Robust control policy learning for autonomous driving requires training environments to be both physically realistic and computationally scalable, properties that existing simulators provide only in isolation. We introduce Sim2Sim2Sim, a framework that bridges high-fidelity vehicle simulation and scalable reinforcement learning by distilling simulator dynamics into a highly parallelizable learned dynamics model. By training control policies purely within this distilled environment and deploying them back into the high-fidelity source simulator, we demonstrate more efficient policy optimization and reliable transfer under challenging dynamics. We further show that predictive accuracy alone does not fully characterize a learned dynamics model's suitability as a reinforcement learning training environment, which should also be assessed by the quality of the policies it enables.
@article{arxiv.2605.01516,
title = {Dynamics Distillation for Efficient and Transferable Control Learning},
author = {Xunjiang Gu and Kashyap Chitta and Mahsa Golchoubian and Vladimir Suplin and Igor Gilitschenski},
journal= {arXiv preprint arXiv:2605.01516},
year = {2026}
}