Journal article · 2022 · Open access

TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning

Dohyeong Kim, Songhwai Oh

IEEE Robotics and Automation Letters, 7(2), 2621–2628 · Published 11 January 2022 · DOI 10.1109/lra.2022.3141829

Open PDFView at the publisherCite this paper

In brief

“TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning” is a 2022 journal article by Dohyeong Kim and Songhwai Oh, published in IEEE Robotics and Automation Letters. OpenAlex counts 39 citations as of 22 November 2026, which puts it in the top 8% of works published in 2022 by citations. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
39
Most cited in
2026 (11)
Field-weighted impact
1.58
References
25
Authors
2

Abstract

As safety is of paramount importance in robotics, reinforcement learning that reflects safety, calledsafe RL, has been studied extensively. In safe RL, we aim to find a policy which maximizes the desired return while satisfying the defined safety constraints. There are various types of constraints, among which constraints on conditional value at risk (CVaR) effectively lower the probability of failures caused by high costs since CVaR is a conditional expectation obtained above a certain percentile. In this paper, we propose a trust region-based safe RL method with CVaR constraints, calledTRC. We first derive the upper bound on CVaR and then approximate the upper bound in a differentiable form in a trust region. Using this approximation, a subproblem to get policy gradients is formulated, and policies are trained by iteratively solving the subproblem. TRC is evaluated through safe navigation tasks in simulations with various robots and a sim-to-real environment with a Jackal robot from Clearpath. Compared to other safe RL methods, the performance is improved by 1.93 times while the constraints are satisfied in all experiments.

Cite this paper

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

APA 7

Kim, D., & Oh, S. (2022). TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning. IEEE Robotics and Automation Letters, 7(2), 2621–2628. https://doi.org/10.1109/lra.2022.3141829

MLA 9

Kim, Dohyeong, and Songhwai Oh. “TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning.” IEEE Robotics and Automation Letters, vol. 7, no. 2, 2022, pp. 2621–2628. https://doi.org/10.1109/lra.2022.3141829.

Chicago

Kim, Dohyeong and Songhwai Oh. 2022. “TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning.” IEEE Robotics and Automation Letters 7 (2): 2621–2628. https://doi.org/10.1109/lra.2022.3141829.

Harvard

Kim, D. and Oh, S. (2022) ‘TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning’, IEEE Robotics and Automation Letters, 7(2), pp. 2621–2628. doi:10.1109/lra.2022.3141829.

IEEE

D. Kim and S. Oh, “TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning,” IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 2621–2628, 2022, doi: 10.1109/lra.2022.3141829.

BibTeX

@article{kim2022trust,
  title     = {{TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning}},
  author    = {Kim, Dohyeong and Oh, Songhwai},
  journal   = {IEEE Robotics and Automation Letters},
  year      = {2022},
  volume    = {7},
  number    = {2},
  pages     = {2621--2628},
  doi       = {10.1109/lra.2022.3141829},
  url       = {https://doi.org/10.1109/lra.2022.3141829}
}

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

Citations by year

YearCitationsShare of the best year
202222
202366
20241010
20251010
20261111

Its field-weighted citation impact is 1.58: it has been cited 1.58 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
  • conditional value at risk
  • trust region
  • policy optimization
  • sim-to-real transfer
  • robot navigation

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?

Kim, D., & Oh, S. (2022). TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning. IEEE Robotics and Automation Letters, 7(2), 2621–2628. https://doi.org/10.1109/lra.2022.3141829

How many times has this paper been cited?

39 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?

Dohyeong Kim, Songhwai Oh.

What is the DOI of this paper?

10.1109/lra.2022.3141829, permanently at https://doi.org/10.1109/lra.2022.3141829. 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.