{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T00:30:48Z","timestamp":1777768248710,"version":"3.51.4"},"reference-count":72,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100000082","name":"National Science Foundation Division of Graduate Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000082","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009455","name":"West Virginia University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009455","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000146","name":"National Science Foundation Division of Chemical Bioengineering Environmental and Transport Systems","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000146","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers & Chemical Engineering"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.compchemeng.2026.109610","type":"journal-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:17:56Z","timestamp":1771949876000},"page":"109610","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Reinforcement learning-based control via Y-wise Affine Neural Networks (YANNs)"],"prefix":"10.1016","volume":"209","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6835-320X","authenticated-orcid":false,"given":"Austin","family":"Braniff","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7937-5785","authenticated-orcid":false,"given":"Yuhe","family":"Tian","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.compchemeng.2026.109610_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.cej.2021.130993","article-title":"A reinforcement learning-based economic model predictive control framework for autonomous operation of chemical reactors","volume":"428","author":"Alhazmi","year":"2022","journal-title":"Chem. Eng. J."},{"key":"10.1016\/j.compchemeng.2026.109610_b2","article-title":"Dynamic risk-based process design and operational optimization via multi-parametric programming","volume":"7","author":"Ali","year":"2023","journal-title":"Digit. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2021.107489","article-title":"Deep reinforcement learning control of hydraulic fracturing","volume":"154","author":"Bangi","year":"2021","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2024.108826","article-title":"Development of algorithms for augmenting and replacing conventional process control using reinforcement learning","volume":"190","author":"Beahr","year":"2024","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b5","series-title":"Advances in Neural Information Processing Systems","article-title":"Safe model-based reinforcement learning with stability guarantees","volume":"vol. 30","author":"Berkenkamp","year":"2017"},{"issue":"9","key":"10.1016\/j.compchemeng.2026.109610_b6","doi-asserted-by":"crossref","first-page":"4966","DOI":"10.1021\/acs.iecr.4c03233","article-title":"Control-informed reinforcement learning for chemical processes","volume":"64","author":"Bloor","year":"2025","journal-title":"Ind. Eng. Chem. Res."},{"key":"10.1016\/j.compchemeng.2026.109610_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2023.108413","article-title":"Control invariant set enhanced safe reinforcement learning: improved sampling efficiency, guaranteed stability and robustness","volume":"179","author":"Bo","year":"2023","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b8","series-title":"Advances in Neural Information Processing Systems","article-title":"Reinforcement learning applied to linear quadratic regulation","volume":"vol.5","author":"Bradtke","year":"1992"},{"key":"10.1016\/j.compchemeng.2026.109610_b9","article-title":"Real-time process safety and systems decision-making toward safe and smart chemical manufacturing","volume":"15","author":"Braniff","year":"2025","journal-title":"Digit. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.conengprac.2024.106062","article-title":"A hierarchical multi-parametric programming approach for dynamic risk-based model predictive quality control","volume":"152","author":"Braniff","year":"2024","journal-title":"Control Eng. Pract."},{"key":"10.1016\/j.compchemeng.2026.109610_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2026.109589","article-title":"YANNs: Y-wise affine neural networks for exact and efficient representations of piecewise linear functions","volume":"208","author":"Braniff","year":"2026","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b12","doi-asserted-by":"crossref","unstructured":"Braniff, A., You, F., Tian, Y., 2025b. Enhanced Reinforcement Learning-driven Process Design via Quantum Machine Learning. In: The 35th European Symposium on Computer Aided Process Engineering. Ghent, Belgium, pp. 1403\u20131408.","DOI":"10.69997\/sct.149501"},{"key":"10.1016\/j.compchemeng.2026.109610_b13","series-title":"Openai gym","author":"Brockman","year":"2016"},{"issue":"Volume 5, 2022","key":"10.1016\/j.compchemeng.2026.109610_b14","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1146\/annurev-control-042920-020211","article-title":"Safe learning in robotics: From learning-based control to safe reinforcement learning","volume":"5","author":"Brunke","year":"2022","journal-title":"Annu. Rev. Control. Robot. Auton. Syst."},{"key":"10.1016\/j.compchemeng.2026.109610_b15","series-title":"Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control","first-page":"419","article-title":"Reinforcement learning","author":"Brunton","year":"2022"},{"key":"10.1016\/j.compchemeng.2026.109610_b16","series-title":"2021 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"1803","article-title":"Stabilizing neural control using self-learned almost Lyapunov critics","author":"Chang","year":"2021"},{"key":"10.1016\/j.compchemeng.2026.109610_b17","series-title":"Advances in Neural Information Processing Systems","article-title":"A Lyapunov-based approach to safe reinforcement learning","volume":"vol. 31","author":"Chow","year":"2018"},{"key":"10.1016\/j.compchemeng.2026.109610_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2023.108393","article-title":"Entropy-maximizing TD3-based reinforcement learning for adaptive PID control of dynamical systems","volume":"178","author":"Chowdhury","year":"2023","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b19","series-title":"Safe exploration in continuous action spaces","author":"Dalal","year":"2018"},{"issue":"6","key":"10.1016\/j.compchemeng.2026.109610_b20","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"},{"key":"10.1016\/j.compchemeng.2026.109610_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2022.107760","article-title":"Reinforcement learning approach to autonomous PID tuning","volume":"161","author":"Dogru","year":"2022","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b22","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.jprocont.2021.06.004","article-title":"Online reinforcement learning for a continuous space system with experimental validation","volume":"104","author":"Dogru","year":"2021","journal-title":"J. Process Control"},{"issue":"2","key":"10.1016\/j.compchemeng.2026.109610_b23","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."},{"issue":"1","key":"10.1016\/j.compchemeng.2026.109610_b24","doi-asserted-by":"crossref","first-page":"123","DOI":"10.3390\/pr11010123","article-title":"One-layer real-time optimization using reinforcement learning: a review with guidelines","volume":"11","author":"Faria","year":"2023","journal-title":"Processes"},{"issue":"11","key":"10.1016\/j.compchemeng.2026.109610_b25","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.2026.109610_b26","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."},{"issue":"2","key":"10.1016\/j.compchemeng.2026.109610_b27","doi-asserted-by":"crossref","first-page":"636","DOI":"10.1109\/TAC.2019.2913768","article-title":"Data-driven economic NMPC using reinforcement learning","volume":"65","author":"Gros","year":"2020","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.compchemeng.2026.109610_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2025.109248","article-title":"A practical reinforcement learning control design for nonlinear systems with input and output constraints","volume":"201","author":"Hassanpour","year":"2025","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2023.108511","article-title":"A practically implementable reinforcement learning control approach by leveraging offset-free model predictive control","volume":"181","author":"Hassanpour","year":"2024","journal-title":"Comput. Chem. Eng."},{"issue":"1","key":"10.1016\/j.compchemeng.2026.109610_b30","doi-asserted-by":"crossref","DOI":"10.1002\/aic.18245","article-title":"A practically implementable reinforcement learning-based process controller design","volume":"70","author":"Hassanpour","year":"2024","journal-title":"AIChE J."},{"key":"10.1016\/j.compchemeng.2026.109610_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2022.107727","article-title":"Reinforcement learning for online adaptation of model predictive controllers: application to a selective catalytic reduction unit","volume":"160","author":"Hedrick","year":"2022","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2020.106982","article-title":"A deep reinforcement learning approach for chemical production scheduling","volume":"141","author":"Hubbs","year":"2020","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2021.107527","article-title":"Twin actor twin delayed deep deterministic policy gradient (TATD3) learning for batch process control","volume":"155","author":"Joshi","year":"2021","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b34","series-title":"Proceedings of the Nineteenth International Conference on Machine Learning","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","author":"Kakade","year":"2002"},{"issue":"7976","key":"10.1016\/j.compchemeng.2026.109610_b35","doi-asserted-by":"crossref","first-page":"982","DOI":"10.1038\/s41586-023-06419-4","article-title":"Champion-level drone racing using deep reinforcement learning","volume":"620","author":"Kaufmann","year":"2023","journal-title":"Nature"},{"key":"10.1016\/j.compchemeng.2026.109610_b36","series-title":"Computer Aided Chemical Engineering","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1016\/B978-0-323-95879-0.50213-7","article-title":"PPOPT \u2013 multiparametric solver for explicit MPC","volume":"vol. 51","author":"Kenefake","year":"2022"},{"issue":"5","key":"10.1016\/j.compchemeng.2026.109610_b37","doi-asserted-by":"crossref","DOI":"10.1002\/aic.17601","article-title":"Safe model-based reinforcement learning for nonlinear optimal control with state and input constraints","volume":"68","author":"Kim","year":"2022","journal-title":"AIChE J."},{"issue":"10","key":"10.1016\/j.compchemeng.2026.109610_b38","doi-asserted-by":"crossref","DOI":"10.1002\/aic.16544","article-title":"Model-based reinforcement learning for nonlinear optimal control with practical asymptotic stability guarantees","volume":"66","author":"Kim","year":"2020","journal-title":"AIChE J."},{"key":"10.1016\/j.compchemeng.2026.109610_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2024.108601","article-title":"Model-based safe reinforcement learning for nonlinear systems under uncertainty with constraints tightening approach","volume":"183","author":"Kim","year":"2024","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b40","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2021.107465","article-title":"Model-based reinforcement learning and predictive control for two-stage optimal control of fed-batch bioreactor","volume":"154","author":"Kim","year":"2021","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.conengprac.2021.105046","article-title":"Deep reinforcement learning with shallow controllers: An experimental application to PID tuning","volume":"121","author":"Lawrence","year":"2022","journal-title":"Control Eng. Pract."},{"key":"10.1016\/j.compchemeng.2026.109610_b42","series-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2019"},{"key":"10.1016\/j.compchemeng.2026.109610_b43","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1109\/OJCSYS.2022.3209945","article-title":"Reinforcement learning with safety and stability guarantees during exploration for linear systems","volume":"1","author":"Marvi","year":"2022","journal-title":"IEEE Open J. Control. Syst."},{"issue":"7540","key":"10.1016\/j.compchemeng.2026.109610_b44","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.compchemeng.2026.109610_b45","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2021.107630","article-title":"Safe chance constrained reinforcement learning for batch process control","volume":"157","author":"Mowbray","year":"2022","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b46","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."},{"issue":"12","key":"10.1016\/j.compchemeng.2026.109610_b47","doi-asserted-by":"crossref","first-page":"2514","DOI":"10.3390\/pr10122514","article-title":"Reinforcement learning control with deep deterministic policy gradient algorithm for multivariable pH process","volume":"10","author":"Panjapornpon","year":"2022","journal-title":"Processes"},{"key":"10.1016\/j.compchemeng.2026.109610_b48","series-title":"Stochastic variance-reduced policy gradient","author":"Papini","year":"2018"},{"key":"10.1016\/j.compchemeng.2026.109610_b49","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2023.108232","article-title":"A practical reinforcement learning implementation approach for continuous process control","volume":"174","author":"Patel","year":"2023","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b50","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2019.106649","article-title":"Reinforcement learning for batch bioprocess optimization","volume":"133","author":"Petsagkourakis","year":"2020","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b51","series-title":"Proceedings of the 30th International Conference on Machine Learning","first-page":"307","article-title":"Safe policy iteration","author":"Pirotta","year":"2013"},{"key":"10.1016\/j.compchemeng.2026.109610_b52","series-title":"Multi-Parametric Optimization and Control","author":"Pistikopoulos","year":"2020"},{"key":"10.1016\/j.compchemeng.2026.109610_b53","series-title":"AC4mpc: actor-critic reinforcement learning for nonlinear model predictive control","author":"Reiter","year":"2024"},{"key":"10.1016\/j.compchemeng.2026.109610_b54","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2024.108988","article-title":"An integrated reinforcement learning framework for simultaneous generation, design, and control of chemical process flowsheets","volume":"194","author":"Reynoso-Donzelli","year":"2025","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b55","series-title":"Machine Learning and Knowledge Discovery in Databases","first-page":"35","article-title":"Local policy search in a convex space and conservative policy iteration as boosted policy search","author":"Scherrer","year":"2014"},{"key":"10.1016\/j.compchemeng.2026.109610_b56","series-title":"Trust region policy optimization","author":"Schulman","year":"2017"},{"key":"10.1016\/j.compchemeng.2026.109610_b57","series-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"10.1016\/j.compchemeng.2026.109610_b58","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.compchemeng.2019.05.029","article-title":"Reinforcement learning \u2013 overview of recent progress and implications for process control","volume":"127","author":"Shin","year":"2019","journal-title":"Comput. Chem. Eng."