@article{Shuai2026, 
author = {Bin Shuai and Min Hua and Letian Tao and Zhilong Zheng and Yujie Yang and Yang Guan and Lei He and Jingliang Duan and Jiaxin Gao and Shuo Feng and Xianyuan Zhan and Jincheng Yu and Yang Yu and Haifeng Zhang and Shengbo Eben Li},
title = {Recent Advances of Reinforcement Learning Algorithms for Autonomous Driving System},
year = {2026},
journal = {Communications in Transportation Research},
keywords = {Autonomous driving, decision-making, vehicle control, reinforcement learning},
url = {https://www.sciopen.com/article/10.26599/COMMTR.2026.9640053},
doi = {10.26599/COMMTR.2026.9640053},
abstract = {Reinforcement learning (RL) is being studied for autonomous driving (AD), but its value depends on the role it plays in a task, the action interface, the evaluation protocol, and the evidence from deployment. This survey examines RL-based AD in modular and end-to-end pipelines and relates reported methods to task formulation and deployment evidence. It maps safe RL, offline RL, model-based RL, and PPO/GRPO-style fine-tuning to maneuver selection, continuous control, world modeling, and VLM/VLA-based driving. It also reviews simulators, datasets, RL platforms, and VLA benchmarks, with attention to reward design, observation space, traffic complexity, and open-loop versus closed-loop evaluation. The survey then examines deployment barriers, including safety, Sim2Real generalization, data efficiency, computation, embodied alignment, and evaluation readiness. RL and VLM/VLA-based methods have shown promise, but current evidence is insufficient to support reliable real-world deployment: many reported results come from restricted scenarios and depend on engineered rewards or simulator assumptions.  }
}