Leveraging Organizational Hierarchy to Simplify Reward Design in Cooperative Multi-agent Reinforcement Learning

The effectiveness of multi-agent reinforcement learning (MARL) hinges largely on the meticulous arrangement of objectives. Yet, conventional MARL methods might not completely harness the inherent structures present in environmental states and agent relationships for goal organization. This study is...

Full description

Saved in:
Bibliographic Details
Main Authors: Lixing Liu, Volkan Ustun, Rajay Kumar
Format: Article
Language:English
Published: LibraryPress@UF 2024-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Online Access:https://journals.flvc.org/FLAIRS/article/view/135588
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850271035476148224
author Lixing Liu
Volkan Ustun
Rajay Kumar
author_facet Lixing Liu
Volkan Ustun
Rajay Kumar
author_sort Lixing Liu
collection DOAJ
description The effectiveness of multi-agent reinforcement learning (MARL) hinges largely on the meticulous arrangement of objectives. Yet, conventional MARL methods might not completely harness the inherent structures present in environmental states and agent relationships for goal organization. This study is conducted within the domain of military training simulations, which are typically characterized by complexity, heterogeneity, non-stationary and doctrine-driven environments with a clear organizational hierarchy and a top-down chain of command. This research investigates the approximation and integration of the organizational hierarchy into MARL for cooperative training scenarios, with the goal of streamlining the processes of reward engineering and enhancing team coordination. In the preliminary experiments, we employed two-tiered commander-subordinate feudal hierarchical (CSFH) networks to separate the prioritized team goal and individual goals. The empirical results demonstrate that the proposed framework enhances learning efficiency. It guarantees the learning of a prioritized policy for the commander agent and encourages subordinate agents to explore areas of interest more frequently, guided by appropriate soft constraints imposed by the commander.
format Article
id doaj-art-54d79c3d982149ac91d069318437bc21
institution OA Journals
issn 2334-0754
2334-0762
language English
publishDate 2024-05-01
publisher LibraryPress@UF
record_format Article
series Proceedings of the International Florida Artificial Intelligence Research Society Conference
spelling doaj-art-54d79c3d982149ac91d069318437bc212025-08-20T01:52:22ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622024-05-013710.32473/flairs.37.1.13558871967Leveraging Organizational Hierarchy to Simplify Reward Design in Cooperative Multi-agent Reinforcement LearningLixing Liu0https://orcid.org/0009-0009-8648-2007Volkan Ustun1https://orcid.org/0000-0002-7090-4086Rajay Kumar2University of Southern CaliforniaInstitute for Creative Technologies, University of Southern CaliforniaInstitute for Creative Technologies, University of Southern CaliforniaThe effectiveness of multi-agent reinforcement learning (MARL) hinges largely on the meticulous arrangement of objectives. Yet, conventional MARL methods might not completely harness the inherent structures present in environmental states and agent relationships for goal organization. This study is conducted within the domain of military training simulations, which are typically characterized by complexity, heterogeneity, non-stationary and doctrine-driven environments with a clear organizational hierarchy and a top-down chain of command. This research investigates the approximation and integration of the organizational hierarchy into MARL for cooperative training scenarios, with the goal of streamlining the processes of reward engineering and enhancing team coordination. In the preliminary experiments, we employed two-tiered commander-subordinate feudal hierarchical (CSFH) networks to separate the prioritized team goal and individual goals. The empirical results demonstrate that the proposed framework enhances learning efficiency. It guarantees the learning of a prioritized policy for the commander agent and encourages subordinate agents to explore areas of interest more frequently, guided by appropriate soft constraints imposed by the commander.https://journals.flvc.org/FLAIRS/article/view/135588
spellingShingle Lixing Liu
Volkan Ustun
Rajay Kumar
Leveraging Organizational Hierarchy to Simplify Reward Design in Cooperative Multi-agent Reinforcement Learning
Proceedings of the International Florida Artificial Intelligence Research Society Conference
title Leveraging Organizational Hierarchy to Simplify Reward Design in Cooperative Multi-agent Reinforcement Learning
title_full Leveraging Organizational Hierarchy to Simplify Reward Design in Cooperative Multi-agent Reinforcement Learning
title_fullStr Leveraging Organizational Hierarchy to Simplify Reward Design in Cooperative Multi-agent Reinforcement Learning
title_full_unstemmed Leveraging Organizational Hierarchy to Simplify Reward Design in Cooperative Multi-agent Reinforcement Learning
title_short Leveraging Organizational Hierarchy to Simplify Reward Design in Cooperative Multi-agent Reinforcement Learning
title_sort leveraging organizational hierarchy to simplify reward design in cooperative multi agent reinforcement learning
url https://journals.flvc.org/FLAIRS/article/view/135588
work_keys_str_mv AT lixingliu leveragingorganizationalhierarchytosimplifyrewarddesignincooperativemultiagentreinforcementlearning
AT volkanustun leveragingorganizationalhierarchytosimplifyrewarddesignincooperativemultiagentreinforcementlearning
AT rajaykumar leveragingorganizationalhierarchytosimplifyrewarddesignincooperativemultiagentreinforcementlearning