{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T03:21:59Z","timestamp":1775186519834,"version":"3.50.1"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T00:00:00Z","timestamp":1731628800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T00:00:00Z","timestamp":1731628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["6213298"],"award-info":[{"award-number":["6213298"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin Municipality","doi-asserted-by":"publisher","award":["18JCYBJC87700"],"award-info":[{"award-number":["18JCYBJC87700"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s11227-024-06681-x","type":"journal-article","created":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T15:44:35Z","timestamp":1731685475000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Robust reinforcement learning with augmented state for leveling control of multi-cylinder hydraulic system"],"prefix":"10.1007","volume":"81","author":[{"given":"Chao","family":"Jia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"ZiJian","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,15]]},"reference":[{"issue":"4","key":"6681_CR1","doi-asserted-by":"publisher","first-page":"1980","DOI":"10.1109\/TIE.2011.2160137","volume":"59","author":"X Lu","year":"2012","unstructured":"Lu X, Huang M (2012) System-decomposition-based multilevel control for hydraulic press machine. IEEE Trans Industr Electron 59(4):1980\u20131987. https:\/\/doi.org\/10.1109\/TIE.2011.2160137","journal-title":"IEEE Trans Industr Electron"},{"issue":"5","key":"6681_CR2","doi-asserted-by":"publisher","first-page":"3541","DOI":"10.1002\/asjc.3038","volume":"25","author":"C Jia","year":"2023","unstructured":"Jia C, Sun Y, Du L, Wang H (2023) Fault-tolerant control strategy for multicylinder hydraulic press machine based on dynamic control allocation and adjustable multiobjective optimization. Asian J Control 25(5):3541\u20133558","journal-title":"Asian J Control"},{"issue":"1","key":"6681_CR3","doi-asserted-by":"publisher","first-page":"14","DOI":"10.3390\/pr10010014","volume":"10","author":"Z Huang","year":"2022","unstructured":"Huang Z, Xu Y, Ren W, Fu C, Cao R, Kong X, Li W (2022) Design of position control method for pump-controlled hydraulic presses via adaptive integral robust control. Processes 10(1):14","journal-title":"Processes"},{"key":"6681_CR4","unstructured":"Hong S, Chiu T.C (2002) Motion synchronization for multi-cylinder electro-hydraulic system. In: IEEE\/ASME International Conference on Advanced Intelligent Mechatronics"},{"issue":"10","key":"6681_CR5","doi-asserted-by":"publisher","first-page":"3713","DOI":"10.1109\/TSMC.2018.2884725","volume":"50","author":"Y Wang","year":"2020","unstructured":"Wang Y, Sun J, He H, Sun C (2020) Deterministic policy gradient with integral compensator for robust quadrotor control. IEEE Trans Syst Man Cybernetics: Syst 50(10):3713\u20133725. https:\/\/doi.org\/10.1109\/TSMC.2018.2884725","journal-title":"IEEE Trans Syst Man Cybernetics: Syst"},{"key":"6681_CR6","doi-asserted-by":"publisher","unstructured":"Brown T.B, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler D.M, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D (2020) Language Models are Few-Shot Learners. arXiv e-prints https:\/\/doi.org\/10.48550\/arXiv.2005.14165","DOI":"10.48550\/arXiv.2005.14165"},{"issue":"7964","key":"6681_CR7","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1038\/s41586-023-06004-9","volume":"618","author":"DJ Mankowitz","year":"2023","unstructured":"Mankowitz DJ, Michi A, Zhernov A, Gelmi M, Selvi M, Paduraru C, Leurent E, Iqbal S, Lespiau J-B, Ahern A, K\u00f6ppe T, Millikin K, Gaffney S, Elster S, Broshear J, Gamble C, Milan K, Tung R, Hwang M, Cemgil T, Barekatain M, Li Y, Mandhane A, Hubert T, Schrittwieser J, Hassabis D, Kohli P, Riedmiller M, Vinyals O, Silver D (2023) Faster