Proposal of a method of effective teamformation using dynamic reorganization and its evaluation

Ryota Katayanagi, Toshiharu Sugawara

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We propose an effective method of dynamic reorganization using reinforcement learning for the team formation in multi-agent systems (MAS). A task in MAS usually consists of a number of subtasks that require their own resources, and it has to be processed in the appropriate team whose agents have the sufficient resources. The resources required for tasks are often unknown a priori and it is also unknown whether their organization is appropriate to form teams for the given tasks or not. Therefore, their organization should be adopted according to the environment where agents are deployed. In this paper, we investigated how the structures of network and the number of tasks affect team formations of the agents. We will show that the utility and the success of the team formation is deeply affected by depth of the tree structure and number of tasks.

Original languageEnglish
Pages (from-to)76-85
Number of pages10
JournalTransactions of the Japanese Society for Artificial Intelligence
Volume26
Issue number1
DOIs
Publication statusPublished - 2011
Externally publishedYes

Fingerprint

Multi agent systems
Reinforcement learning

Keywords

  • Multi-agent system
  • Q-learning
  • Reorganization
  • Team formation

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

@article{f53239bc120140d6826f9842cd381398,
title = "Proposal of a method of effective teamformation using dynamic reorganization and its evaluation",
abstract = "We propose an effective method of dynamic reorganization using reinforcement learning for the team formation in multi-agent systems (MAS). A task in MAS usually consists of a number of subtasks that require their own resources, and it has to be processed in the appropriate team whose agents have the sufficient resources. The resources required for tasks are often unknown a priori and it is also unknown whether their organization is appropriate to form teams for the given tasks or not. Therefore, their organization should be adopted according to the environment where agents are deployed. In this paper, we investigated how the structures of network and the number of tasks affect team formations of the agents. We will show that the utility and the success of the team formation is deeply affected by depth of the tree structure and number of tasks.",
keywords = "Multi-agent system, Q-learning, Reorganization, Team formation",
author = "Ryota Katayanagi and Toshiharu Sugawara",
year = "2011",
doi = "10.1527/tjsai.26.76",
language = "English",
volume = "26",
pages = "76--85",
journal = "Transactions of the Japanese Society for Artificial Intelligence",
issn = "1346-0714",
publisher = "Japanese Society for Artificial Intelligence",
number = "1",

}

TY - JOUR

T1 - Proposal of a method of effective teamformation using dynamic reorganization and its evaluation

AU - Katayanagi, Ryota

AU - Sugawara, Toshiharu

PY - 2011

Y1 - 2011

N2 - We propose an effective method of dynamic reorganization using reinforcement learning for the team formation in multi-agent systems (MAS). A task in MAS usually consists of a number of subtasks that require their own resources, and it has to be processed in the appropriate team whose agents have the sufficient resources. The resources required for tasks are often unknown a priori and it is also unknown whether their organization is appropriate to form teams for the given tasks or not. Therefore, their organization should be adopted according to the environment where agents are deployed. In this paper, we investigated how the structures of network and the number of tasks affect team formations of the agents. We will show that the utility and the success of the team formation is deeply affected by depth of the tree structure and number of tasks.

AB - We propose an effective method of dynamic reorganization using reinforcement learning for the team formation in multi-agent systems (MAS). A task in MAS usually consists of a number of subtasks that require their own resources, and it has to be processed in the appropriate team whose agents have the sufficient resources. The resources required for tasks are often unknown a priori and it is also unknown whether their organization is appropriate to form teams for the given tasks or not. Therefore, their organization should be adopted according to the environment where agents are deployed. In this paper, we investigated how the structures of network and the number of tasks affect team formations of the agents. We will show that the utility and the success of the team formation is deeply affected by depth of the tree structure and number of tasks.

KW - Multi-agent system

KW - Q-learning

KW - Reorganization

KW - Team formation

UR - http://www.scopus.com/inward/record.url?scp=78650982150&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650982150&partnerID=8YFLogxK

U2 - 10.1527/tjsai.26.76

DO - 10.1527/tjsai.26.76

M3 - Article

AN - SCOPUS:78650982150

VL - 26

SP - 76

EP - 85

JO - Transactions of the Japanese Society for Artificial Intelligence

JF - Transactions of the Japanese Society for Artificial Intelligence

SN - 1346-0714

IS - 1

ER -