Learning to Interact in Multi-Agent Self-Play for Controllable Autonomous Driving Scenario Generation
Large-scale, multi-agent self-play trains robust driving policies effectively in simulation, but controlling these models to generate specific, safety-critical edge cases remains a key challenge. Existing goal-conditioned self-play frameworks rely primarily on static map-location goals and fail to reliably produce complex agent interactions such as aggressive tailgating or adversarial cut-offs. These agent interactions are necessary for rigorous autonomous vehicle (AV) testing. To address this, we present an extended multi-agent self-play framework that introduces agent-relative dynamic goals. By conditioning policies on this extended goal representation, our framework enables targeted, controllable scenario synthesis. We demonstrate that our approach successfully generates interactive driving behaviors that static-goal baselines cannot simulate, providing a flexible tool for long-tail scenario generation in AV testing.
Authors
- Maximilian Naumann (ORCID: https://orcid.org/0000-0003-1755-4352)
- Ethan Pronovost
- Marcell Vazquez-Chanlatte (ORCID: https://orcid.org/0000-0002-1248-0000)
- Beyazit Yalcinkaya (ORCID: https://orcid.org/0000-0001-9987-635X)
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-18
- DOI
- https://doi.org/10.48550/arxiv.2611.24876
- Primary Topic
- Autonomous Vehicle Technology and Safety
- Type
- preprint