Transformer Based Multi-Agent Framework

Hu, S; Zhu, F; Chang, X; Liang, X

Transformer Based Multi-Agent Framework

Hu, S Zhu, F Chang, X

Liang, X

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2021 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2021, 2021, 00, pp. 1-2
Issue Date:: 2021-01-01

Closed Access

	Filename	Description	Size
	Transformer_Based_Multi-Agent_Framework.pdf	Published version	103.75 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Hu, S
dc.contributor.author	Zhu, F
dc.contributor.author	Chang, X https://orcid.org/0000-0002-7778-8807
dc.contributor.author	Liang, X
dc.date	2021-07-05
dc.date.accessioned	2022-06-11T22:37:17Z
dc.date.available	2022-06-11T22:37:17Z
dc.date.issued	2021-01-01
dc.identifier.citation	2021 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2021, 2021, 00, pp. 1-2
dc.identifier.isbn	9781665449892
dc.identifier.uri	http://hdl.handle.net/10453/158110
dc.description.abstract	We present a Transformer-like agent to learn the policy of multi-agent cooperation tasks, which is a breakthrough for traditional RNN-based multi-agent models that need to be retrained for each task. Our model can handle various input and output with strong transferability and can parallel tackle different tasks. Besides, We are the first to successfully utilize transformer into a recurrent architecture, providing insight on stabilizing transformers in recurrent RL tasks.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	2021 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2021
dc.relation.ispartof	2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
dc.relation.isbasedon	10.1109/ICMEW53276.2021.9455984
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Transformer Based Multi-Agent Framework
dc.type	Conference Proceeding
utslib.citation.volume	00
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
dc.date.updated	2022-06-11T22:37:16Z
pubs.finish-date	2021-07-09
pubs.publication-status	Published
pubs.start-date	2021-07-05
pubs.volume	00

Abstract:

We present a Transformer-like agent to learn the policy of multi-agent cooperation tasks, which is a breakthrough for traditional RNN-based multi-agent models that need to be retrained for each task. Our model can handle various input and output with strong transferability and can parallel tackle different tasks. Besides, We are the first to successfully utilize transformer into a recurrent architecture, providing insight on stabilizing transformers in recurrent RL tasks.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/158110