RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

Hao Gao, Shaoyu Chen, Bo Jiang, Bencheng Liao, Yiang Shi, Xiaoyang Guo, Yuechuan Pu, haoran yin, Xiangyu Li, xinbang zhang, ying zhang, Wenyu Liu, Qian Zhang, Xinggang Wang

Keywords: End-to-end, Autonomous driving, Reinforcement learning, 3DGS environment, Closed-loop

TL;DR: A 3DGS-based Reinforcement Learning training paradigm for end-to-end autonomous driving

Abstract: Existing end-to-end autonomous driving (AD) algorithms typically follow the Imitation Learning (IL) paradigm, which faces challenges such as causal confusion and an open-loop gap. In this work, we propose RAD, a 3DGS-based closed-loop Reinforcement Learning (RL) framework for end-to-end Autonomous Driving. By leveraging 3DGS techniques, we construct a photorealistic digital replica of the real physical world, enabling the AD policy to extensively explore the state space and learn to handle out-of-distribution scenarios through large-scale trial and error. To enhance safety, we design specialized rewards to guide the policy in effectively responding to safety-critical events and understanding real-world causal relationships. To better align with human driving behavior, we incorporate IL into RL training as a regularization term. We introduce a closed-loop evaluation benchmark consisting of diverse, previously unseen 3DGS environments. Compared to IL-based methods, RAD achieves stronger performance in most closed-loop metrics, particularly exhibiting a 3× lower collision rate. Abundant closed-loop results are presented in the supplementary material. Code is available at https://github.com/hustvl/RAD for facilitating future research.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 11454