AATEAM: Achieving the ad hoc teamwork by employing the attention mechanism
In the ad hoc teamwork setting, a team of agents needs to perform a task without prior coordination. The most advanced approach learns policies based on previous experiences and reuses one of the policies to interact with new teammates. However, the selected policy in many cases is sub-optimal. Swit...
Saved in:
Main Authors: | , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2020
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8132 https://ink.library.smu.edu.sg/context/sis_research/article/9135/viewcontent/6196_Article_Text_9421_1_10_20200516.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-9135 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-91352023-09-14T08:31:30Z AATEAM: Achieving the ad hoc teamwork by employing the attention mechanism CHEN, Shuo ANDREJCZUK, Ewa CAO, Zhiguang ZHANG, Jie In the ad hoc teamwork setting, a team of agents needs to perform a task without prior coordination. The most advanced approach learns policies based on previous experiences and reuses one of the policies to interact with new teammates. However, the selected policy in many cases is sub-optimal. Switching between policies to adapt to new teammates' behaviour takes time, which threatens the successful performance of a task. In this paper, we propose AATEAM – a method that uses the attention-based neural networks to cope with new teammates' behaviour in real-time. We train one attention network per teammate type. The attention networks learn both to extract the temporal correlations from the sequence of states (i.e. contexts) and the mapping from contexts to actions. Each attention network also learns to predict a future state given the current context and its output action. The prediction accuracies help to determine which actions the ad hoc agent should take. We perform extensive experiments to show the effectiveness of our method. 2020-01-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8132 info:doi/10.1609/aaai.v34i05.6196 https://ink.library.smu.edu.sg/context/sis_research/article/9135/viewcontent/6196_Article_Text_9421_1_10_20200516.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 Engineering Electrical and electronic engineering 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 |
Engineering Electrical and electronic engineering Databases and Information Systems |
spellingShingle |
Engineering Electrical and electronic engineering Databases and Information Systems CHEN, Shuo ANDREJCZUK, Ewa CAO, Zhiguang ZHANG, Jie AATEAM: Achieving the ad hoc teamwork by employing the attention mechanism |
description |
In the ad hoc teamwork setting, a team of agents needs to perform a task without prior coordination. The most advanced approach learns policies based on previous experiences and reuses one of the policies to interact with new teammates. However, the selected policy in many cases is sub-optimal. Switching between policies to adapt to new teammates' behaviour takes time, which threatens the successful performance of a task. In this paper, we propose AATEAM – a method that uses the attention-based neural networks to cope with new teammates' behaviour in real-time. We train one attention network per teammate type. The attention networks learn both to extract the temporal correlations from the sequence of states (i.e. contexts) and the mapping from contexts to actions. Each attention network also learns to predict a future state given the current context and its output action. The prediction accuracies help to determine which actions the ad hoc agent should take. We perform extensive experiments to show the effectiveness of our method. |
format |
text |
author |
CHEN, Shuo ANDREJCZUK, Ewa CAO, Zhiguang ZHANG, Jie |
author_facet |
CHEN, Shuo ANDREJCZUK, Ewa CAO, Zhiguang ZHANG, Jie |
author_sort |
CHEN, Shuo |
title |
AATEAM: Achieving the ad hoc teamwork by employing the attention mechanism |
title_short |
AATEAM: Achieving the ad hoc teamwork by employing the attention mechanism |
title_full |
AATEAM: Achieving the ad hoc teamwork by employing the attention mechanism |
title_fullStr |
AATEAM: Achieving the ad hoc teamwork by employing the attention mechanism |
title_full_unstemmed |
AATEAM: Achieving the ad hoc teamwork by employing the attention mechanism |
title_sort |
aateam: achieving the ad hoc teamwork by employing the attention mechanism |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2020 |
url |
https://ink.library.smu.edu.sg/sis_research/8132 https://ink.library.smu.edu.sg/context/sis_research/article/9135/viewcontent/6196_Article_Text_9421_1_10_20200516.pdf |
_version_ |
1779157176206491648 |