MARGoS: A Configuration-Driven Platform for Reproducible MARL Experiments in ARGoS

原文：MARGoS: A Configuration-Driven Platform for Reproducible MARL Experiments in ARGoS

作者：Tom Philipp Backert, Mohammad D. Soorati, Javad Ghofrani

来源：arXiv cs.RO（机器人）

正文

Computer Science > Software Engineering

arXiv:2610.13772v1 (cs)

[Submitted on 9 Oct 2026]

Title:MARGoS: A Configuration-Driven Platform for Reproducible MARL Experiments in ARGoS

Authors:Tom Philipp Backert, Mohammad D. Soorati, Javad Ghofrani

View a PDF of the paper titled MARGoS: A Configuration-Driven Platform for Reproducible MARL Experiments in ARGoS, by Tom Philipp Backert and 2 other authors

View PDF

HTML (experimental)

Abstract:Multi-agent reinforcement learning (MARL) has become a prominent research direction, particularly within collective robotics, where the ARGoS simulator is widely used to study emergent swarm behavior. Yet despite this growth, systematic support for reuse and reproducibility in MARL-based swarm robotics remains limited and insufficiently standardized: a single experiment is assembled from manually aligned simulator files, training scripts, configuration values, paths, seeds, and environment details, so reuse and reproduction stay fragile even within one research group. To address this gap, we introduce MARGoS, a lightweight, configuration-driven platform developed in this project that elevates these experiment-defining inputs to first-class, platform-managed artifacts. MARGoS enables reproducible experimentation through configuration hashing, end-to-end seed propagation, frozen (immutable) configurations, structured logging, environment fingerprinting, and exportable experiment bundles that facilitate sharing, replay, and verification of results across machines and over time. A five-dimension evaluation (architecture, efficiency, reproducibility, usability, and collaboration) supports our claim that managing experiment variation as a platform responsibility makes ARGoS+MARL experiments easier to reuse, reproduce, and hand off. Our code is available at this https URL.

Comments:

Submitted version (prior to peer review) of a paper published in the VARIABILITY 2026 Satellite Events proceedings (Project Showcase Track), LNCS 17104, Springer. 11 pages, 3 figures, 3 tables

Subjects:

Software Engineering (cs.SE); Multiagent Systems (cs.MA); Robotics (cs.RO)

Cite as:

arXiv:2610.13772 [cs.SE]

(or

arXiv:2610.13772v1 [cs.SE] for this version)

https://doi.org/10.48550/arXiv.2610.13772

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

软件工程 · 多智能体 · 机器人

由「前沿雷达」于 2026-10-09 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。