DRAMA at the PettingZoo: Dynamically restricted action spaces for multi-agent reinforcement learning frameworks


Oesterle, Michael ; Grams, Tim ; Bartelt, Christian


[img] PDF
0762.pdf - Published

Download (2MB)

URL: https://hdl.handle.net/10125/107324
URN: urn:nbn:de:bsz:180-madoc-674336
Document Type: Conference or workshop publication
Year of publication: 2024
Book title: Proceedings of the 57th Annual Hawaii International Conference on System Sciences, HICSS 2024, Hilton Hawaiian Village Waikiki Beach Resort, Hawaii, USA, January 3-6, 2024
Page range: 7810-7819
Conference title: HICSS 2024, 57th Hawaii International Conference on System Sciences
Location of the conference venue: Honolulu, HI
Date of the conference: 03.-06.01.2024
Publisher: Bui, Tung X.
Place of publication: Honolulu, HI
Publishing house: Department of IT-Management, Shidler College of Business, University of Hawaii
ISBN: 978-0-9981331-7-1
Publication language: English
Institution: Außerfakultäre Einrichtungen > Institut für Enterprise Systems (InES)
Pre-existing license: Creative Commons Attribution, Non-Commercial, No Derivatives 4.0 International (CC BY-NC-ND 4.0)
Subject: 004 Computer science, internet
Keywords (English): multi-agent reinforcement learning , openAI gym , pettingzoo , multi-agent systems , action-space restriction
Abstract: The Agent Environment Cycle (AEC) of PettingZoo has been a major paradigm shift in the implementation of Multi-Agent Reinforcement Learning (MARL) frameworks, providing a unified and concise interface for any kind of multi-agent environment. Based on this model, we propose DRAMA, a principled approach for dynamic action space restrictions. DRAMA can be used to add statically computed physical constraints as well as a self-learning multi-agent governance: It generalizes the idea of action masking to continuous action spaces and self-learning restrictions, while being fully compatible with the AEC implementation of PettingZoo—and, by transitivity, with most major MARL frameworks. In this paper, we provide the theoretical background of restricted multi-agent systems, present an extension of PettingZoo via wrapper classes, and show the potential of our approach for various use cases. By treating dynamic restrictions as an additional player of a multi-agent system, our approach offers novel capabilities and flexibility in handling multi-agent environments and thus serves as a valuable tool for researchers and practitioners in the field.




Dieser Eintrag ist Teil der Universitätsbibliographie.

Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.




Metadata export


Citation


+ Search Authors in

+ Download Statistics

Downloads per month over past year

View more statistics



You have found an error? Please let us know about your desired correction here: E-Mail


Actions (login required)

Show item Show item