University of Limerick Institutional Repository

Collaborative reinforcement learning of autonomic behaviour

DSpace Repository

Show simple item record

dc.contributor.author Dowling, Jim
dc.contributor.author Cunningham, Raymond
dc.contributor.author Curran, Eoin
dc.contributor.author Cahill, Vinny
dc.date.accessioned 2011-07-15T10:21:24Z
dc.date.available 2011-07-15T10:21:24Z
dc.date.issued 2004
dc.identifier.uri http://hdl.handle.net/10344/1105
dc.description peer-reviewed
dc.description.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. en_US
dc.description.sponsorship SFI
dc.language.iso eng en_US
dc.publisher IEEE Computer Society en_US
dc.subject collaborative reinforcement learning en_US
dc.title Collaborative reinforcement learning of autonomic behaviour en_US
dc.type Conference item en_US
dc.type.supercollection all_ul_research en_US
dc.type.supercollection ul_published_reviewed en_US
dc.type.restriction none en


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Browse

My Account

Statistics