{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T14:20:39Z","timestamp":1783174839987,"version":"3.54.6"},"reference-count":30,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers & Chemical Engineering"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.compchemeng.2026.109775","type":"journal-article","created":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:41:01Z","timestamp":1783147261000},"page":"109775","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Safe offline-to-online reinforcement learning via execution-time risk-aware selection for industrial process control"],"prefix":"10.1016","volume":"214","author":[{"given":"Jiyang","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2698-2770","authenticated-orcid":false,"given":"Na","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.compchemeng.2026.109775_b1","series-title":"Constrained policy optimization","author":"Achiam","year":"2017"},{"key":"10.1016\/j.compchemeng.2026.109775_b2","doi-asserted-by":"crossref","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\u00f6nighofer, B., Niekum, S., Topcu, U., 2018. Safe Reinforcement Learning via Shielding. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp. 2669\u20132678.","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"10.1016\/j.compchemeng.2026.109775_b3","series-title":"Constrained Markov Decision Processes","author":"Altman","year":"1999"},{"key":"10.1016\/j.compchemeng.2026.109775_b4","series-title":"Control barrier functions: Theory and applications","author":"Ames","year":"2019"},{"key":"10.1016\/j.compchemeng.2026.109775_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2025.109515","article-title":"A survey and tutorial of reinforcement learning methods in process systems engineering","volume":"206","author":"Bloor","year":"2026","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109775_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.jprocont.2025.103535","article-title":"An offline-to-online reinforcement learning framework with trajectory-guided exploration for industrial process control","volume":"154","author":"Chen","year":"2025","journal-title":"J. Process Control"},{"key":"10.1016\/j.compchemeng.2026.109775_b7","series-title":"Advances in Neural Information Processing Systems","first-page":"1522","article-title":"Risk-sensitive and robust decision-making: a CVaR optimization approach","author":"Chow","year":"2015"},{"key":"10.1016\/j.compchemeng.2026.109775_b8","first-page":"16091","article-title":"Probabilistic shielding for safe reinforcement learning","volume":"vol. 39, no. 15","author":"Hamel-De le Court","year":"2025"},{"issue":"6","key":"10.1016\/j.compchemeng.2026.109775_b9","doi-asserted-by":"crossref","first-page":"1791","DOI":"10.3390\/pr13061791","article-title":"Recent advances in reinforcement learning for chemical process control","volume":"13","author":"Devarakonda","year":"2025","journal-title":"Processes"},{"issue":"2","key":"10.1016\/j.compchemeng.2026.109775_b10","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1109\/JAS.2024.124227","article-title":"Reinforcement learning in process industries: Review and perspective","volume":"11","author":"Dogru","year":"2024","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"10.1016\/j.compchemeng.2026.109775_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2025.109535","article-title":"Safe deployment of offline reinforcement learning via input convex action correction","volume":"206","author":"Durkin","year":"2026","journal-title":"Comput. Chem. Eng."},{"issue":"11","key":"10.1016\/j.compchemeng.2026.109775_b12","doi-asserted-by":"crossref","first-page":"2311","DOI":"10.3390\/pr10112311","article-title":"Where reinforcement learning meets process control: Review and guidelines","volume":"10","author":"Faria","year":"2022","journal-title":"Processes"},{"issue":"1","key":"10.1016\/j.compchemeng.2026.109775_b13","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u0131a","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.compchemeng.2026.109775_b14","series-title":"International Conference on Autonomous Agents and Multiagent Systems","doi-asserted-by":"crossref","first-page":"2291","DOI":"10.65109\/GWPH6856","article-title":"Leveraging approximate model-based shielding for probabilistic safety guarantees in continuous environments","author":"Goodall","year":"2024"},{"key":"10.1016\/j.compchemeng.2026.109775_b15","series-title":"Proceedings of the 27th International Conference on Artificial Intelligence and Statistics","first-page":"280","article-title":"A primal-dual-critic algorithm for offline constrained reinforcement learning","volume":"vol. 238","author":"Hong","year":"2024"},{"key":"10.1016\/j.compchemeng.2026.109775_b16","series-title":"Proceedings of Machine Learning Research","first-page":"1","article-title":"Realizable continuous-space shields for safe reinforcement learning","author":"Kim","year":"2025"},{"issue":"11","key":"10.1016\/j.compchemeng.2026.109775_b17","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1145\/3715958","article-title":"Shields for safe reinforcement learning","volume":"68","author":"K\u00f6nighofer","year":"2025","journal-title":"Commun. ACM"},{"key":"10.1016\/j.compchemeng.2026.109775_b18","series-title":"A survey of safe reinforcement learning and constrained MDPs: A technical survey on single-agent and multi-agent safety","author":"Kushwaha","year":"2025"},{"key":"10.1016\/j.compchemeng.2026.109775_b19","article-title":"Datasets and benchmarks for offline safe reinforcement learning","author":"Liu","year":"2024","journal-title":"J. Data-Centric Mach. Learn. Res."},{"key":"10.1016\/j.compchemeng.2026.109775_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2020.106886","article-title":"A review on reinforcement learning: Introduction and applications in industrial process control","volume":"139","author":"Nian","year":"2020","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109775_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2023.108558","article-title":"Quantitative comparison of reinforcement learning and data-driven model predictive control for chemical and biological processes","volume":"181","author":"Oh","year":"2024","journal-title":"Comput. Chem. Eng."},{"issue":"1","key":"10.1016\/j.compchemeng.2026.109775_b22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s12555-024-0990-1","article-title":"Reinforcement learning for process control: Review and benchmark problems","volume":"23","author":"Park","year":"2025","journal-title":"Int. J. Control. Autom. Syst."},{"key":"10.1016\/j.compchemeng.2026.109775_b23","article-title":"A survey on offline reinforcement learning: Taxonomy, review, and open problems","author":"Prudencio","year":"2023","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.compchemeng.2026.109775_b24","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.compchemeng.2019.05.029","article-title":"Reinforcement learning\u2014Overview of recent progress and implications for process control","volume":"127","author":"Shin","year":"2019","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109775_b25","series-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"10.1016\/j.compchemeng.2026.109775_b26","series-title":"Advances in Neural Information Processing Systems","first-page":"1468","article-title":"Policy gradient for coherent risk measures","author":"Tamar","year":"2015"},{"key":"10.1016\/j.compchemeng.2026.109775_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2021.109597","article-title":"A predictive safety filter for learning-based control of constrained nonlinear dynamical systems","volume":"129","author":"Wabersich","year":"2021","journal-title":"Automatica"},{"key":"10.1016\/j.compchemeng.2026.109775_b28","series-title":"Off-policy primal-dual safe reinforcement learning","author":"Wu","year":"2024"},{"issue":"8","key":"10.1016\/j.compchemeng.2026.109775_b29","doi-asserted-by":"crossref","first-page":"3638","DOI":"10.1109\/TAC.2020.3024161","article-title":"Safe reinforcement learning using robust MPC","volume":"66","author":"Zanon","year":"2021","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.compchemeng.2026.109775_b30","doi-asserted-by":"crossref","first-page":"26631","DOI":"10.52202\/068431-1931","article-title":"Smpl: Simulated industrial manufacturing and process control learning environments","volume":"35","author":"Zhang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"}],"container-title":["Computers & Chemical Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0098135426002280?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0098135426002280?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T14:01:03Z","timestamp":1783173663000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0098135426002280"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":30,"alternative-id":["S0098135426002280"],"URL":"https:\/\/doi.org\/10.1016\/j.compchemeng.2026.109775","relation":{"is-supplemented-by":[{"id-type":"uri","id":"https:\/\/github.com\/lab1206\/soorl-ras","asserted-by":"subject"}]},"ISSN":["0098-1354"],"issn-type":[{"value":"0098-1354","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Safe offline-to-online reinforcement learning via execution-time risk-aware selection for industrial process control","name":"articletitle","label":"Article Title"},{"value":"Computers & Chemical Engineering","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compchemeng.2026.109775","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109775"}}