Preprint · 2022 · Open access

SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving

Linrui Zhang, Zhang, Qin, Shen, Li, Bo Yuan, Xueqian Wang

arXiv (Cornell University) · Published 17 June 2022 · DOI 10.48550/arxiv.2206.08528

Open PDFView at the publisherCite this paper

In brief

“SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving” is a 2022 preprint by Linrui Zhang and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 14 citations as of 22 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
14
Most cited in
2024 (5)
References
24
Authors
5

Abstract

Safe reinforcement learning (RL) has achieved significant success on risk-sensitive tasks and shown promise in autonomous driving (AD) as well. Considering the distinctiveness of this community, efficient and reproducible baselines are still lacking for safe AD. In this paper, we release SafeRL-Kit to benchmark safe RL methods for AD-oriented tasks. Concretely, SafeRL-Kit contains several latest algorithms specific to zero-constraint-violation tasks, including Safety Layer, Recovery RL, off-policy Lagrangian method, and Feasible Actor-Critic. In addition to existing approaches, we propose a novel first-order method named Exact Penalty Optimization (EPO) and sufficiently demonstrate its capability in safe AD. All algorithms in SafeRL-Kit are implemented (i) under the off-policy setting, which improves sample efficiency and can better leverage past logs; (ii) with a unified learning framework, providing off-the-shelf interfaces for researchers to incorporate their domain-specific knowledge into fundamental safe RL methods. Conclusively, we conduct a comparative evaluation of the above algorithms in SafeRL-Kit and shed light on their efficacy for safe autonomous driving. The source code is available at \href{ https://github.com/zlr20/saferl_kit}{this https URL}.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Zhang, L., Qin, Z., Li, S., Yuan, B., & Wang, X. (2022). SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2206.08528

MLA 9

Zhang, Linrui, et al. “SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving.” arXiv (Cornell University), 2022. https://doi.org/10.48550/arxiv.2206.08528.

Chicago

Zhang, Linrui, Zhang, Qin, Shen, Li, Bo Yuan, and Xueqian Wang. 2022. “SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2206.08528.

Harvard

Zhang, L. et al. (2022) ‘SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving’, arXiv (Cornell University). doi:10.48550/arxiv.2206.08528.

IEEE

L. Zhang, Z. Qin, S. Li, B. Yuan, and X. Wang, “SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving,” arXiv (Cornell University), 2022, doi: 10.48550/arxiv.2206.08528.

BibTeX

@misc{zhang2022saferl,
  title     = {{SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving}},
  author    = {Zhang, Linrui and Qin, Zhang, and Li, Shen, and Yuan, Bo and Wang, Xueqian},
  howpublished = {arXiv (Cornell University)},
  year      = {2022},
  doi       = {10.48550/arxiv.2206.08528},
  url       = {https://doi.org/10.48550/arxiv.2206.08528}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202322
202455
202544
202633

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics

  • safe reinforcement learning
  • autonomous driving
  • benchmarking
  • safety layer
  • off-policy learning
  • sample efficiency

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Zhang, L., Qin, Z., Li, S., Yuan, B., & Wang, X. (2022). SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2206.08528

How many times has this paper been cited?

14 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Linrui Zhang, Zhang, Qin, Shen, Li, Bo Yuan, Xueqian Wang.

What is the DOI of this paper?

10.48550/arxiv.2206.08528, permanently at https://doi.org/10.48550/arxiv.2206.08528. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.