Journal article · 2024 · Open access

GUARD: A Safe Reinforcement Learning Benchmark

Weiye Zhao, Yifan Sun, Li, Feihan, Rui Chen, Ruixuan Liu, Tianhao Wei, Changliu Liu

Transactions on machine learning research · Published 1 April 2024 · DOI 10.48550/arxiv.2305.13681

Open full textView at the publisherCite this paper

In brief

“GUARD: A Safe Reinforcement Learning Benchmark” is a 2024 journal article by Weiye Zhao and 6 co-authors, published in Transactions on machine learning research. OpenAlex counts 14 citations as of 22 November 2026, which puts it in the top 6% of works published in 2024 by citations. It is open access under a CC BY licence: the full text is free to read at Transactions on machine learning research.

Citations
14
Most cited in
2025 (4)
Field-weighted impact
0.89
References
44
Authors
7

Abstract

Due to the trial-and-error nature, it is typically challenging to apply RL algorithms to safety-critical real-world applications, such as autonomous driving, human-robot interaction, robot manipulation, etc, where such errors are not tolerable. Recently, safe RL (i.e. constrained RL) has emerged rapidly in the literature, in which the agents explore the environment while satisfying constraints. Due to the diversity of algorithms and tasks, it remains difficult to compare existing safe RL algorithms. To fill that gap, we introduce GUARD, a Generalized Unified SAfe Reinforcement Learning Development Benchmark. GUARD has several advantages compared to existing benchmarks. First, GUARD is a generalized benchmark with a wide variety of RL agents, tasks, and safety constraint specifications. Second, GUARD comprehensively covers state-of-the-art safe RL algorithms with self-contained implementations. Third, GUARD is highly customizable in tasks and algorithms. We present a comparison of state-of-the-art safe RL algorithms in various task settings using GUARD and establish baselines that future work can build on.

Cite this paper

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

APA 7

Zhao, W., Sun, Y., Feihan, L., Chen, R., Liu, R., Wei, T., & Liu, C. (2024). GUARD: A Safe Reinforcement Learning Benchmark. Transactions on machine learning research. https://doi.org/10.48550/arxiv.2305.13681

MLA 9

Zhao, Weiye, et al. “GUARD: A Safe Reinforcement Learning Benchmark.” Transactions on machine learning research, 2024. https://doi.org/10.48550/arxiv.2305.13681.

Chicago

Zhao, Weiye, Yifan Sun, Li, Feihan, Rui Chen, Ruixuan Liu, Tianhao Wei, and Changliu Liu. 2024. “GUARD: A Safe Reinforcement Learning Benchmark.” Transactions on machine learning research. https://doi.org/10.48550/arxiv.2305.13681.

Harvard

Zhao, W. et al. (2024) ‘GUARD: A Safe Reinforcement Learning Benchmark’, Transactions on machine learning research. doi:10.48550/arxiv.2305.13681.

IEEE

W. Zhao et al., “GUARD: A Safe Reinforcement Learning Benchmark,” Transactions on machine learning research, 2024, doi: 10.48550/arxiv.2305.13681.

BibTeX

@article{zhao2024guard,
  title     = {{GUARD: A Safe Reinforcement Learning Benchmark}},
  author    = {Zhao, Weiye and Sun, Yifan and Feihan, Li, and Chen, Rui and Liu, Ruixuan and Wei, Tianhao and Liu, Changliu},
  journal   = {Transactions on machine learning research},
  year      = {2024},
  doi       = {10.48550/arxiv.2305.13681},
  url       = {https://doi.org/10.48550/arxiv.2305.13681}
}

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

Citations by year

YearCitationsShare of the best year
202333
202433
202544
202644

Its field-weighted citation impact is 0.89: it has been cited 0.89 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

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

  • safe reinforcement learning
  • constrained reinforcement learning
  • benchmark
  • algorithm comparison
  • safety constraints
  • safety-critical applications
  • autonomous driving
  • human-robot interaction

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?

Zhao, W., Sun, Y., Feihan, L., Chen, R., Liu, R., Wei, T., & Liu, C. (2024). GUARD: A Safe Reinforcement Learning Benchmark. Transactions on machine learning research. https://doi.org/10.48550/arxiv.2305.13681

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 Transactions on machine learning research: sign in and open the full text from this page.

Who wrote this paper?

Weiye Zhao, Yifan Sun, Li, Feihan, Rui Chen, Ruixuan Liu, Tianhao Wei, Changliu Liu.

What is the DOI of this paper?

10.48550/arxiv.2305.13681, permanently at https://doi.org/10.48550/arxiv.2305.13681. 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.