Explaining sequences of actions in multi-agent deep reinforcement learning models

This paper introduces a method to explain MADRL agents’ behaviors by abstracting their actions into high-level strategies. Particularly, a spatio-temporal neural network model is applied to encode the agents’ sequences of actions as memory episodes wherein an aggregating memory retrieval can general...

Full description

Saved in:

Bibliographic Details
Main Authors:	KHAING, Phyo Wai, GENG, Minghong, PATERIA, Shubham, SUBAGDJA, Budhitama, TAN, Ah-hwee
Format:	text
Language:	English
Published:	Institutional Knowledge at Singapore Management University 2024
Subjects:	Multi-agent Deep Reinforcement Learning; Explainable Artificial Intelligence; Sequential Decision Making Databases and Information Systems
Online Access:	https://ink.library.smu.edu.sg/sis_research/9783 https://ink.library.smu.edu.sg/context/sis_research/article/10783/viewcontent/p2537__1_.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-10783
record_format	dspace
spelling	sg-smu-ink.sis_research-107832024-12-16T02:04:34Z Explaining sequences of actions in multi-agent deep reinforcement learning models KHAING, Phyo Wai GENG, Minghong PATERIA, Shubham SUBAGDJA, Budhitama TAN, Ah-hwee This paper introduces a method to explain MADRL agents’ behaviors by abstracting their actions into high-level strategies. Particularly, a spatio-temporal neural network model is applied to encode the agents’ sequences of actions as memory episodes wherein an aggregating memory retrieval can generalize them into a concise abstract representation of collective strategies. To assess the effectiveness of our method, we applied it to explain the actions of QMIX MADRL agents playing a StarCraft Multi-agent Challenge (SMAC) video game. A user study on the perceived explainability of the extracted strategies indicates that our method can provide comprehensible explanations at various levels of granularity. 2024-05-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9783 https://ink.library.smu.edu.sg/context/sis_research/article/10783/viewcontent/p2537__1_.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 Multi-agent Deep Reinforcement Learning; Explainable Artificial Intelligence; Sequential Decision Making 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	Multi-agent Deep Reinforcement Learning; Explainable Artificial Intelligence; Sequential Decision Making Databases and Information Systems
spellingShingle	Multi-agent Deep Reinforcement Learning; Explainable Artificial Intelligence; Sequential Decision Making Databases and Information Systems KHAING, Phyo Wai GENG, Minghong PATERIA, Shubham SUBAGDJA, Budhitama TAN, Ah-hwee Explaining sequences of actions in multi-agent deep reinforcement learning models
description	This paper introduces a method to explain MADRL agents’ behaviors by abstracting their actions into high-level strategies. Particularly, a spatio-temporal neural network model is applied to encode the agents’ sequences of actions as memory episodes wherein an aggregating memory retrieval can generalize them into a concise abstract representation of collective strategies. To assess the effectiveness of our method, we applied it to explain the actions of QMIX MADRL agents playing a StarCraft Multi-agent Challenge (SMAC) video game. A user study on the perceived explainability of the extracted strategies indicates that our method can provide comprehensible explanations at various levels of granularity.
format	text
author	KHAING, Phyo Wai GENG, Minghong PATERIA, Shubham SUBAGDJA, Budhitama TAN, Ah-hwee
author_facet	KHAING, Phyo Wai GENG, Minghong PATERIA, Shubham SUBAGDJA, Budhitama TAN, Ah-hwee
author_sort	KHAING, Phyo Wai
title	Explaining sequences of actions in multi-agent deep reinforcement learning models
title_short	Explaining sequences of actions in multi-agent deep reinforcement learning models
title_full	Explaining sequences of actions in multi-agent deep reinforcement learning models
title_fullStr	Explaining sequences of actions in multi-agent deep reinforcement learning models
title_full_unstemmed	Explaining sequences of actions in multi-agent deep reinforcement learning models
title_sort	explaining sequences of actions in multi-agent deep reinforcement learning models
publisher	Institutional Knowledge at Singapore Management University
publishDate	2024
url	https://ink.library.smu.edu.sg/sis_research/9783 https://ink.library.smu.edu.sg/context/sis_research/article/10783/viewcontent/p2537__1_.pdf
_version_	1819113137642668032

Explaining sequences of actions in multi-agent deep reinforcement learning models

Similar Items