252 search results - page 31 / 51 » Learning Partially Observable Action Models: Efficient Algor... |
135
Voted
ICMLA
2004
15 years 4 months ago
2004
Predictive state representation (PSR) models for controlled dynamical systems have recently been proposed as an alternative to traditional models such as partially observable Mark...
114
click to vote
ICRA
2010
IEEE
15 years 1 months ago
2010
IEEE
Abstract— We propose a planning algorithm that allows usersupplied domain knowledge to be exploited in the synthesis of information feedback policies for systems modeled as parti...
142
Voted
ICML
2009
IEEE
16 years 3 months ago
2009
IEEE
Many machine learning algorithms can be formulated as a generalized eigenvalue problem. One major limitation of such formulation is that the generalized eigenvalue problem is comp...
117
click to vote
ICML
2006
IEEE
16 years 3 months ago
2006
IEEE
We formalize the associative bandit problem framework introduced by Kaelbling as a learning-theory problem. The learning environment is modeled as a k-armed bandit where arm payof...
127
Voted
AAAI
2010
15 years 4 months ago
2010
Partially-observable Markov decision processes (POMDPs) provide a powerful model for sequential decision-making problems with partially-observed state and are known to have (appro...