3502 search results - page 217 / 701 » From Machine Learning to Machine Reasoning |
166
click to vote
ICML
1995
IEEE
16 years 7 months ago
1995
IEEE
The success ofreinforcement learninginpractical problems depends on the ability to combine function approximation with temporal di erence methods such as value iteration. Experime...
159
click to vote
NIPS
2007
15 years 8 months ago
2007
This paper1 explores the use of a Maximal Average Margin (MAM) optimality principle for the design of learning algorithms. It is shown that the application of this risk minimizati...
164
click to vote
COLT
2003
Springer
15 years 11 months ago
2003
Springer
We consider three natural models of random logarithmic depth decision trees over Boolean variables. We give an efficient algorithm that for each of these models learns all but an ...
184
click to vote
ICML
2008
IEEE
16 years 7 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...
181
click to vote
ICML
2000
IEEE
15 years 11 months ago
2000
IEEE
The reinforcement learning problem can be decomposed into two parallel types of inference: (i) estimating the parameters of a model for the underlying process; (ii) determining be...