{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T01:13:17Z","timestamp":1769562797522,"version":"3.49.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T00:00:00Z","timestamp":1705968000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T00:00:00Z","timestamp":1705968000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"crossref","award":["202004910825"],"award-info":[{"award-number":["202004910825"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61605203"],"award-info":[{"award-number":["61605203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2015173"],"award-info":[{"award-number":["2015173"]}],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s00521-023-09341-y","type":"journal-article","created":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T12:01:36Z","timestamp":1706011296000},"page":"6441-6465","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Nonlinear control strategies for 3-DOF control moment gyroscope using deep reinforcement learning"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2689-1249","authenticated-orcid":false,"given":"Yan","family":"Xiong","sequence":"first","affiliation":[]},{"given":"Siyuan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jianxiang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Mingxing","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Guo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,23]]},"reference":[{"issue":"12","key":"9341_CR1","doi-asserted-by":"publisher","first-page":"14413","DOI":"10.1109\/TVT.2020.3034800","volume":"69","author":"J Hu","year":"2020","unstructured":"Hu J, Niu H, Carrasco J, Lennox B, Arvin F (2020) Voronoi-based multi-robot autonomous exploration in unknown environments via deep reinforcement learning. IEEE Trans Veh Technol 69(12):14413\u201314423. https:\/\/doi.org\/10.1109\/TVT.2020.3034800","journal-title":"IEEE Trans Veh Technol"},{"key":"9341_CR2","doi-asserted-by":"crossref","unstructured":"Kaelbling LP, Littman ML, Moore AW (1996) Reinforcement learning: a survey. J Artif Intell Res 4:237\u2013285 https:\/\/arxiv.org\/abs\/cs\/9605103","DOI":"10.1613\/jair.301"},{"key":"9341_CR3","first-page":"1","volume":"19","author":"T De Bruin","year":"2018","unstructured":"De Bruin T, Kober J, Tuyls K, Babuska R (2018) Experience selection in deep reinforcement learning for control. J Mach Learn Res 19:1\u201356","journal-title":"J Mach Learn Res"},{"issue":"7587","key":"9341_CR4","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison CJ, Guez A, Sifre L, Van Den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M et al (2016) Mastering the game of go with deep neural networks and tree search. Nature 529(7587):484\u2013489. https:\/\/doi.org\/10.1038\/nature16961","journal-title":"Nature"},{"key":"9341_CR5","doi-asserted-by":"publisher","unstructured":"Badia AP, Piot B, Kapturowski S, Sprechmann P, Vitvitskyi A, Guo ZD, Blundell C (2020) Agent57: Outperforming the atari human benchmark. In: International conference on machine learning, pp 507\u2013517 . https:\/\/doi.org\/10.48550\/arXiv.2003.13350. PMLR","DOI":"10.48550\/arXiv.2003.13350"},{"key":"9341_CR6","doi-asserted-by":"publisher","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971. https:\/\/doi.org\/10.48550\/arXiv.1509.02971","DOI":"10.48550\/arXiv.1509.02971"},{"issue":"6","key":"9341_CR7","doi-asserted-by":"publisher","first-page":"1905","DOI":"10.1002\/rnc.5122","volume":"31","author":"C He","year":"2021","unstructured":"He C, Wan Y, Gu Y, Lewis FL (2021) Integral reinforcement learning-based approximate minimum time-energy path planning in an unknown environment. Int J Robust Nonlinear Control 31(6):1905\u20131922. https:\/\/doi.org\/10.1002\/rnc.5122","journal-title":"Int J Robust Nonlinear Control"},{"issue":"7","key":"9341_CR8","doi-asserted-by":"publisher","first-page":"3039","DOI":"10.1002\/rnc.4923","volume":"30","author":"Z Xu","year":"2020","unstructured":"Xu Z, Ni H, Reza Karimi H, Zhang D (2020) A markovian jump system approach to consensus of heterogeneous multiagent systems with partially unknown and uncertain attack strategies. Int J Robust