301 search results - page 28 / 61 » Approximate predictive state representations |
ICML
2010
IEEE
13 years 9 months ago
2010
IEEE
We present the first temporal-difference learning algorithm for off-policy control with unrestricted linear function approximation whose per-time-step complexity is linear in the ...
ICANN
2009
Springer
14 years 1 months ago
2009
Springer
Recurrent neural networks serve as black-box models for nonlinear dynamical systems identification and time series prediction. Training of recurrent networks typically minimizes t...
ICML
2007
IEEE
14 years 9 months ago
2007
IEEE
The supremacy of n-gram models in statistical language modelling has recently been challenged by parametric models that use distributed representations to counteract the difficult...
ICCV
2003
IEEE
14 years 10 months ago
2003
IEEE
Within this paper a new framework for Bayesian tracking is presented, which approximates the posterior distribution at multiple resolutions. We propose a tree-based representation...
ATAL
2003
Springer
14 years 2 months ago
2003
Springer
Traditional goal-oriented approaches to building intelligent agents only consider absolute satisfaction of goals. However, in continuous domains there may be many instances in whi...