301 search results - page 1 / 61 » Approximate predictive state representations |
ATAL
2008
Springer
13 years 11 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 10 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 10 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 10 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 10 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 ...