Collaborative reinforcement learning of autonomic behaviour.
Citation:
Jim Dowling, Raymond Cunningham, Eoin Curran, and Vinny Cahill., Collaborative reinforcement learning of autonomic behaviour., Proceedings 15th International Workshop on Database and Expert Systems Applications, 2004., 15th International Workshop on Database and Expert Systems Applications (DEXA '04), 30 Aug.-3 Sept, IEEE Computer Society Press, 2004, 700-704Download Item:
Abstract:
This paper introduces Collaborative Reinforcement
Learning (CRL), a coordination model for solving
system-wide optimisation problems in distributed systems
where there is no support for global state. In
CRL the autonomic properties of a distributed system
emerge from the coordination of individual agents solving
discrete optimisation problems using Reinforcement
Learning. In the context of an ad hoc routing protocol,
we show how system-wide optimisation in CRL can be
used to establish and maintain autonomic properties for
decentralised distributed systems.
Author's Homepage:
http://people.tcd.ie/vjcahillDescription:
PUBLISHED
Author: CAHILL, VINNY
Other Titles:
Proceedings 15th International Workshop on Database and Expert Systems Applications, 2004.15th International Workshop on Database and Expert Systems Applications (DEXA '04)
Publisher:
IEEE Computer Society PressType of material:
Conference PaperCollections
Availability:
Full text availableKeywords:
Computer ScienceMetadata
Show full item recordLicences: