[{"author":[{"last_name":"Odriozola-Olalde","full_name":"Odriozola-Olalde, Haritz","first_name":"Haritz"},{"id":"708cad98-e86a-11ef-8098-bdae2d7c6af1","orcid":"0000-0002-0783-904X","last_name":"Cano Cordoba","first_name":"Filip","full_name":"Cano Cordoba, Filip"},{"full_name":"Könighofer, Bettina","first_name":"Bettina","last_name":"Könighofer"},{"last_name":"Arana-Arexolaleiba","full_name":"Arana-Arexolaleiba, Nestor","first_name":"Nestor"},{"last_name":"Zamalloa","first_name":"Maider","full_name":"Zamalloa, Maider"},{"last_name":"Perez-Cerrolaza","first_name":"Jon","full_name":"Perez-Cerrolaza, Jon"}],"has_accepted_license":"1","date_created":"2026-09-27T22:01:51Z","license":"https://creativecommons.org/licenses/by/4.0/","corr_author":"1","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","fulldoi":"https://doi.org/10.1016/j.iswa.2026.200729","quality_controlled":"1","month":"09","supplementarymaterial":"no","oa_version":"Published Version","keyword":["Reinforcement learning","Runtime safety assurance","Shield","Safety","Industrial application"],"article_processing_charge":"Yes","publication":"Intelligent Systems with Applications","dataavailabilitystatement":"No data was used for the research described in the article.","article_type":"review","publication_status":"epub_ahead","ddc":["000"],"language":[{"iso":"eng"}],"department":[{"_id":"ToHe"}],"publisher":"Elsevier","day":"18","scopus_import":"1","project":[{"_id":"62781420-2b32-11ec-9570-8d9b63373d4d","name":"Vigilant Algorithmic Monitoring of Software","grant_number":"101020093","call_identifier":"H2020"}],"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 .","year":"2026","main_file_link":[{"open_access":"1","url":"https://doi.org/10.1016/j.iswa.2026.200729"}],"researchdata_availability":"no","PlanS_conform":"1","citation":{"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>","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.","short":"H. Odriozola-Olalde, F. Cano Cordoba, B. Könighofer, N. Arana-Arexolaleiba, M. Zamalloa, J. Perez-Cerrolaza, Intelligent Systems with Applications 32 (2026).","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>.","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>","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>."},"das_tickbox":"1","ec_funded":1,"intvolume":"        32","DOAJ_listed":"1","article_number":"200729","volume":32,"date_updated":"2026-10-07T06:25:37Z","status":"public","type":"journal_article","doi":"10.1016/j.iswa.2026.200729","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","short":"CC BY (4.0)"},"date_published":"2026-09-18T00:00:00Z","_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."}],"oa":1,"title":"Shielded reinforcement learning for industrial applications: A systematic literature survey","publication_identifier":{"issn":["2667-3053"]},"OA_place":"publisher","OA_type":"gold"}]