{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T22:27:59Z","timestamp":1786487279970,"version":"3.56.0"},"reference-count":31,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012550","name":"Nemzeti Kutat\u00e1si, Fejleszt\u00e9si \u00e9s Innovaci\u00f3s Alap","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012550","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003825","name":"Magyar Tudom\u00e1nyos Akad\u00e9mia","doi-asserted-by":"publisher","award":["B0\/00439\/25\/6"],"award-info":[{"award-number":["B0\/00439\/25\/6"]}],"id":[{"id":"10.13039\/501100003825","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003825","name":"Magyar Tudom\u00e1nyos Akad\u00e9mia","doi-asserted-by":"publisher","award":["2024-2.1.2-EK\\u00D6P-KDP-2024-00017"],"award-info":[{"award-number":["2024-2.1.2-EK\\u00D6P-KDP-2024-00017"]}],"id":[{"id":"10.13039\/501100003825","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005881","name":"Ministry of Culture and Innovation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005881","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":[[2026,9]]},"DOI":"10.1016\/j.compchemeng.2026.109704","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T13:39:15Z","timestamp":1779197955000},"page":"109704","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Reactor runaway aware RL Agents for safe reactor operation"],"prefix":"10.1016","volume":"212","author":[{"given":"Bal\u00e1zs","family":"Fricz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1102-8234","authenticated-orcid":false,"given":"Kinga","family":"Szatm\u00e1ri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1881-4216","authenticated-orcid":false,"given":"S\u00e1ndor","family":"N\u00e9meth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lajos","family":"Nagy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0053-8962","authenticated-orcid":false,"given":"Wenshuai","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6550-5101","authenticated-orcid":false,"given":"Alex","family":"Kummer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.compchemeng.2026.109704_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2024.108739","article-title":"Reinforcement learning for the optimization and online control of emulsion polymerization reactors: Particle morphology","volume":"187","author":"Ballard","year":"2024","journal-title":"Comput. Chem. Eng."},{"issue":"2","key":"10.1016\/j.compchemeng.2026.109704_b2","first-page":"423","article-title":"Reinforcement learning: An introduction. By Richard\u2019s Sutton","volume":"6","author":"Barto","year":"2021","journal-title":"SIAM Rev."},{"key":"10.1016\/j.compchemeng.2026.109704_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.jlp.2019.103938","article-title":"Analysis of thermal runaway events in French chemical industry","volume":"62","author":"Dakkoune","year":"2019","journal-title":"J. Loss Prev. Process. Ind."},{"key":"10.1016\/j.compchemeng.2026.109704_b4","series-title":"International Conference on Machine Learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"key":"10.1016\/j.compchemeng.2026.109704_b5","series-title":"International Conference on Machine Learning","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.compchemeng.2026.109704_b6","series-title":"Intelligent Control Systems: An Introduction with Examples","author":"Hangos","year":"2001"},{"key":"10.1016\/j.compchemeng.2026.109704_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2024.108588","article-title":"A reinforcement learning-based temperature control of fluidized bed reactor in gas-phase polyethylene process","volume":"183","author":"Hong","year":"2024","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109704_b8","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."},{"issue":"1","key":"10.1016\/j.compchemeng.2026.109704_b9","first-page":"11","article-title":"The importance of intelligent control systems","volume":"1","author":"Kavitha","year":"2019","journal-title":"Int. J. Hum. Comput. Stud."},{"key":"10.1016\/j.compchemeng.2026.109704_b10","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1016\/j.ces.2018.11.008","article-title":"Completion of thermal runaway criteria: Two new criteria to define runaway limits","volume":"196","author":"Kummer","year":"2019","journal-title":"Chem. Eng. Sci."},{"key":"10.1016\/j.compchemeng.2026.109704_b11","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1016\/j.psep.2020.09.059","article-title":"What do we know already about reactor runaway?\u2013A review","volume":"147","author":"Kummer","year":"2021","journal-title":"Process. Saf. Environ. Prot."},{"key":"10.1016\/j.compchemeng.2026.109704_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2019.106694","article-title":"Semi-batch reactor control with NMPC avoiding thermal runaway","volume":"134","author":"Kummer","year":"2020","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109704_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2021.117541","article-title":"A data-driven output voltage control of solid oxide fuel cell using multi-agent deep reinforcement learning","volume":"304","author":"Li","year":"2021","journal-title":"Appl. Energy"},{"key":"10.1016\/j.compchemeng.2026.109704_b14","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.neunet.2022.10.016","article-title":"Accelerating reinforcement learning with case-based model-assisted experience augmentation for process control","volume":"158","author":"Lin","year":"2023","journal-title":"Neural Netw."