Reinforcement Learning for Multi-Agent Systems with Temporal Logic Specifications

Terashima, Keita; Kobayashi, Koichi; Yamashita, Yuh

Reinforcement Learning for Multi-Agent Systems with Temporal Logic Specifications

Terashima, Keita; Kobayashi, Koichi; Yamashita, Yuh

IEICE transactions on fundamentals of electronics communications and computer sciences, 2024, E107A(1), 31-37

Permalink : https://hdl.handle.net/2115/92468

このアイテムのアクセス数:108件（2026-01-14 16:32 集計）

閲覧可能ファイル

ファイル	フォーマット	サイズ	閲覧回数	説明
E107.A_2023KEP0016	pdf	1.79 MB	68

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

アクセス権	open access
URI	https://hdl.handle.net/2115/92468
タイトル	Reinforcement Learning for Multi-Agent Systems with Temporal Logic Specifications
著者	Terashima, Keita ; Kobayashi, Koichi ; Yamashita, Yuh
著者名 Terashima, Keita
e-Rad_Researcher 50452115 著者名 Kobayashi, Koichi
e-Rad_Researcher 90210426 著者名 Yamashita, Yuh
言語	英語
キーワード	multi-agent systems
	reinforcement learning
	linear temporal logic
	aggregator
	surveillance
発行日	2024-01-01
出版者	IEICE - Institute of the Electronics, Information and Communication Engineers
収録物名	IEICE transactions on fundamentals of electronics communications and computer sciences
巻(号)	E107A(1)
ページ	31-37
抄録	In a multi-agent system, it is important to consider a design method of cooperative actions in order to achieve a common goal. In this paper, we propose two novel multi-agent reinforcement learning methods, where the control specification is described by linear temporal logic formulas, which represent a common goal. First, we propose a simple solution method, which is directly extended from the single-agent case. In this method, there are some technical issues caused by the increase in the number of agents. Next, to overcome these technical issues, we propose a new method in which an aggregator is introduced. Finally, these two methods are compared by numerical simulations, with a surveillance problem as an example.
資源タイプ	学術雑誌論文
出版タイプ	Version of Record
権利情報	copyright©2024 IEICE
PISSN	0916-8508
関連情報 (isIdenticalTo)	出版社版DOI https://doi.org/10.1587/transfun.2023KEP0016