Preprint · 2024 · Open access
Embedding Safety into RL: A New Take on Trust Region Methods
arXiv (Cornell University) · Published 5 November 2024 · DOI 10.48550/arxiv.2411.02957
In brief
“Embedding Safety into RL: A New Take on Trust Region Methods” is a 2024 preprint by Nikola Milošević and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 11 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
- 11
- Most cited in
- 2025 (6)
- References
- 28
- Authors
- 3
Abstract
Reinforcement Learning (RL) agents can solve diverse tasks but often exhibit unsafe behavior. Constrained Markov Decision Processes (CMDPs) address this by enforcing safety constraints, yet existing methods either sacrifice reward maximization or allow unsafe training. We introduce Constrained Trust Region Policy Optimization (C-TRPO), which reshapes the policy space geometry to ensure trust regions contain only safe policies, guaranteeing constraint satisfaction throughout training. We analyze its theoretical properties and connections to TRPO, Natural Policy Gradient (NPG), and Constrained Policy Optimization (CPO). Experiments show that C-TRPO reduces constraint violations while maintaining competitive returns.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Milošević, N., Johannes, M., & Scherf, N. (2024). Embedding Safety into RL: A New Take on Trust Region Methods. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2411.02957
MLA 9
Milošević, Nikola, et al. “Embedding Safety into RL: A New Take on Trust Region Methods.” arXiv (Cornell University), 2024. https://doi.org/10.48550/arxiv.2411.02957.
Chicago
Milošević, Nikola, Müller, Johannes, and Nico Scherf. 2024. “Embedding Safety into RL: A New Take on Trust Region Methods.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2411.02957.
Harvard
Milošević, N., Johannes, M. and Scherf, N. (2024) ‘Embedding Safety into RL: A New Take on Trust Region Methods’, arXiv (Cornell University). doi:10.48550/arxiv.2411.02957.
IEEE
N. Milošević, M. Johannes, and N. Scherf, “Embedding Safety into RL: A New Take on Trust Region Methods,” arXiv (Cornell University), 2024, doi: 10.48550/arxiv.2411.02957.
BibTeX
@misc{milosevic2024embedding,
title = {{Embedding Safety into RL: A New Take on Trust Region Methods}},
author = {Milošević, Nikola and Johannes, Müller, and Scherf, Nico},
howpublished = {arXiv (Cornell University)},
year = {2024},
doi = {10.48550/arxiv.2411.02957},
url = {https://doi.org/10.48550/arxiv.2411.02957}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- safe reinforcement learning
- trust region policy optimization
- constrained Markov decision process
- safety constraints
- constraint satisfaction
- natural policy gradient
- constrained policy optimization
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Milošević, N., Johannes, M., & Scherf, N. (2024). Embedding Safety into RL: A New Take on Trust Region Methods. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2411.02957
How many times has this paper been cited?
11 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?
Nikola Milošević, Müller, Johannes, Nico Scherf.
What is the DOI of this paper?
10.48550/arxiv.2411.02957, permanently at https://doi.org/10.48550/arxiv.2411.02957. 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.