The paper introduces Endpoint-Constrained Optimization (ECO), a lightweight postprocessing layer that corrects intermediate waypoints of end-to-end driving policies while preserving the predicted endpoint. ECO does not require maps, privileged simulator state, or additional training, and can be applied to a wide range of waypoint-emitting policies. Experiments on two closed-loop simulators show that ECO significantly improves closed-loop performance, achieving top results in the HUGSIM Closed-Loop Driving Challenge and boosting scene scores on AlpaSim.
By Brayden Zhang, Mahsa Golchoubian, Igor Gilitschenski, Boris Ivanovic, Kashyap Chitta
arXiv:2608.22549v1 Announce Type: new
Abstract: Batched simulators for autonomous driving have recently enabled training reinforcement learning (RL) agents at scale, encompassing thousands of traffic...
By Cevahir Koprulu, David Paz, Feng Tao, Yuliang Guo, Xinyu Huang, Ufuk Topcu, Liu Ren
arXiv:2608. 10403v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown promising performance in autonomous driving, yet ensuring the safety of online RL policies remains challenging due to insufficient exposure to safety-critical driving scenes.
By Xincong Hu (Nanjing University), Lei Ou (Nanjing University), Maosen Li (Yinwang Intelligent Technology Co., Ltd), Jingtao Zhang (Yinwang Intelligent Technology Co., Ltd), Liguo Hou (Yinwang Intelligent Technology Co., Ltd), Zongzhang Zhang (Nanjing University)
arXiv:2510. 09041v3 Announce Type: replace-cross Abstract: Deep reinforcement learning (DRL) has demonstrated remarkable success in developing autonomous driving policies.
By Junchao Fan, Qi Wei, Ruichen Zhang, Yang Lu, Jianhua Wang, Xiaolin Chang, Bo Ai
arXiv:2603. 18315v2 Announce Type: replace-cross Abstract: Traditional reinforcement learning (RL) methods rely on manually engineered rewards or sparse collision signals, which fail to capture the rich contextual understanding required for safe driving and make unsafe exploration unavoidable in real-world settings.
By Zilin Huang, Zihao Sheng, Zhengyang Wan, Yansong Qu, Junwei You, Sicong Jiang, Sikai Chen
arXiv:2606. 30537v1 Announce Type: cross Abstract: Autonomous driving policies should be able to improve continually as deployment exposes them to increasingly diverse and long-tail traffic situations.
By Cheng Gong, Haoyang Wang, Chao Lu, Zirui Li, Jianwei Gong
arXiv:2607. 13028v1 Announce Type: cross Abstract: Training robust autonomous driving agents requires a simulator that is fast enough for reinforcement learning at scale, realistic enough to ground behavior in real-world map structure, and diverse enough to cover the safety-critical long tail that logged data rarely contains.
By Zhouchonghao Wu, Akshay Rangesh, Weixin Li, Wei-Jer Chang, Zachary Lee, Tim Wang, Wei Zhan
arXiv:2606. 06423v1 Announce Type: cross Abstract: Safety-critical traffic scenario generation is essential for evaluating autonomous driving systems under rare but high-risk interactions.
By Qi Lan, Yining Tang, Yu Shen, Yi Zhou, Yuhao Wei, Jie Li, Guofa Li
arXiv:2503. 23650v2 Announce Type: replace Abstract: Reinforcement learning (RL), with its ability to explore and optimize policies in complex, dynamic decision-making tasks, has emerged as a promising approach to addressing motion planning (MoP) challenges in autonomous driving (AD).
By Zhuoren Li, Guizhe Jin, Ran Yu, Weiqi Zhang, Zhiwen Chen, Nan Li, Lu Xiong, Ilya Kolmanovsky, Dimitar Filev, Bo Leng, Jia Hu
arXiv:2601.01762v4 Announce Type: replace-cross
Abstract: Practical autonomous driving requires models that generalize by reasoning through spatial-temporal possibilities to exclude unsafe outcomes....
By Yanhao Wu, Haoyang Zhang, Fei He, Rui Wu, Yanhu Shan, Congpei Qiu, Liang Gao, Wei Ke, Tong Zhang
arXiv:2606. 31106v1 Announce Type: cross Abstract: Large-scale datasets and fast simulators have enabled improvements in driving policies that appear safe and robust, yet strong performance in nominal scenarios can still mask flawed reasoning and unsafe heuristics.
By Hyeonchang Jeon, Kyungbeom Kim, Eugene Vinitsky, Kyung-Joong Kim
arXiv:2602.05863v3 Announce Type: replace
Abstract: Group Relative Policy Optimization (GRPO) remains the dominant critic-free approach for fine-tuning LLMs and VLMs, but its compatibility with const...
By Roger Girgis, Rodrigue de Schaetzen, Luke Rowe, Azal\'ee Robitaille, Christopher Pal, Liam Paull