OS21-4 Strategy Analysis of Multi-Agent Games Using Self-Organizing Map

Title:	OS21-4 Strategy Analysis of Multi-Agent Games Using Self-Organizing Map
Publication:	ICAROB2018
Volume:	23
Pages:	757-760
ISSN:	2188-7829
DOI:	10.5954/ICAROB.2018.OS21-4
Author(s):	Moeko Tominaga, Yasunori Takemura, Kazuo Ishii
Publication Date:	February 2, 2018
Keywords:	Strategy, Self-Organizing Map, team behavior, SOM
Abstract:	As technology develops, realization of a symbiotic society between human beings and robots sharing their environment has become one of most important subjects. For example, soccer is a multi-agent game that require strategies such as each members' position and defense. The behavior of a player changes depending on the game situation such as winning or losing, score gap, remaining time. The players may play offensive when their team is losing, or be defensive when their team is winning with minimum score difference. In this paper, human soccer game is observed and analyzed to determine how the state vector of each players affect team behavior. The team strategy is analyzed based on parameters such as the positions, the number players, score, time and actions of soccer robots using Self-Organizing Map(SOM)
PDF File:	https://alife-robotics.co.jp/members2018/icarob/data/html/data/OS_pdf/OS21/OS21-4.pdf
Copyright:	© The authors. This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited. See for details: https://creativecommons.org/licenses/by-nc/4.0/

HOME