterm window of future observations. They are appealing from a learning perspective because they are fully observed (meaning expressions for maximum likelihood do not involve hidden quantities), but are still expressive enough to both capture existing models and predict new models. While maximum-likelihood learning algorithms for… CONTINUE READING