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.

翻译：我们提出了一个可复现的基准测试平台，用于评估车联网与自动驾驶车辆多智能体强化学习策略的仿真到现实迁移性能。该平台基于信息物理移动实验室，整合了仿真环境、高保真数字孪生系统与物理测试场，能够对多智能体强化学习运动规划策略进行结构化零样本评估。我们通过在所有三个领域部署SigmaRL训练的策略来展示其应用，揭示了性能下降的两个互补来源：仿真与硬件控制栈之间的架构差异，以及环境真实度提升引发的仿真到现实差距。该开源平台能够在真实可复现条件下，对多智能体强化学习中的仿真到现实挑战进行系统化分析。