Saved in:
| Main Authors: | , , , , |
|---|---|
| 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 |