Sciweavers

437 search results - page 53 / 88
» Policy Gradient Critics
Sort
View
CORR
2008
Springer
88views Education» more  CORR 2008»
13 years 9 months ago
The Korrontea Data Modeling
Needs of multimedia systems evolved due to the evolution of their architecture which is now distributed into heterogeneous contexts. A critical issue lies in the fact that they ha...
Emmanuel Bouix, Philippe Roose, Marc Dalmau
ML
2002
ACM
143views Machine Learning» more  ML 2002»
13 years 8 months ago
A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov Decision Processes
An issue that is critical for the application of Markov decision processes MDPs to realistic problems is how the complexity of planning scales with the size of the MDP. In stochas...
Michael J. Kearns, Yishay Mansour, Andrew Y. Ng
ICML
2005
IEEE
14 years 9 months ago
Relating reinforcement learning performance to classification performance
We prove a quantitative connection between the expected sum of rewards of a policy and binary classification performance on created subproblems. This connection holds without any ...
John Langford, Bianca Zadrozny
DASFAA
2009
IEEE
151views Database» more  DASFAA 2009»
14 years 3 months ago
The Challenge of Assuring Data Trustworthiness
Abstract. With the increased need of data sharing among multiple organizations, such as government organizations, financial corporations, medical hospitals and academic institution...
Elisa Bertino, Chenyun Dai, Murat Kantarcioglu
COMPSAC
2009
IEEE
14 years 3 months ago
On Information Flow Forensics in Business Application Scenarios
To-date, security analysis techniques focus on the explicit access to data, thereby neglecting information flows happening over covert channels. As a result, critical business so...
Claus Wonnemann, Rafael Accorsi, Günter M&uum...