SOURCE-LINKED INTELLIGENCE

What Emerges and What Breaks in Self-Play Driving

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Training autonomous driving policies through pure self-play has recently shown promising results. Following Gigaflow and Puffer- Drive, we train driving policies in a similar self-play fashion, but extend the models from MLPs to Transformers and train on the high-definition map of a real city, where we ultimately aim to deploy them. On the CARLA and Waymax benchmarks, our policies fall short of Gigaflow, and we trace the gap to specific failure modes, including reward hacking at traffic lights and a missing incentive to stop at stop signs. We further analyze which traffic rules emerge from sel

Read original source ↗ Open in workspace

recordType

paper

region

Global