301 search results - page 1 / 61 » Approximate predictive state representations |
ATAL
2008
Springer
13 years 6 months ago
2008
Springer
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 ...
AAAI
2006
13 years 6 months ago
2006
Planning in partially-observable dynamical systems is a challenging problem, and recent developments in point-based techniques such as Perseus significantly improve performance as...
ICML
2008
IEEE
14 years 5 months ago
2008
IEEE
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...
AAAI
2006
13 years 6 months ago
2006
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...
ATAL
2010
Springer
13 years 5 months ago
2010
Springer
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 ...