3523 search results - page 525 / 705 » Feature interaction in policies |
166
click to vote
NOMS
2008
IEEE
16 years 1 months ago
2008
IEEE
— Wireless networks have become a ubiquitous reality and ever more surround our everyday activities. They form and disappear around us spontaneously and have become new means for...
147
click to vote
ATAL
2007
Springer
16 years 24 days ago
2007
Springer
In this paper, we discuss the use of Targeted Trajectory Distribution Markov Decision Processes (TTD-MDPs)—a variant of MDPs in which the goal is to realize a specified distrib...
191
click to vote
HPDC
2006
IEEE
16 years 20 days ago
2006
IEEE
Consider a workload in which massively parallel tasks that require large resource pools are interleaved with short tasks that require fast response but consume fewer resources. We...
196
click to vote
ICAC
2006
IEEE
16 years 20 days ago
2006
IEEE
— Recent advances have demonstrated the potential benefits of coordinated management of thermal load in data centers, including reduced cooling costs and improved resistance to ...
241
click to vote
BERTINORO
2005
Springer
16 years 5 days ago
2005
Springer
Abstract. This paper describes the application of a decentralised coordination algorithm, called Collaborative Reinforcement Learning (CRL), to two different distributed system pr...