Multi-agent task allocation based on the learning of managers and local preference selections

Yuka Ishihara, Toshiharu Sugawara*

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

2 Citations (Scopus)


This paper discusses an adaptive distributed allocation method in which agents individually learn strategies for preferences to decide on the rank of tasks which they want to be allocated by a manager. In a distributed edge-computing environment, multiple managers that control the provision of a variety of services requested from different locations have to allocate the corresponding tasks to appropriate agents, which are usually programs developed by different companies. In our proposed method, each agent learns which manager will allocate tasks it performs well and how to declare its preferred tasks. We experimentally evaluated the proposed learning method and showed that agents using the proposed method could effectively execute requested tasks and could adapt to changes in patterns of the requested tasks.

Original languageEnglish
Pages (from-to)675-684
Number of pages10
JournalProcedia Computer Science
Publication statusPublished - 2020
Event24th KES International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2020 - Virtual Online
Duration: 2020 Sept 162020 Sept 18


  • Distributed task allocation
  • Edge computing
  • Multi-agent systems
  • Reinforcement learning

ASJC Scopus subject areas

  • Computer Science(all)


Dive into the research topics of 'Multi-agent task allocation based on the learning of managers and local preference selections'. Together they form a unique fingerprint.

Cite this