Please use this identifier to cite or link to this item:
https://hdl.handle.net/1959.11/17940
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Abed-alguni, Bilal H | en |
dc.contributor.author | Chalup, Stephan K | en |
dc.contributor.author | Henskens, Frans A | en |
dc.contributor.author | Paul, David | en |
dc.date.accessioned | 2015-09-29T10:05:00Z | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | Vietnam Journal of Computer Science, 2(4), p. 213-226 | en |
dc.identifier.issn | 2196-8896 | en |
dc.identifier.issn | 2196-8888 | en |
dc.identifier.uri | https://hdl.handle.net/1959.11/17940 | - |
dc.description.abstract | The hierarchical organisation of distributed systems can provide an efficient decomposition for machine learning. This paper proposes an algorithm for cooperative policy construction for independent learners, named Q-learning with aggregation (QA-learning). The algorithm is based on a distributed hierarchical learning model and utilises three specialisations of agents: workers, tutors and consultants. The consultant agent incorporates the entire system in its problem space, which it decomposes into sub-problems that are assigned to the tutor and worker agents. The QA-learning algorithm aggregates the Q-tables of worker agents into a central repository managed by their tutor agent. Each tutor's Q-table is then incorporated into the consultant's Q-table, resulting in a Q-table for the entire problem. The algorithm was tested using a distributed hunter prey problem, and experimental results show that QA-learning converges to a solution faster than single agent Q-learning and some famous cooperative Q-learning algorithms. | en |
dc.language | en | en |
dc.publisher | SpringerOpen | en |
dc.relation.ispartof | Vietnam Journal of Computer Science | en |
dc.title | A multi-agent cooperative reinforcement learning model using a hierarchy of consultants, tutors and workers | en |
dc.type | Journal Article | en |
dc.identifier.doi | 10.1007/s40595-015-0045-x | en |
dcterms.accessRights | Gold | en |
dc.subject.keywords | Distributed and Grid Systems | en |
dc.subject.keywords | Adaptive Agents and Intelligent Robotics | en |
local.contributor.firstname | Bilal H | en |
local.contributor.firstname | Stephan K | en |
local.contributor.firstname | Frans A | en |
local.contributor.firstname | David | en |
local.subject.for2008 | 080501 Distributed and Grid Systems | en |
local.subject.for2008 | 080101 Adaptive Agents and Intelligent Robotics | en |
local.subject.seo2008 | 970108 Expanding Knowledge in the Information and Computing Sciences | en |
local.profile.school | School of Science and Technology | en |
local.profile.email | bilal.abedalguni@uon.edu.au | en |
local.profile.email | stephan.chalup@newcastle.edu.au | en |
local.profile.email | frans.henskens@newcastle.edu.au | en |
local.profile.email | dpaul4@une.edu.au | en |
local.output.category | C1 | en |
local.record.place | au | en |
local.record.institution | University of New England | en |
local.identifier.epublicationsrecord | une-20150721-142653 | en |
local.publisher.place | Germany | en |
local.format.startpage | 213 | en |
local.format.endpage | 226 | en |
local.peerreviewed | Yes | en |
local.identifier.volume | 2 | en |
local.identifier.issue | 4 | en |
local.access.fulltext | Yes | en |
local.contributor.lastname | Abed-alguni | en |
local.contributor.lastname | Chalup | en |
local.contributor.lastname | Henskens | en |
local.contributor.lastname | Paul | en |
dc.identifier.staff | une-id:dpaul4 | en |
local.profile.orcid | 0000-0002-2428-5667 | en |
local.profile.role | author | en |
local.profile.role | author | en |
local.profile.role | author | en |
local.profile.role | author | en |
local.identifier.unepublicationid | une:18150 | en |
dc.identifier.academiclevel | Academic | en |
dc.identifier.academiclevel | Academic | en |
dc.identifier.academiclevel | Academic | en |
local.title.maintitle | A multi-agent cooperative reinforcement learning model using a hierarchy of consultants, tutors and workers | en |
local.output.categorydescription | C1 Refereed Article in a Scholarly Journal | en |
local.search.author | Abed-alguni, Bilal H | en |
local.search.author | Chalup, Stephan K | en |
local.search.author | Henskens, Frans A | en |
local.search.author | Paul, David | en |
local.uneassociation | Unknown | en |
local.year.published | 2015 | en |
local.subject.for2020 | 460605 Distributed systems and algorithms | en |
local.subject.for2020 | 460604 Dependable systems | en |
local.subject.seo2020 | 280115 Expanding knowledge in the information and computing sciences | en |
local.codeupdate.date | 2022-02-09T13:48:33.046 | en |
local.codeupdate.eperson | dpaul4@une.edu.au | en |
local.codeupdate.finalised | true | en |
local.original.for2020 | 460601 Cloud computing | en |
local.original.for2020 | undefined | en |
local.original.for2020 | 460605 Distributed systems and algorithms | en |
local.original.for2020 | 460604 Dependable systems | en |
local.original.seo2020 | 280115 Expanding knowledge in the information and computing sciences | en |
Appears in Collections: | Journal Article |
Files in This Item:
File | Description | Size | Format |
---|
Items in Research UNE are protected by copyright, with all rights reserved, unless otherwise indicated.