259 search results - page 17 / 52 » Reinforcement Learning with the Use of Costly Features |
ECML
2004
Springer
14 years 3 months ago
2004
Springer
Abstract. We present first experiments using Support Vector Regression as function approximator for an on-line, sarsa-like reinforcement learner. To overcome the batch nature of S...
INFOCOM
2005
IEEE
14 years 3 months ago
2005
IEEE
Abstract— Protocols for distributed hash tables (DHTs) incorporate features to achieve low latency for lookup requests in the face of churn, continuous changes in membership. The...
NIPS
1993
13 years 11 months ago
1993
Dynamic programming provides a methodology to develop planners and controllers for nonlinear systems. However, general dynamic programming is computationally intractable. We have ...
COLING
2008
13 years 11 months ago
2008
It is difficult to identify sentence importance from a single point of view. In this paper, we propose a learning-based approach to combine various sentence features. They are cat...
ICIP
2010
IEEE
13 years 8 months ago
2010
IEEE
This paper presents the combined use of gradient and mutual information for infrared and intensity templates matching. We propose to joint: (i) feature matching in a multiresoluti...