995 search results - page 76 / 199 » Learning Useful Horn Approximations |
ICML
2000
IEEE
14 years 10 months ago
2000
IEEE
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...
IJCNN
2000
IEEE
14 years 2 months ago
2000
IEEE
We introduce an algorithm for learning a local metric to a continuous input space that measures distances in terms of relevance to the processing task. The relevance is defined a...
WSC
2008
14 years 8 days ago
2008
Reinforcement Learning (RL) is a simulation-based technique useful in solving Markov decision processes if their transition probabilities are not easily obtainable or if the probl...
NIPS
1994
13 years 11 months ago
1994
For many types of machine learning algorithms, one can compute the statistically optimal" way to select training data. In this paper, we review how optimal data selection tec...
ICRA
2009
IEEE
13 years 7 months ago
2009
IEEE
Contextual reasoning through graphical models such as Markov Random Fields often show superior performance against local classifiers in many domains. Unfortunately, this performanc...