Advanced Double Layered Multi-Agent Systems Based on A3C in Real-Time Path Planning

In this paper, we propose an advanced double layered multi-agent system to reduce learning time, expressing a state space using a 2D grid. This system is based on asynchronous advantage actor-critic systems (A3C) and reduces the state space that agents need to consider by hierarchically expressing a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Dajeong Lee, Junoh Kim, Kyungeun Cho, Yunsick Sung
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	asynchronous advantage actor-critic multi-agent system simulation framework Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/21379be50307415bab637cd1756dbbfc
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:21379be50307415bab637cd1756dbbfc
record_format	dspace
spelling	oai:doaj.org-article:21379be50307415bab637cd1756dbbfc2021-11-25T17:24:26ZAdvanced Double Layered Multi-Agent Systems Based on A3C in Real-Time Path Planning10.3390/electronics102227622079-9292https://doaj.org/article/21379be50307415bab637cd1756dbbfc2021-11-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/22/2762https://doaj.org/toc/2079-9292In this paper, we propose an advanced double layered multi-agent system to reduce learning time, expressing a state space using a 2D grid. This system is based on asynchronous advantage actor-critic systems (A3C) and reduces the state space that agents need to consider by hierarchically expressing a 2D grid space and determining actions. Specifically, the state space is expressed in the upper and lower layers. Based on the learning results using A3C in the lower layer, the upper layer makes decisions without additional learning, and accordingly, the total learning time can be reduced. Our method was verified experimentally using a virtual autonomous surface vehicle simulator. It reduced the learning time required to reach a 90% goal achievement rate by 7.1% compared to the conventional double layered A3C. In addition, the goal achievement by the proposed method was 18.86% higher than that of the traditional double layered A3C over 20,000 learning episodes.Dajeong LeeJunoh KimKyungeun ChoYunsick SungMDPI AGarticleasynchronous advantage actor-criticmulti-agent systemsimulation frameworkElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2762, p 2762 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	asynchronous advantage actor-critic multi-agent system simulation framework Electronics TK7800-8360
spellingShingle	asynchronous advantage actor-critic multi-agent system simulation framework Electronics TK7800-8360 Dajeong Lee Junoh Kim Kyungeun Cho Yunsick Sung Advanced Double Layered Multi-Agent Systems Based on A3C in Real-Time Path Planning
description	In this paper, we propose an advanced double layered multi-agent system to reduce learning time, expressing a state space using a 2D grid. This system is based on asynchronous advantage actor-critic systems (A3C) and reduces the state space that agents need to consider by hierarchically expressing a 2D grid space and determining actions. Specifically, the state space is expressed in the upper and lower layers. Based on the learning results using A3C in the lower layer, the upper layer makes decisions without additional learning, and accordingly, the total learning time can be reduced. Our method was verified experimentally using a virtual autonomous surface vehicle simulator. It reduced the learning time required to reach a 90% goal achievement rate by 7.1% compared to the conventional double layered A3C. In addition, the goal achievement by the proposed method was 18.86% higher than that of the traditional double layered A3C over 20,000 learning episodes.
format	article
author	Dajeong Lee Junoh Kim Kyungeun Cho Yunsick Sung
author_facet	Dajeong Lee Junoh Kim Kyungeun Cho Yunsick Sung
author_sort	Dajeong Lee
title	Advanced Double Layered Multi-Agent Systems Based on A3C in Real-Time Path Planning
title_short	Advanced Double Layered Multi-Agent Systems Based on A3C in Real-Time Path Planning
title_full	Advanced Double Layered Multi-Agent Systems Based on A3C in Real-Time Path Planning
title_fullStr	Advanced Double Layered Multi-Agent Systems Based on A3C in Real-Time Path Planning
title_full_unstemmed	Advanced Double Layered Multi-Agent Systems Based on A3C in Real-Time Path Planning
title_sort	advanced double layered multi-agent systems based on a3c in real-time path planning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/21379be50307415bab637cd1756dbbfc
work_keys_str_mv	AT dajeonglee advanceddoublelayeredmultiagentsystemsbasedona3cinrealtimepathplanning AT junohkim advanceddoublelayeredmultiagentsystemsbasedona3cinrealtimepathplanning AT kyungeuncho advanceddoublelayeredmultiagentsystemsbasedona3cinrealtimepathplanning AT yunsicksung advanceddoublelayeredmultiagentsystemsbasedona3cinrealtimepathplanning
_version_	1718412395774214144

Advanced Double Layered Multi-Agent Systems Based on A3C in Real-Time Path Planning

Ejemplares similares