How to Post-Train Autonomous Vehicle Models in Closed-Loop with NVIDIA Alpamayo
NVIDIA introduces a method to bridge the gap between training and deployment of autonomous vehicle models using closed-loop post-training with their Alpamayo platform, improving vision-language-action models for complex driving scenes.
Developing autonomous vehicle (AV) policies requires bridging an important gap between training and deployment. Vision-language-action (VLA) models that can reason over more complex driving scenes and produce richer intermediate reasoning are predominantly trained in open-loop, where model outputs are directly compared to ground-truth behaviors without considering their effect on the environment. NVIDIA's Alpamayo platform supports closed-loop post-training, enabling AV models to be refined by interacting with simulated environments, thus improving their real-world performance and safety.