sorting algorithms discovered using deep reinforcement learning. Nature 618(7964):257\u2013263. https:\/\/doi.org\/10.1038\/s41586-023-06004-9","journal-title":"Nature"},{"issue":"7540","key":"6681_CR8","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533. https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"6681_CR9","doi-asserted-by":"publisher","unstructured":"Dong K, Luo Y, Cheng E, Sun Z, Zhao L, Zhang Q, Zhou C, Song B (2022) Balance between efficient and effective learning: Dense2sparse reward shaping for robot manipulation with environment uncertainty. In: 2022 IEEE\/ASME International Conference on Advanced Intelligent Mechatronics (AIM), pp. 1192\u20131198. https:\/\/doi.org\/10.1109\/AIM52237.2022.9863259","DOI":"10.1109\/AIM52237.2022.9863259"},{"key":"6681_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2022.105302","volume":"127","author":"H Zhang","year":"2022","unstructured":"Zhang H, Zhao C, Ding J (2022) Online reinforcement learning with passivity-based stabilizing term for real time overhead crane control without knowledge of the system model. Control Eng Pract 127:105302. https:\/\/doi.org\/10.1016\/j.conengprac.2022.105302","journal-title":"Control Eng Pract"},{"key":"6681_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2022.105345","volume":"129","author":"Y Yao","year":"2022","unstructured":"Yao Y, Ding J, Zhao C, Wang Y, Chai T (2022) Data-driven constrained reinforcement learning for optimal control of a multistage evaporation process. Control Eng Pract 129:105345. https:\/\/doi.org\/10.1016\/j.conengprac.2022.105345","journal-title":"Control Eng Pract"},{"issue":"12","key":"6681_CR12","doi-asserted-by":"publisher","first-page":"2499","DOI":"10.1109\/TSMC.2017.2785794","volume":"49","author":"H Wu","year":"2019","unstructured":"Wu H, Song S, You K, Wu C (2019) Depth control of model-free auvs via reinforcement learning. IEEE Trans Systems, Man, Cybernetics: Syst 49(12):2499\u20132510. https:\/\/doi.org\/10.1109\/TSMC.2017.2785794","journal-title":"IEEE Trans Systems, Man, Cybernetics: Syst"},{"key":"6681_CR13","doi-asserted-by":"crossref","unstructured":"Wyrwal D, Lindner T, Nowak P, Bialek M (2020) Control strategy of hydraulic cylinder based on deep reinforcement learning. In: 2020 Mechatronics Systems and Materials (MSM)","DOI":"10.1109\/MSM49833.2020.9202351"},{"issue":"13","key":"6681_CR14","doi-asserted-by":"publisher","first-page":"7646","DOI":"10.1002\/rnc.6235","volume":"32","author":"M Wu","year":"2022","unstructured":"Wu M, Liu L, Yu Z, Li W (2022) Safe reward-based deep reinforcement learning control for an electro-hydraulic servo system. Int J Robust Nonlinear Control 32(13):7646\u20137662. https:\/\/doi.org\/10.1002\/rnc.6235","journal-title":"Int J Robust Nonlinear Control"},{"key":"6681_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02281-6","author":"L Wei","year":"2024","unstructured":"Wei L, Xu Q, Hu Z (2024) Mobile robot path planning based on multi-experience pool deep deterministic policy gradient in unknown environment. Int J Mach Learn Cybern. https:\/\/doi.org\/10.1007\/s13042-024-02281-6","journal-title":"Int J Mach Learn Cybern"},{"key":"6681_CR16","doi-asserted-by":"publisher","unstructured":"Zhang H, Chen H, Xiao C, Li B, Liu M, Boning D, Hsieh C.-J (2020) Robust deep reinforcement learning against adversarial perturbations on state observations. arXiv e-prints, 2003\u201308938 https:\/\/doi.org\/10.48550\/arXiv.2003.08938","DOI":"10.48550\/arXiv.2003.08938"},{"issue":"7","key":"6681_CR17","doi-asserted-by":"publisher","first-page":"3257","DOI":"10.3390\/app11073257","volume":"11","author":"C-H Pi","year":"2021","unstructured":"Pi C-H, Ye W-Y, Cheng S (2021) Robust quadrotor control through reinforcement learning with disturbance compensation. Appl Sci 11(7):3257. https:\/\/doi.org\/10.3390\/app11073257","journal-title":"Appl