File(s) under permanent embargo
Self-organisation in an agent network via multiagent Q-learning
conference contribution
posted on 2023-05-23, 14:46 authored by Ye, D, Zhang, M, Quan BaiQuan Bai, Ito, TIn this paper, a decentralised self-organisation mechanism in an agent network is proposed. The aim of this mechanism is to achieve efficient task allocation in the agent network via dynamically altering the structural relations among agents, i.e. changing the underlying network structure. The mechanism enables agents in the network to reason with whom to adapt relations and to learn how to adapt relations by using only local information. The local information is accumulated from agents' historical interactions with others. The proposed mechanism is evaluated through a comparison with a centralised allocation method and the K-Adapt method. Experimental results demonstrate the decent performance of the proposed mechanism in terms of several evaluation criteria.
History
Publication title
Proceedings of the 11th International Workshop on Knowledge Management and Acquisition for Smart Systems and Services (PKAW 2010)Volume
6232Pagination
14-26ISBN
978-3-642-15036-4Department/School
School of Information and Communication TechnologyPublisher
Springer NaturePlace of publication
SwitzerlandEvent title
11th International Workshop on Knowledge Management and Acquisition for Smart Systems and Services (PKAW 2010)Event Venue
Daegue, KoreaDate of Event (Start Date)
2010-08-20Date of Event (End Date)
2010-09-03Rights statement
Copyright 2010 Springer-Verlag Berlin HeidelbergRepository Status
- Restricted