908 search results - page 98 / 182 » Stochastic Finite Learning |
EUROCOLT
1995
Springer
14 years 14 days ago
1995
Springer
k. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multi...
ICML
2010
IEEE
13 years 6 months ago
2010
IEEE
POMDPs are the models of choice for reinforcement learning (RL) tasks where the environment cannot be observed directly. In many applications we need to learn the POMDP structure ...
NIPS
1998
13 years 10 months ago
1998
The Expectation Maximization EM algorithm is an iterative procedure for maximum likelihood parameter estimation from data sets with missing or hidden variables 2 . It has been app...
NIPS
1996
13 years 10 months ago
1996
In cellular telephone systems, an important problem is to dynamically allocate the communication resource channels so as to maximize service in a stochastic caller environment. Th...
ICML
1998
IEEE
14 years 9 months ago
1998
IEEE
Stochastic topological models, and hidden Markov models in particular, are a useful tool for robotic navigation and planning. In previous work we have shown how weak odometric dat...