Saved in:
Bibliographic Details
Main Authors: Beerwerth, Julius, Xu, Jianye, Schäfer, Simon, Belderink, Fynn, Alrifaee, Bassam
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.16578
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913162168631296
author Beerwerth, Julius
Xu, Jianye
Schäfer, Simon
Belderink, Fynn
Alrifaee, Bassam
author_facet Beerwerth, Julius
Xu, Jianye
Schäfer, Simon
Belderink, Fynn
Alrifaee, Bassam
contents We present a reproducible benchmark for evaluating sim-to-real transfer of Multi-Agent Reinforcement Learning (MARL) policies for Connected and Automated Vehicles (CAVs). The platform, based on the Cyber-Physical Mobility Lab (CPM Lab) [1], integrates simulation, a high-fidelity digital twin, and a physical testbed, enabling structured zero-shot evaluation of MARL motion-planning policies. We demonstrate its use by deploying a SigmaRL-trained policy [2] across all three domains, revealing two complementary sources of performance degradation: architectural differences between simulation and hardware control stacks, and the sim-to-real gap induced by increasing environmental realism. The open-source setup enables systematic analysis of sim-to-real challenges in MARL under realistic, reproducible conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16578
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Zero-Shot MARL Benchmark in the Cyber-Physical Mobility Lab
Beerwerth, Julius
Xu, Jianye
Schäfer, Simon
Belderink, Fynn
Alrifaee, Bassam
Robotics
Systems and Control
We present a reproducible benchmark for evaluating sim-to-real transfer of Multi-Agent Reinforcement Learning (MARL) policies for Connected and Automated Vehicles (CAVs). The platform, based on the Cyber-Physical Mobility Lab (CPM Lab) [1], integrates simulation, a high-fidelity digital twin, and a physical testbed, enabling structured zero-shot evaluation of MARL motion-planning policies. We demonstrate its use by deploying a SigmaRL-trained policy [2] across all three domains, revealing two complementary sources of performance degradation: architectural differences between simulation and hardware control stacks, and the sim-to-real gap induced by increasing environmental realism. The open-source setup enables systematic analysis of sim-to-real challenges in MARL under realistic, reproducible conditions.
title Zero-Shot MARL Benchmark in the Cyber-Physical Mobility Lab
topic Robotics
Systems and Control
url https://arxiv.org/abs/2601.16578