Scaling up multi-agent reinforcement learning in complex domains

TD-FALCON (Temporal Difference - Fusion Architecture for Learning, COgnition, and Navigation) is a class of self-organizing neural networks that incorporates Temporal Difference (TD) methods for real-time reinforcement learning. In this paper, we present two strategies, i.e. policy sharing and neigh...

Full description

Saved in:

Bibliographic Details
Main Authors:	XIAO, Dan, TAN, Ah-hwee
Format:	text
Language:	English
Published:	Institutional Knowledge at Singapore Management University 2008
Subjects:	Databases and Information Systems
Online Access:	https://ink.library.smu.edu.sg/sis_research/6798 https://ink.library.smu.edu.sg/context/sis_research/article/7801/viewcontent/Scaling_Up_IAT08.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Singapore Management University
Language:	English

id	sg-smu-ink.sis_research-7801
record_format	dspace
spelling	sg-smu-ink.sis_research-78012022-01-27T08:34:13Z Scaling up multi-agent reinforcement learning in complex domains XIAO, Dan TAN, Ah-hwee TD-FALCON (Temporal Difference - Fusion Architecture for Learning, COgnition, and Navigation) is a class of self-organizing neural networks that incorporates Temporal Difference (TD) methods for real-time reinforcement learning. In this paper, we present two strategies, i.e. policy sharing and neighboring-agent mechanism, to further improve the learning efficiency of TD-FALCON in complex multi-agent domains. Through experiments on a traffic control problem domain and the herding task, we demonstrate that those strategies enable TD-FALCON to remain functional and adaptable in complex multi-agent domains 2008-12-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6798 info:doi/10.1109/WIIAT.2008.259 https://ink.library.smu.edu.sg/context/sis_research/article/7801/viewcontent/Scaling_Up_IAT08.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems
institution	Singapore Management University
building	SMU Libraries
continent	Asia
country	Singapore Singapore
content_provider	SMU Libraries
collection	InK@SMU
language	English
topic	Databases and Information Systems
spellingShingle	Databases and Information Systems XIAO, Dan TAN, Ah-hwee Scaling up multi-agent reinforcement learning in complex domains
description	TD-FALCON (Temporal Difference - Fusion Architecture for Learning, COgnition, and Navigation) is a class of self-organizing neural networks that incorporates Temporal Difference (TD) methods for real-time reinforcement learning. In this paper, we present two strategies, i.e. policy sharing and neighboring-agent mechanism, to further improve the learning efficiency of TD-FALCON in complex multi-agent domains. Through experiments on a traffic control problem domain and the herding task, we demonstrate that those strategies enable TD-FALCON to remain functional and adaptable in complex multi-agent domains
format	text
author	XIAO, Dan TAN, Ah-hwee
author_facet	XIAO, Dan TAN, Ah-hwee
author_sort	XIAO, Dan
title	Scaling up multi-agent reinforcement learning in complex domains
title_short	Scaling up multi-agent reinforcement learning in complex domains
title_full	Scaling up multi-agent reinforcement learning in complex domains
title_fullStr	Scaling up multi-agent reinforcement learning in complex domains
title_full_unstemmed	Scaling up multi-agent reinforcement learning in complex domains
title_sort	scaling up multi-agent reinforcement learning in complex domains
publisher	Institutional Knowledge at Singapore Management University
publishDate	2008
url	https://ink.library.smu.edu.sg/sis_research/6798 https://ink.library.smu.edu.sg/context/sis_research/article/7801/viewcontent/Scaling_Up_IAT08.pdf
_version_	1770576070931644416

Scaling up multi-agent reinforcement learning in complex domains

Similar Items