ATSIS : achieving the ad hoc teamwork by sub-task inference and selection

In an ad hoc teamwork setting, the team needs to coordinate their activities to perform a task without prior agreement on how to achieve it. The ad hoc agent cannot communicate with its teammates but it can observe their behaviour and plan accordingly. To do so, the existing approaches rely on the t...

Full description

Saved in:
Bibliographic Details
Main Authors: Chen, Shuo, Andrejczuk, Ewa, Irissappane, Athirai Aravazhi, Zhang, Jie
Other Authors: School of Computer Science and Engineering
Format: Conference or Workshop Item
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/141012
http://www.ijcai.org
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-141012
record_format dspace
spelling sg-ntu-dr.10356-1410122020-06-04T07:22:32Z ATSIS : achieving the ad hoc teamwork by sub-task inference and selection Chen, Shuo Andrejczuk, Ewa Irissappane, Athirai Aravazhi Zhang, Jie School of Computer Science and Engineering School of Electrical and Electronic Engineering 28th International Joint Conference on Artificial Intelligence (IJCAI 2019) ST Engineering - NTU Corporate Laboratory Engineering::Electrical and electronic engineering Agent-based and Multi-agent Systems Coordination and Cooperation In an ad hoc teamwork setting, the team needs to coordinate their activities to perform a task without prior agreement on how to achieve it. The ad hoc agent cannot communicate with its teammates but it can observe their behaviour and plan accordingly. To do so, the existing approaches rely on the teammates' behaviour models. However, the models may not be accurate, which can compromise teamwork. For this reason, we present Ad Hoc Teamwork by Sub-task Inference and Selection (ATSIS) algorithm that uses a sub-task inference without relying on teammates' models. First, the ad hoc agent observes its teammates to infer which sub-tasks they are handling. Based on that, it selects its own sub-task using a partially observable Markov decision process that handles the uncertainty of the sub-task inference. Last, the ad hoc agent uses the Monte Carlo tree search to find the set of actions to perform the sub-task. Our experiments show the benefits of ATSIS for robust teamwork. NRF (Natl Research Foundation, S’pore) Accepted version 2020-06-03T07:13:34Z 2020-06-03T07:13:34Z 2019 Conference Paper Chen, S., Andrejczuk, E., Irissappane, A. A., & Zhang, J. (2019). ATSIS : achieving the ad hoc teamwork by sub-task inference and selection. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19), 172-179. doi:10.24963/ijcai.2019/25 978-0-9992411-4-1 https://hdl.handle.net/10356/141012 http://www.ijcai.org 10.24963/ijcai.2019/25 172 179 en C-RP11 © 2019 International Joint Conferences on Artificial Intelligence. All rights reserved. This paper was published in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19) and is made available with permission of International Joint Conferences on Artificial Intelligence. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
Agent-based and Multi-agent Systems
Coordination and Cooperation
spellingShingle Engineering::Electrical and electronic engineering
Agent-based and Multi-agent Systems
Coordination and Cooperation
Chen, Shuo
Andrejczuk, Ewa
Irissappane, Athirai Aravazhi
Zhang, Jie
ATSIS : achieving the ad hoc teamwork by sub-task inference and selection
description In an ad hoc teamwork setting, the team needs to coordinate their activities to perform a task without prior agreement on how to achieve it. The ad hoc agent cannot communicate with its teammates but it can observe their behaviour and plan accordingly. To do so, the existing approaches rely on the teammates' behaviour models. However, the models may not be accurate, which can compromise teamwork. For this reason, we present Ad Hoc Teamwork by Sub-task Inference and Selection (ATSIS) algorithm that uses a sub-task inference without relying on teammates' models. First, the ad hoc agent observes its teammates to infer which sub-tasks they are handling. Based on that, it selects its own sub-task using a partially observable Markov decision process that handles the uncertainty of the sub-task inference. Last, the ad hoc agent uses the Monte Carlo tree search to find the set of actions to perform the sub-task. Our experiments show the benefits of ATSIS for robust teamwork.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Chen, Shuo
Andrejczuk, Ewa
Irissappane, Athirai Aravazhi
Zhang, Jie
format Conference or Workshop Item
author Chen, Shuo
Andrejczuk, Ewa
Irissappane, Athirai Aravazhi
Zhang, Jie
author_sort Chen, Shuo
title ATSIS : achieving the ad hoc teamwork by sub-task inference and selection
title_short ATSIS : achieving the ad hoc teamwork by sub-task inference and selection
title_full ATSIS : achieving the ad hoc teamwork by sub-task inference and selection
title_fullStr ATSIS : achieving the ad hoc teamwork by sub-task inference and selection
title_full_unstemmed ATSIS : achieving the ad hoc teamwork by sub-task inference and selection
title_sort atsis : achieving the ad hoc teamwork by sub-task inference and selection
publishDate 2020
url https://hdl.handle.net/10356/141012
http://www.ijcai.org
_version_ 1681059047331069952