181 search results - page 14 / 37 » On Policy Learning in Restricted Policy Spaces |
ICML
2002
IEEE
14 years 8 months ago
2002
IEEE
This paper addresses cost-sensitive classification in the setting where there are costs for measuring each attribute as well as costs for misclassification errors. We show how to ...
NIPS
2008
13 years 9 months ago
2008
Recently, fitted Q-iteration (FQI) based methods have become more popular due to their increased sample efficiency, a more stable learning process and the higher quality of the re...
ECML
2006
Springer
13 years 11 months ago
2006
Springer
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
JMLR
2006
13 years 7 months ago
2006
Policy search is a method for approximately solving an optimal control problem by performing a parametric optimization search in a given class of parameterized policies. In order ...
IJAIT
2008
13 years 7 months ago
2008
ion mechanism to create a representation of space consisting of the circular order of detected landmarks and the relative position of walls towards the agent's moving directio...