},{"issue":"7587","key":"10.1016\/j.compchemeng.2026.109610_b59","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"issue":"7676","key":"10.1016\/j.compchemeng.2026.109610_b60","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"Silver","year":"2017","journal-title":"Nature"},{"key":"10.1016\/j.compchemeng.2026.109610_b61","article-title":"Reinforcement learning for control of valves","volume":"4","author":"Siraskar","year":"2021","journal-title":"Mach. Learn. Appl."},{"issue":"10","key":"10.1016\/j.compchemeng.2026.109610_b62","doi-asserted-by":"crossref","DOI":"10.1002\/aic.16689","article-title":"Toward self-driving processes: A deep reinforcement learning approach to control","volume":"65","author":"Spielberg","year":"2019","journal-title":"AIChE J."},{"key":"10.1016\/j.compchemeng.2026.109610_b63","series-title":"Reinforcement Learning, Second Edition: An Introduction","author":"Sutton","year":"2018"},{"issue":"3","key":"10.1016\/j.compchemeng.2026.109610_b64","doi-asserted-by":"crossref","first-page":"4915","DOI":"10.1109\/LRA.2021.3070252","article-title":"Recovery RL: safe reinforcement learning with learned recovery zones","volume":"6","author":"Thananjeyan","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.compchemeng.2026.109610_b65","doi-asserted-by":"crossref","DOI":"10.1016\/j.ces.2020.116232","article-title":"Simultaneous design & control of a reactive distillation system \u2013 a parametric optimization & control approach","volume":"230","author":"Tian","year":"2021","journal-title":"Chem. Eng. Sci."},{"issue":"3","key":"10.1016\/j.compchemeng.2026.109610_b66","doi-asserted-by":"crossref","DOI":"10.1002\/aic.18306","article-title":"Control Lyapunov-barrier function-based safe reinforcement learning for nonlinear optimal control","volume":"70","author":"Wang","year":"2024","journal-title":"AIChE J."},{"issue":"12","key":"10.1016\/j.compchemeng.2026.109610_b67","doi-asserted-by":"crossref","first-page":"7272","DOI":"10.1109\/TCYB.2024.3485697","article-title":"Safe transfer-reinforcement-learning-based optimal control of nonlinear systems","volume":"54","author":"Wang","year":"2024","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.compchemeng.2026.109610_b68","series-title":"Computer Aided Chemical Engineering","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/B978-0-443-28824-1.50042-9","article-title":"A virtual entity of the digital twin based on deep reinforcement learning model for dynamic scheduling process","volume":"vol. 53","author":"Wang","year":"2024"},{"key":"10.1016\/j.compchemeng.2026.109610_b69","article-title":"A tutorial review of policy iteration methods in reinforcement learning for nonlinear optimal control","volume":"15","author":"Wang","year":"2025","journal-title":"Digit. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109610_b70","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.arcontrol.2021.10.006","article-title":"Reinforcement learning for batch process control: Review and perspectives","volume":"52","author":"Yoo","year":"2021","journal-title":"Annu. Rev. Control."},{"issue":"8","key":"10.1016\/j.compchemeng.2026.109610_b71","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"},{"issue":"7","key":"10.1016\/j.compchemeng.2026.109610_b72","doi-asserted-by":"crossref","DOI":"10.1002\/aic.18840","article-title":"Reinforcement learning for optimal control of stochastic nonlinear systems","volume":"71","author":"Zhu","year":"2025","journal-title":"AIChE J."}],"container-title":["Computers & Chemical Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0098135426000633?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0098135426000633?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T15:55:21Z","timestamp":1777478121000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0098135426000633"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":72,"alternative-id":["S0098135426000633"],"URL":"https:\/\/doi.org\/10.1016\/j.compchemeng.2026.109610","relation":{},"ISSN":["0098-1354"],"issn-type":[{"value":"0098-1354","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Reinforcement learning-based control via Y-wise Affine Neural Networks (YANNs)","name":"articletitle","label":"Article Title"},{"value":"Computers & Chemical Engineering","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compchemeng.2026.109610","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":"109610"}}