{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,16]],"date-time":"2026-08-16T14:25:57Z","timestamp":1786890357801,"version":"build-2736575974"},"reference-count":65,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.engappai.2026.115524","type":"journal-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T08:58:44Z","timestamp":1782982724000},"page":"115524","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P4","title":["Deep reinforcement learning in applied control: Challenges, analysis, and insights"],"prefix":"10.1016","volume":"181","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2649-6991","authenticated-orcid":false,"given":"Klinsmann","family":"Agyei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6004-676X","authenticated-orcid":false,"given":"Pouria","family":"Sarhadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3233-5847","authenticated-orcid":false,"given":"Daniel","family":"Polani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.115524_b1","series-title":"Optimal Control: Linear Quadratic Methods","author":"Anderson","year":"2007"},{"issue":"1","key":"10.1016\/j.engappai.2026.115524_b2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/0278364919887447","article-title":"Learning dexterous in-hand manipulation","volume":"39","author":"Andrychowicz","year":"2020","journal-title":"Int. J. Robot. Res."},{"key":"10.1016\/j.engappai.2026.115524_b3","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.arcontrol.2020.05.001","article-title":"Autonomy and metrics of autonomy","volume":"49","author":"Antsaklis","year":"2020","journal-title":"Annu. Rev. Control."},{"issue":"6","key":"10.1016\/j.engappai.2026.115524_b4","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","article-title":"Deep reinforcement learning: A brief survey","volume":"34","author":"Arulkumaran","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"issue":"1","key":"10.1016\/j.engappai.2026.115524_b5","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/S0947-3580(00)70906-X","article-title":"Limitations on control system performance","volume":"6","author":"\u00c5str\u00f6m","year":"2000","journal-title":"Eur. J. Control"},{"issue":"15","key":"10.1016\/j.engappai.2026.115524_b6","doi-asserted-by":"crossref","first-page":"5504","DOI":"10.1021\/acs.iecr.0c05678","article-title":"A deep reinforcement learning approach to improve the learning performance in process control","volume":"60","author":"Bao","year":"2021","journal-title":"Ind. Eng. Chem. Res."},{"key":"10.1016\/j.engappai.2026.115524_b7","series-title":"International Conference on Machine Learning","first-page":"449","article-title":"A distributional perspective on reinforcement learning","author":"Bellemare","year":"2017"},{"issue":"3","key":"10.1016\/j.engappai.2026.115524_b8","first-page":"17","article-title":"A brief history of automatic control","volume":"16","author":"Bennett","year":"2002","journal-title":"IEEE Control Syst. Mag."},{"key":"10.1016\/j.engappai.2026.115524_b9","series-title":"Process Control: Modeling, Design, and Simulation","author":"Bequette","year":"2003"},{"key":"10.1016\/j.engappai.2026.115524_b10","series-title":"Dota 2 with large-scale deep reinforcement learning","author":"Berner","year":"2019"},{"key":"10.1016\/j.engappai.2026.115524_b11","series-title":"Datasheet crazyflie 2.1 - rev 3","author":"Bitcraze","year":"2021"},{"key":"10.1016\/j.engappai.2026.115524_b12","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.arcontrol.2018.09.005","article-title":"Reinforcement learning for control: Performance, stability, and deep approximators","volume":"46","author":"Bu\u015foniu","year":"2018","journal-title":"Annu. Rev. Control."},{"key":"10.1016\/j.engappai.2026.115524_b13","doi-asserted-by":"crossref","unstructured":"Cai, Y., Zhang, C., Zhao, H., Zhao, L., Bian, J., 2023. Curriculum offline reinforcement learning. In: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems. pp. 1221\u20131229.","DOI":"10.65109\/XIYU8267"},{"issue":"4","key":"10.1016\/j.engappai.2026.115524_b14","doi-asserted-by":"crossref","first-page":"816","DOI":"10.1109\/JAS.2024.124323","article-title":"Goal-oriented control systems (GOCS): From how to what","volume":"11","author":"Chen","year":"2024","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"10.1016\/j.engappai.2026.115524_b15","series-title":"International Conference on Learning Representations","article-title":"Randomized ensembled double Q-learning: Learning fast without a model","author":"Chen","year":"2021"},{"issue":"9","key":"10.1016\/j.engappai.2026.115524_b16","doi-asserted-by":"crossref","first-page":"2028","DOI":"10.1002\/cjce.24508","article-title":"A survey and comparative evaluation of actor-critic methods in process control","volume":"100","author":"Dutta","year":"2022","journal-title":"Can. J. Chem. Eng."},{"key":"10.1016\/j.engappai.2026.115524_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2023.108386","article-title":"A reinforcement learning-based transformed inverse model strategy for nonlinear process control","volume":"178","author":"Dutta","year":"2023","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.engappai.2026.115524_b18","unstructured":"Engstrom, L., Ilyas, A., Santurkar, S., Tsipras, D., Janoos, F., Rudolph, L., Madry, A., 2019. Implementation matters in deep rl: A case study on ppo and trpo. In: International Conference on Learning Representations."