Approximate difference rewards for scalable multigent reinforcement learning

We address the problem ofmultiagent credit assignment in a large scale multiagent system. Difference rewards (DRs) are an effective tool to tackle this problem, but their exact computation is known to be challenging even for small number of agents. We propose a scalable method to compute difference...

Full description

Saved in:
Bibliographic Details
Main Authors: SINGH, Arambam James, KUMAR, Akshat, LAU, Hoong Chuin
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2021
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6022
https://ink.library.smu.edu.sg/context/sis_research/article/7025/viewcontent/AAMAS_2021_ext_abs.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-7025
record_format dspace
spelling sg-smu-ink.sis_research-70252021-07-08T09:06:10Z Approximate difference rewards for scalable multigent reinforcement learning SINGH, Arambam James KUMAR, Akshat LAU, Hoong Chuin We address the problem ofmultiagent credit assignment in a large scale multiagent system. Difference rewards (DRs) are an effective tool to tackle this problem, but their exact computation is known to be challenging even for small number of agents. We propose a scalable method to compute difference rewards based on aggregate information in a multiagent system with large number of agents by exploiting the symmetry present in several practical applications. Empirical evaluation on two multiagent domains - air-traffic control and cooperative navigation, shows better solution quality than previous approaches. 2021-05-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6022 info:doi/10.5555/3463952.3464191 https://ink.library.smu.edu.sg/context/sis_research/article/7025/viewcontent/AAMAS_2021_ext_abs.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 Reinforcement learning multiagent systems Artificial Intelligence and Robotics Operations Research, Systems Engineering and Industrial Engineering
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Reinforcement learning
multiagent systems
Artificial Intelligence and Robotics
Operations Research, Systems Engineering and Industrial Engineering
spellingShingle Reinforcement learning
multiagent systems
Artificial Intelligence and Robotics
Operations Research, Systems Engineering and Industrial Engineering
SINGH, Arambam James
KUMAR, Akshat
LAU, Hoong Chuin
Approximate difference rewards for scalable multigent reinforcement learning
description We address the problem ofmultiagent credit assignment in a large scale multiagent system. Difference rewards (DRs) are an effective tool to tackle this problem, but their exact computation is known to be challenging even for small number of agents. We propose a scalable method to compute difference rewards based on aggregate information in a multiagent system with large number of agents by exploiting the symmetry present in several practical applications. Empirical evaluation on two multiagent domains - air-traffic control and cooperative navigation, shows better solution quality than previous approaches.
format text
author SINGH, Arambam James
KUMAR, Akshat
LAU, Hoong Chuin
author_facet SINGH, Arambam James
KUMAR, Akshat
LAU, Hoong Chuin
author_sort SINGH, Arambam James
title Approximate difference rewards for scalable multigent reinforcement learning
title_short Approximate difference rewards for scalable multigent reinforcement learning
title_full Approximate difference rewards for scalable multigent reinforcement learning
title_fullStr Approximate difference rewards for scalable multigent reinforcement learning
title_full_unstemmed Approximate difference rewards for scalable multigent reinforcement learning
title_sort approximate difference rewards for scalable multigent reinforcement learning
publisher Institutional Knowledge at Singapore Management University
publishDate 2021
url https://ink.library.smu.edu.sg/sis_research/6022
https://ink.library.smu.edu.sg/context/sis_research/article/7025/viewcontent/AAMAS_2021_ext_abs.pdf
_version_ 1770575740612378624