},{"issue":"9\u201310","key":"10.1016\/j.compchemeng.2026.109704_b15","doi-asserted-by":"crossref","first-page":"1597","DOI":"10.1049\/rpg2.12997","article-title":"Research on temperature control of proton exchange membrane electrolysis cell based on MO-TD3","volume":"18","author":"Ma","year":"2024","journal-title":"IET Renew. Power Gener."},{"key":"10.1016\/j.compchemeng.2026.109704_b16","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.jprocont.2018.11.004","article-title":"Continuous control of a polymerization system with deep reinforcement learning","volume":"75","author":"Ma","year":"2019","journal-title":"J. Process Control"},{"key":"10.1016\/j.compchemeng.2026.109704_b17","article-title":"Robust control for anaerobic digestion systems of Tequila vinasses under uncertainty: A deep deterministic policy gradient algorithm","volume":"3","author":"Mendiola-Rodriguez","year":"2022","journal-title":"Digit. Chem. Eng."},{"issue":"1","key":"10.1016\/j.compchemeng.2026.109704_b18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000086","article-title":"Model-based reinforcement learning: A survey","volume":"16","author":"Moerland","year":"2023","journal-title":"Found. Trends Mach. Learn."},{"key":"10.1016\/j.compchemeng.2026.109704_b19","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.2026.109704_b20","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.2026.109704_b21","article-title":"Real-world implementation of offline reinforcement learning for process control in industrial dividing wall column","author":"Park","year":"2025","journal-title":"Comput. Chem. Eng."},{"issue":"10","key":"10.1016\/j.compchemeng.2026.109704_b22","doi-asserted-by":"crossref","first-page":"3114","DOI":"10.1002\/bit.28784","article-title":"Reinforcement learning based temperature control of a fermentation bioreactor for ethanol production","volume":"121","author":"Rajasekhar","year":"2024","journal-title":"Biotechnol. Bioeng."},{"key":"10.1016\/j.compchemeng.2026.109704_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2022.107819","article-title":"Multi-agent reinforcement learning-based exploration of optimal operation strategies of semi-batch reactors","volume":"162","author":"Sass","year":"2022","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109704_b24","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.neucom.2019.11.022","article-title":"Optimizing zinc electrowinning processes with current switching via deep deterministic policy gradient learning","volume":"380","author":"Shi","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.compchemeng.2026.109704_b25","series-title":"Thermal Safety of Chemical Processes: Risk Assessment and Process Design","author":"Stoessel","year":"2021"},{"issue":"7","key":"10.1016\/j.compchemeng.2026.109704_b26","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1205\/cherd.05221","article-title":"Safety and runaway prevention in batch and semibatch reactors\u2014A review","volume":"84","author":"Westerterp","year":"2006","journal-title":"Chem. Eng. Res. Des."},{"key":"10.1016\/j.compchemeng.2026.109704_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.coche.2023.100986","article-title":"Runaway criteria for predicting the thermal behavior of chemical reactors","volume":"43","author":"Yang","year":"2024","journal-title":"Curr. Opin. Chem. Eng."},{"issue":"11","key":"10.1016\/j.compchemeng.2026.109704_b28","doi-asserted-by":"crossref","first-page":"6227","DOI":"10.1002\/cjce.24878","article-title":"Multi-agent reinforcement learning for process control: Exploring the intersection between fields of reinforcement learning, control theory, and game theory","volume":"101","author":"Yifei","year":"2023","journal-title":"Can. J. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109704_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2020.107133","article-title":"Reinforcement learning based optimal control of batch processes using Monte-Carlo deep deterministic policy gradient with phase segmentation","volume":"144","author":"Yoo","year":"2021","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109704_b30","doi-asserted-by":"crossref","first-page":"24611","DOI":"10.52202\/068431-1787","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compchemeng.2026.109704_b31","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.compchemeng.2019.03.003","article-title":"Operational safety of chemical processes via safeness-index based MPC: Two large-scale case studies","volume":"125","author":"Zhang","year":"2019","journal-title":"Comput. Chem. Eng."}],"container-title":["Computers & Chemical Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0098135426001572?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0098135426001572?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T21:31:37Z","timestamp":1786483897000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0098135426001572"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":31,"alternative-id":["S0098135426001572"],"URL":"https:\/\/doi.org\/10.1016\/j.compchemeng.2026.109704","relation":{},"ISSN":["0098-1354"],"issn-type":[{"value":"0098-1354","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Reactor runaway aware RL Agents for safe reactor operation","name":"articletitle","label":"Article Title"},{"value":"Computers & Chemical Engineering","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compchemeng.2026.109704","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"109704"}}