},{"key":"10.1016\/j.engappai.2026.115524_b19","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2024.3396025","article-title":"Learning to fly in seconds","author":"Eschmann","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.engappai.2026.115524_b20","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.engappai.2026.115524_b21","series-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"Glorot","year":"2010"},{"key":"10.1016\/j.engappai.2026.115524_b22","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.engappai.2026.115524_b23","series-title":"ICML","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"issue":"1","key":"10.1016\/j.engappai.2026.115524_b24","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1109\/JOE.2023.3278290","article-title":"Adaptive Formation Motion Planning and Control of Autonomous Underwater Vehicles Using Deep Reinforcement Learning","volume":"49","author":"Hadi","year":"2024","journal-title":"IEEE J. Ocean. Eng."},{"issue":"7","key":"10.1016\/j.engappai.2026.115524_b25","first-page":"103","article-title":"Give us PID controllers and we can control the world","volume":"58","author":"H\u00e4gglund","year":"2024","journal-title":"IFAC-OnLine"},{"key":"10.1016\/j.engappai.2026.115524_b26","series-title":"TD-MPC2: Scalable, robust world models for continuous control","author":"Hansen","year":"2023"},{"key":"10.1016\/j.engappai.2026.115524_b27","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","author":"Hansen","year":"2024"},{"key":"10.1016\/j.engappai.2026.115524_b28","series-title":"2020 IEEE 32nd International Conference on Tools with Artificial Intelligence","first-page":"391","article-title":"WD3: Taming the estimation bias in deep reinforcement learning","author":"He","year":"2020"},{"key":"10.1016\/j.engappai.2026.115524_b29","series-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence","article-title":"Deep Reinforcement Learning that Matters","author":"Henderson","year":"2018"},{"issue":"1","key":"10.1016\/j.engappai.2026.115524_b30","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1146\/annurev-control-090419-075625","article-title":"Learning-based model predictive control: Toward safe learning in control","volume":"3","author":"Hewing","year":"2020","journal-title":"Annu. Rev. Control. Robot. Auton. Syst."},{"key":"10.1016\/j.engappai.2026.115524_b31","series-title":"Dropout q-functions for doubly efficient reinforcement learning","author":"Hiraoka","year":"2021"},{"key":"10.1016\/j.engappai.2026.115524_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.conengprac.2023.105462","article-title":"TASAC: A twin-actor reinforcement learning framework with a stochastic policy with an application to batch process control","volume":"134","author":"Joshi","year":"2023","journal-title":"Control Eng. Pract."},{"key":"10.1016\/j.engappai.2026.115524_b33","series-title":"International Conference on Artificial Intelligence and Statistics","first-page":"1701","article-title":"Data-efficient reinforcement learning with probabilistic model predictive control","author":"Kamthe","year":"2018"},{"key":"10.1016\/j.engappai.2026.115524_b34","doi-asserted-by":"crossref","unstructured":"Kendall, A., et al., 2019. Learning to drive in a day. In: 2019 International Conference on Robotics and Automation. ICRA, pp. 8248\u20138254.","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"10.1016\/j.engappai.2026.115524_b35","series-title":"An Introduction to Data-Driven Control Systems","author":"Khaki-Sedigh","year":"2023"},{"key":"10.1016\/j.engappai.2026.115524_b36","series-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"10.1016\/j.engappai.2026.115524_b37","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.engappai.2026.115524_b38","series-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"10.1016\/j.engappai.2026.115524_b39","series-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015"},{"key":"10.1016\/j.engappai.2026.115524_b40","series-title":"Advances in Neural Information Processing Systems","article-title":"Simple random search of static linear policies is competitive for reinforcement learning","volume":"Vol. 31","author":"Mania","year":"2018"},{"issue":"16","key":"10.1016\/j.engappai.2026.115524_b41","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1098\/rspl.1867.0055","article-title":"On governors","author":"Maxwell","year":"1868","journal-title":"Proc. R. Soc. Lond."},{"issue":"2","key":"10.1016\/j.engappai.2026.115524_b42","first-page":"280","article-title":"Directional stability of automatically steered bodies","volume":"34","author":"Minorsky","year":"1922","journal-title":"J. Am. Soc. Nav. Eng."},{"key":"10.1016\/j.engappai.2026.115524_b43","series-title":"International Conference on Machine Learning","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016"},{"key":"10.1016\/j.engappai.2026.115524_b44","series-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"10.1016\/j.engappai.2026.115524_b45","series-title":"Crazyflie 2.1 Quadcopter Nonlinear System Identification","author":"Nguyen","year":"2023"},{"key":"10.1016\/j.engappai.2026.115524_b46","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."