← Back to Benchmarks
simmediumsim-to-realmetric · varies

Zero-Shot MARL Benchmark in the Cyber-Physical Mobility Lab

Description

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 co

Source

http://arxiv.org/abs/2601.16578v1