DRAMA at the PettingZoo: Dynamically Restricted Action Spaces for Multi-Agent Reinforcement Learning Frameworks

Simple item page
dc.contributor.authorOesterle, Michael
dc.contributor.authorGrams, Tim
dc.contributor.authorBartelt, Christian
dc.date.accessioned2023-12-26T18:55:44Z
dc.date.available2023-12-26T18:55:44Z
dc.date.issued2024-01-03
dc.identifier.doi10.24251/HICSS.2024.935
dc.identifier.isbn978-0-9981331-7-1
dc.identifier.otherdc3e6a7f-0784-43f6-9b05-fcda8901f8e2
dc.identifier.urihttps://hdl.handle.net/10125/107324
dc.language.isoeng
dc.relation.ispartofProceedings of the 57th Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectSoftware Technology and Software Development
dc.subjectaction space restriction
dc.subjectmulti-agent reinforcement learning
dc.subjectmulti-agent systems
dc.subjectopenai gym
dc.subjectpettingzoo
dc.titleDRAMA at the PettingZoo: Dynamically Restricted Action Spaces for Multi-Agent Reinforcement Learning Frameworks
dc.typeConference Paper
dc.type.dcmiText
dcterms.abstractThe 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.
dcterms.extent10 pages
prism.startingpage7810

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0762.pdf
Size:
2.61 MB
Format:
Adobe Portable Document Format
Download

Collections

Software Technology and Software Development