Predictive state representations (PSRs) are models that represent the state of a dynamical system as a set of predictions about future events. The existing work with PSRs focuses ...
Britton Wolfe, Michael R. James, Satinder P. Singh
Planning in partially-observable dynamical systems is a challenging problem, and recent developments in point-based techniques such as Perseus significantly improve performance as...
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...
We discuss the problem of finding a good state representation in stochastic systems with observations. We develop a duality theory that generalizes existing work in predictive sta...
Christopher Hundt, Prakash Panangaden, Joelle Pine...
A central problem in artificial intelligence is to choose actions to maximize reward in a partially observable, uncertain environment. To do so, we must learn an accurate model of ...