GS3-3 Efficient collective search by agents that remember failures

Title:	GS3-3 Efficient collective search by agents that remember failures
Publication:	ICAROB2018
Volume:	23
Pages:	93-95
ISSN:	2188-7829
DOI:	10.5954/ICAROB.2018.GS3-3
Author(s):	Masao Kubo, Nhuhai Phung, Hiroshi Sato
Publication Date:	February 2, 2018
Keywords:	swarm intelligence, machine learning, complex systems
Abstract:	The BRT agent is an algorithm that can find appropriate collective behaviors by changing the agreement contents in a trial and error manner. Computer experiments show that it is necessary to change the agreement contents the number of times that is proportional to the square of the number of choices on average. In this paper, we attempted to shorten this search time by introducing an agent that memorizes behaviors that were not able to achieve the expected effect of what we executed. As a result, we found that search time can be improved by just mixing a few this taboo list agents.
PDF File:	https://alife-robotics.co.jp/members2018/icarob/data/html/data/GS_pdf/GS3/GS3-3.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/