Sci"},{"issue":"5","key":"6681_CR18","doi-asserted-by":"publisher","first-page":"1054","DOI":"10.1109\/TNN.1998.712192","volume":"9","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: An introduction. IEEE Trans Neural Networks 9(5):1054","journal-title":"IEEE Trans Neural Networks"},{"key":"6681_CR19","doi-asserted-by":"publisher","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M.A (2013) Playing atari with deep reinforcement learning. ArXiv abs\/1312.5602[SPACE]https:\/\/doi.org\/10.48550\/arXiv.1312.5602","DOI":"10.48550\/arXiv.1312.5602"},{"key":"6681_CR20","doi-asserted-by":"publisher","unstructured":"Lillicrap T.P, Hunt J.J, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. arXiv e-prints, 1509\u201302971 https:\/\/doi.org\/10.48550\/arXiv.1509.02971","DOI":"10.48550\/arXiv.1509.02971"},{"key":"6681_CR21","unstructured":"Fujimoto S, Hoof H, Meger D (2018) Addressing function approximation error in actor-critic methods. In: Proceedings of the 35th International Conference on Machine Learning. Proceedings of the 35th International Conference on Machine Learning, pp. 1587\u20131596"},{"key":"6681_CR22","doi-asserted-by":"publisher","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv e-prints, 1707\u201306347 https:\/\/doi.org\/10.48550\/arXiv.1707.06347","DOI":"10.48550\/arXiv.1707.06347"},{"key":"6681_CR23","doi-asserted-by":"publisher","unstructured":"Haarnoja T, Zhou A, Abbeel P, Levine S (2018) Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. arXiv e-prints, 1801\u201301290 https:\/\/doi.org\/10.48550\/arXiv.1801.01290","DOI":"10.48550\/arXiv.1801.01290"},{"key":"6681_CR24","doi-asserted-by":"publisher","unstructured":"Sutton R.S, Maei H.R, Precup D, Bhatnagar S, Silver D, Szepesv\u00e1ri C, Wiewiora E (2009) Fast gradient-descent methods for temporal-difference learning with linear function approximation. Association for Computing Machinery, New York, NY, USA . https:\/\/doi.org\/10.1145\/1553374.1553501","DOI":"10.1145\/1553374.1553501"},{"issue":"5","key":"6681_CR25","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1080\/00207177208932211","volume":"15","author":"PC Young","year":"1972","unstructured":"Young PC, Willems JC (1972) An approach to the linear multivariable servomechanism problem. Int J Control 15(5):961\u2013979. https:\/\/doi.org\/10.1080\/00207177208932211","journal-title":"Int J Control"},{"key":"6681_CR26","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1016\/j.ins.2022.01.047","volume":"591","author":"B Fernandez-Gauna","year":"2022","unstructured":"Fernandez-Gauna B, Gra\u00f1a M, Osa-Amilibia J-L, Larrucea X (2022) Actor-critic continuous state reinforcement learning for wind-turbine control robust optimization. Inf Sci 591:365\u2013380. https:\/\/doi.org\/10.1016\/j.ins.2022.01.047","journal-title":"Inf Sci"},{"key":"6681_CR27","doi-asserted-by":"publisher","unstructured":"Pattanaik A, Tang Z, Liu S, Bommannan G, Chowdhary G (2017) Robust deep reinforcement learning with adversarial attacks. arXiv e-prints, 1712\u201303632 https:\/\/doi.org\/10.48550\/arXiv.1712.03632","DOI":"10.48550\/arXiv.1712.03632"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06681-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-06681-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06681-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T16:03:34Z","timestamp":1731686614000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-06681-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,15]]},"references-count":27,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6681"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-06681-x","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,15]]},"assertion":[{"value":"1 November 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 November 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"185"}}