},{"key":"10.1016\/j.engappai.2026.115524_b47","series-title":"MTS\/IEEE Oceans 2001. an Ocean Odyssey. Conference Proceedings (IEEE Cat. No. 01CH37295)","first-page":"450","article-title":"Development of a six-degree of freedom simulation model for the REMUS autonomous underwater vehicle","volume":"Vol. 1","author":"Prestero","year":"2001"},{"issue":"268","key":"10.1016\/j.engappai.2026.115524_b48","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.engappai.2026.115524_b49","doi-asserted-by":"crossref","DOI":"10.1146\/annurev-control-053018-023825","article-title":"A tour of reinforcement learning: The view from continuous control","author":"Recht","year":"2019","journal-title":"Annu. Rev. Control. Robot. Auton. Syst."},{"issue":"9","key":"10.1016\/j.engappai.2026.115524_b50","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1109\/TAC.1985.1104070","article-title":"Robustness of continuous-time adaptive control algorithms in the presence of unmodeled dynamics","volume":"30","author":"Rohrs","year":"2003","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.engappai.2026.115524_b51","series-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"Salimans","year":"2017"},{"key":"10.1016\/j.engappai.2026.115524_b52","series-title":"On the standard performance criteria for applied control design: PID, MPC or Machine Learning Controller?","author":"Sarhadi","year":"2025"},{"key":"10.1016\/j.engappai.2026.115524_b53","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.arcontrol.2023.03.009","article-title":"Learning quadrotor dynamics for precise, safe, and agile flight control","volume":"55","author":"Saviolo","year":"2023","journal-title":"Annu. Rev. Control."},{"key":"10.1016\/j.engappai.2026.115524_b54","series-title":"International Conference on Machine Learning","first-page":"1889","article-title":"Trust region policy optimization","author":"Schulman","year":"2015"},{"key":"10.1016\/j.engappai.2026.115524_b55","series-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"issue":"10","key":"10.1016\/j.engappai.2026.115524_b56","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.engappai.2026.115524_b57","doi-asserted-by":"crossref","unstructured":"Tang, C., Abbatematteo, B., Hu, J., Chandra, R., Mart\u00edn-Mart\u00edn, R., Stone, P., 2025. Deep reinforcement learning for robotics: A survey of real-world successes. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 39, pp. 28694\u201328698.","DOI":"10.1609\/aaai.v39i27.35095"},{"key":"10.1016\/j.engappai.2026.115524_b58","series-title":"2022 American Control Conference","first-page":"1048","article-title":"Data-driven control: Overview and perspectives","author":"Tang","year":"2022"},{"key":"10.1016\/j.engappai.2026.115524_b59","series-title":"2024 UKACC 14th International Conference on Control","first-page":"1","article-title":"Model free deep deterministic policy gradient controller for setpoint tracking of non-minimum phase systems","author":"Tavakkoli","year":"2024"},{"issue":"3","key":"10.1016\/j.engappai.2026.115524_b60","doi-asserted-by":"crossref","DOI":"10.1103\/PRXLife.2.033009","article-title":"Intrinsic Motivation in Dynamical Control Systems","volume":"2","author":"Tiomkin","year":"2024","journal-title":"PRX Life"},{"key":"10.1016\/j.engappai.2026.115524_b61","doi-asserted-by":"crossref","DOI":"10.1016\/j.robot.2025.105327","article-title":"Reinforcement learning in robotic systems: A review on sim-to-real transfer","author":"Tiwari","year":"2026","journal-title":"Robot. Auton. Syst."},{"key":"10.1016\/j.engappai.2026.115524_b62","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.apergo.2015.09.013","article-title":"A literature review on the levels of automation during the years. What are the different taxonomies that have been proposed?","volume":"53","author":"Vagia","year":"2016","journal-title":"Appl. Ergon."},{"issue":"5","key":"10.1016\/j.engappai.2026.115524_b63","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.2514\/3.20949","article-title":"Benchmark problems for robust control design","volume":"15","author":"Wie","year":"1992","journal-title":"J. Guid. Control Dyn."},{"key":"10.1016\/j.engappai.2026.115524_b64","series-title":"1992 American Control Conference","first-page":"2047","article-title":"Benchmark problems for robust control design (1992 ACC version)","author":"Wie","year":"1992"},{"key":"10.1016\/j.engappai.2026.115524_b65","series-title":"2020 IEEE Symposium Series on Computational Intelligence","first-page":"737","article-title":"Sim-to-real transfer in deep reinforcement learning for robotics: a survey","author":"Zhao","year":"2020"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626018087?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626018087?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,16]],"date-time":"2026-08-16T14:13:50Z","timestamp":1786889630000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626018087"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":65,"alternative-id":["S0952197626018087"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115524","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Deep reinforcement learning in applied control: Challenges, analysis, and insights","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115524","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":"115524"}}