Please use this identifier to cite or link to this item:
Title: A multi-agent cooperative reinforcement learning model using a hierarchy of consultants, tutors and workers
Contributor(s): Abed-alguni, Bilal H (author); Chalup, Stephan K (author); Henskens, Frans A (author); Paul, David  (author)orcid 
Publication Date: 2015
Open Access: Yes
DOI: 10.1007/s40595-015-0045-xOpen Access Link
Handle Link:
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.
Publication Type: Journal Article
Source of Publication: Vietnam Journal of Computer Science, 2(4), p. 213-226
Publisher: SpringerOpen
Place of Publication: Germany
ISSN: 2196-8888
Field of Research (FOR): 080501 Distributed and Grid Systems
080101 Adaptive Agents and Intelligent Robotics
Socio-Economic Objective (SEO): 970108 Expanding Knowledge in the Information and Computing Sciences
Peer Reviewed: Yes
HERDC Category Description: C1 Refereed Article in a Scholarly Journal
Statistics to Oct 2018: Visitors: 648
Views: 656
Downloads: 0
Appears in Collections:Journal Article

Files in This Item:
3 files
File Description SizeFormat 
Show full item record

Page view(s)

checked on Dec 29, 2018
Google Media

Google ScholarTM



Items in Research UNE are protected by copyright, with all rights reserved, unless otherwise indicated.