---
DOAJ_listed: '1'
OA_place: publisher
OA_type: gold
PlanS_conform: '1'
_id: '22999'
abstract:
- lang: eng
  text: The safety of Reinforcement Learning (RL)-based controllers has become a prominent
    research area in recent years, with various approaches being proposed to address
    this critical issue. Runtime Safety Assurance (RSA) methods for RL, such as Shielded
    RL, provide formal safety guarantees by preventing agents from taking unsafe actions
    and suggesting safe alternatives when necessary. However, previous surveys and
    reviews on RSA for RL have not thoroughly analysed the challenges and applications
    within the industrial sector. This study builds on existing state-of-the-art research
    on Shielded RL methods, emphasising its contributions to industrial applications
    and offering a domain-specific categorisation. This categorisation highlights
    the primary industrial domains utilising Shielded RL, detailing the optimised
    functions achieved by RL and the safety functions ensured by the shield. Additionally,
    the study presents a categorisation based on environmental features, enabling
    readers to assess the complexity of the problems addressed by the techniques studied.
    The shield’s attributes are analysed for each work, identifying key trends in
    their application, including their adaptability to new scenarios. Finally, a basic
    categorisation model for Shielded RL approaches, grounded in industrial safety
    standards, is introduced. This model serves as a baseline for future studies aiming
    to evaluate the maturity level of the works reviewed.
acknowledgement: "This work was supported in part by the SAFEXPLAIN project under
  Grant 101069595.\r\nThis work was supported in part by the ROBOCONS project under
  Grant 101235566, from the European Union‘s HORIZON-CL5-2024-D4-02 research and innovation
  programme.\r\nThis work was supported in part by the Austrian Science Fund (FWF)
  - Reference 10.55776/COE12.\r\nThis work was supported in part by the Intelligent
  Systems for Industrial Systems research group of Mondragon Unibertsitatea - Reference
  IT1870-26. Department of Science, Universities and Innovation of the Basque Government.\r\nThis
  work was supported in part by the European Research Council under Grant No.: ERC-2020-AdG
  101020093. This work was also supported by the ISTA Responsible AI Program, made
  possible through the support of Garrett Camp and the Camp Foundation ."
article_number: '200729'
article_processing_charge: Yes
article_type: review
author:
- first_name: Haritz
  full_name: Odriozola-Olalde, Haritz
  last_name: Odriozola-Olalde
- first_name: Filip
  full_name: Cano Cordoba, Filip
  id: 708cad98-e86a-11ef-8098-bdae2d7c6af1
  last_name: Cano Cordoba
  orcid: 0000-0002-0783-904X
- first_name: Bettina
  full_name: Könighofer, Bettina
  last_name: Könighofer
- first_name: Nestor
  full_name: Arana-Arexolaleiba, Nestor
  last_name: Arana-Arexolaleiba
- first_name: Maider
  full_name: Zamalloa, Maider
  last_name: Zamalloa
- first_name: Jon
  full_name: Perez-Cerrolaza, Jon
  last_name: Perez-Cerrolaza
citation:
  ama: 'Odriozola-Olalde H, Cano Cordoba F, Könighofer B, Arana-Arexolaleiba N, Zamalloa
    M, Perez-Cerrolaza J. Shielded reinforcement learning for industrial applications:
    A systematic literature survey. <i>Intelligent Systems with Applications</i>.
    2026;32. doi:<a href="https://doi.org/10.1016/j.iswa.2026.200729">10.1016/j.iswa.2026.200729</a>'
  apa: 'Odriozola-Olalde, H., Cano Cordoba, F., Könighofer, B., Arana-Arexolaleiba,
    N., Zamalloa, M., &#38; Perez-Cerrolaza, J. (2026). Shielded reinforcement learning
    for industrial applications: A systematic literature survey. <i>Intelligent Systems
    with Applications</i>. Elsevier. <a href="https://doi.org/10.1016/j.iswa.2026.200729">https://doi.org/10.1016/j.iswa.2026.200729</a>'
  chicago: 'Odriozola-Olalde, Haritz, Filip Cano Cordoba, Bettina Könighofer, Nestor
    Arana-Arexolaleiba, Maider Zamalloa, and Jon Perez-Cerrolaza. “Shielded Reinforcement
    Learning for Industrial Applications: A Systematic Literature Survey.” <i>Intelligent
    Systems with Applications</i>. Elsevier, 2026. <a href="https://doi.org/10.1016/j.iswa.2026.200729">https://doi.org/10.1016/j.iswa.2026.200729</a>.'
  ieee: 'H. Odriozola-Olalde, F. Cano Cordoba, B. Könighofer, N. Arana-Arexolaleiba,
    M. Zamalloa, and J. Perez-Cerrolaza, “Shielded reinforcement learning for industrial
    applications: A systematic literature survey,” <i>Intelligent Systems with Applications</i>,
    vol. 32. Elsevier, 2026.'
  ista: 'Odriozola-Olalde H, Cano Cordoba F, Könighofer B, Arana-Arexolaleiba N, Zamalloa
    M, Perez-Cerrolaza J. 2026. Shielded reinforcement learning for industrial applications:
    A systematic literature survey. Intelligent Systems with Applications. 32, 200729.'
  mla: 'Odriozola-Olalde, Haritz, et al. “Shielded Reinforcement Learning for Industrial
    Applications: A Systematic Literature Survey.” <i>Intelligent Systems with Applications</i>,
    vol. 32, 200729, Elsevier, 2026, doi:<a href="https://doi.org/10.1016/j.iswa.2026.200729">10.1016/j.iswa.2026.200729</a>.'
  short: H. Odriozola-Olalde, F. Cano Cordoba, B. Könighofer, N. Arana-Arexolaleiba,
    M. Zamalloa, J. Perez-Cerrolaza, Intelligent Systems with Applications 32 (2026).
corr_author: '1'
das_tickbox: '1'
dataavailabilitystatement: No data was used for the research described in the article.
date_created: 2026-09-27T22:01:51Z
date_published: 2026-09-18T00:00:00Z
date_updated: 2026-10-07T06:25:37Z
day: '18'
ddc:
- '000'
department:
- _id: ToHe
doi: 10.1016/j.iswa.2026.200729
ec_funded: 1
fulldoi: https://doi.org/10.1016/j.iswa.2026.200729
has_accepted_license: '1'
intvolume: '        32'
keyword:
- Reinforcement learning
- Runtime safety assurance
- Shield
- Safety
- Industrial application
language:
- iso: eng
license: https://creativecommons.org/licenses/by/4.0/
main_file_link:
- open_access: '1'
  url: https://doi.org/10.1016/j.iswa.2026.200729
month: '09'
oa: 1
oa_version: Published Version
project:
- _id: 62781420-2b32-11ec-9570-8d9b63373d4d
  call_identifier: H2020
  grant_number: '101020093'
  name: Vigilant Algorithmic Monitoring of Software
publication: Intelligent Systems with Applications
publication_identifier:
  issn:
  - 2667-3053
publication_status: epub_ahead
publisher: Elsevier
quality_controlled: '1'
researchdata_availability: no
scopus_import: '1'
status: public
supplementarymaterial: no
title: 'Shielded reinforcement learning for industrial applications: A systematic
  literature survey'
tmp:
  image: /images/cc_by.png
  legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode
  name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)
  short: CC BY (4.0)
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 32
year: '2026'
...