246 search results - page 3 / 50 » Approximate Predictive Representations of Partially Observab... |
AAAI
2006
13 years 7 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 7 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 ...
FLAIRS
2008
13 years 8 months ago
2008
Current studies have demonstrated that the representational power of predictive state representations (PSRs) is at least equal to the one of partially observable Markov decision p...
AAAI
2006
13 years 7 months ago
2006
We present tractable, exact algorithms for learning actions' effects and preconditions in partially observable domains. Our algorithms maintain a propositional logical repres...
JAIR
2000
13 years 5 months ago
2000
Partially observable Markov decision processes (POMDPs) provide an elegant mathematical framework for modeling complex decision and planning problems in stochastic domains in whic...