rl_based.md

RL-based Methods for SCSG

This directory contains methods for SCSG based on Reinforcement Learning, taking the scenario generation process as a series of actions instead of some sampling point.

---

Dense reinforcement learning for safety validation of autonomous vehicles

paper link is here

citation:

@article{feng2023dense,
  title={Dense reinforcement learning for safety validation of autonomous vehicles},
  author={Feng, Shuo and Sun, Haowei and Yan, Xintao and Zhu, Haojie and Zou, Zhengxia and Shen, Shengyin and Liu, Henry X},
  journal={Nature},
  volume={615},
  number={7953},
  pages={620--627},
  year={2023},
  publisher={Nature Publishing Group UK London}
}

Metadrive: composing diverse driving scenarios for generalizable reinforcement learning

paper link: here

citation:

@misc{li2022metadrive,
      title={MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning}, 
      author={Quanyi Li and Zhenghao Peng and Lan Feng and Qihang Zhang and Zhenghai Xue and Bolei Zhou},
      year={2022},
      eprint={2109.12674},
      archivePrefix={arXiv},
      primaryClass={id='cs.LG' full_name='Machine Learning' is_active=True alt_name=None in_archive='cs' is_general=False description='Papers on all aspects of machine learning research (supervised, unsupervised, reinforcement learning, bandit problems, and so on) including also robustness, explanation, fairness, and methodology. cs.LG is also an appropriate primary category for applications of machine learning methods.'}
}

Deep imitation learning for autonomous driving in generic urban scenarios with enhanced safety

paper link is here

citation:

@misc{chen2019deep,
      title={Deep Imitation Learning for Autonomous Driving in Generic Urban Scenarios with Enhanced Safety}, 
      author={Jianyu Chen and Bodi Yuan and Masayoshi Tomizuka},
      year={2019},
      eprint={1903.00640},
      archivePrefix={arXiv},
      primaryClass={id='cs.RO' full_name='Robotics' is_active=True alt_name=None in_archive='cs' is_general=False description='Roughly includes material in ACM Subject Class I.2.9.'}
}