Nonlinear Control 30(7):3039\u20133053. https:\/\/doi.org\/10.1002\/rnc.4923","journal-title":"Int J Robust Nonlinear Control"},{"key":"9341_CR9","doi-asserted-by":"publisher","first-page":"121922","DOI":"10.1109\/ACCESS.2019.2938240","volume":"7","author":"X Li","year":"2019","unstructured":"Li X, Lv Z, Wang S, Wei Z, Wu L (2019) A reinforcement learning model based on temporal difference algorithm. IEEE Access 7:121922\u2013121930. https:\/\/doi.org\/10.1109\/ACCESS.2019.2938240","journal-title":"IEEE Access"},{"key":"9341_CR10","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.neucom.2019.10.060","volume":"408","author":"Z Chen","year":"2020","unstructured":"Chen Z, Qin B, Sun M, Sun Q (2020) Q-learning-based parameters adaptive algorithm for active disturbance rejection control and its application to ship course control. Neurocomputing 408:51\u201363. https:\/\/doi.org\/10.1016\/j.neucom.2019.10.060","journal-title":"Neurocomputing"},{"key":"9341_CR11","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/j.neucom.2020.03.070","volume":"425","author":"Y Zheng","year":"2021","unstructured":"Zheng Y, Chen Z, Huang Z, Sun M, Sun Q (2021) Active disturbance rejection controller for multi-area interconnected power system based on reinforcement learning. Neurocomputing 425:149\u2013159. https:\/\/doi.org\/10.1016\/j.neucom.2020.03.070","journal-title":"Neurocomputing"},{"issue":"17","key":"9341_CR12","doi-asserted-by":"publisher","first-page":"8463","DOI":"10.1002\/rnc.5740","volume":"31","author":"Y Zheng","year":"2021","unstructured":"Zheng Y, Tao J, Sun Q, Sun H, Sun M, Chen Z (2021) An intelligent course keeping active disturbance rejection controller based on double deep q-network for towing system of unpowered cylindrical drilling platform. Int J Robust Nonlinear Control 31(17):8463\u20138480. https:\/\/doi.org\/10.1002\/rnc.5740","journal-title":"Int J Robust Nonlinear Control"},{"key":"9341_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2020.107360","volume":"210","author":"Y Sun","year":"2020","unstructured":"Sun Y, Ran X, Zhang G, Wang X, Xu H (2020) Auv path following controlled by modified deep deterministic policy gradient. Ocean Eng 210:107360. https:\/\/doi.org\/10.1016\/j.oceaneng.2020.107360","journal-title":"Ocean Eng"},{"key":"9341_CR14","doi-asserted-by":"publisher","unstructured":"Yu R, Shi Z, Huang C, Li T, Ma Q (2017) Deep reinforcement learning based optimal trajectory tracking control of autonomous underwater vehicle. In: 2017 36th Chinese control conference (CCC), pp 4958\u20134965. https:\/\/doi.org\/10.23919\/ChiCC.2017.8028138. IEEE","DOI":"10.23919\/ChiCC.2017.8028138"},{"issue":"5","key":"9341_CR15","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.2514\/1.A34120","volume":"55","author":"T Sasaki","year":"2018","unstructured":"Sasaki T, Shimomura T, Schaub H (2018) Robust attitude control using a double-gimbal variable-speed control moment gyroscope. J Spacecraft Rockets 55(5):1235\u20131247. https:\/\/doi.org\/10.2514\/1.A34120","journal-title":"J Spacecraft Rockets"},{"key":"9341_CR16","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.mechatronics.2018.11.011","volume":"57","author":"J Montoya-Ch\u00e1irez","year":"2019","unstructured":"Montoya-Ch\u00e1irez J, Santib\u00e1\u00f1ez V, Moreno-Valenzuela J (2019) Adaptive control schemes applied to a control moment gyroscope of 2 degrees of freedom. Mechatronics 57:73\u201385. https:\/\/doi.org\/10.1016\/j.mechatronics.2018.11.011","journal-title":"Mechatronics"},{"issue":"12","key":"9341_CR17","doi-asserted-by":"publisher","first-page":"6805","DOI":"10.1007\/s00521-020-05456-8","volume":"33","author":"J Montoya-Ch\u00e1irez","year":"2021","unstructured":"Montoya-Ch\u00e1irez J, Rossomando FG, Carelli R, Santib\u00e1\u00f1ez V, Moreno-Valenzuela J (2021) Adaptive rbf neural network-based control of an underactuated control moment gyroscope. Neural Comput Appl 33(12):6805\u20136818. https:\/\/doi.org\/10.1007\/s00521-020-05456-8","journal-title":"Neural Comput Appl"},{"key":"9341_CR18","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1016\/j.neucom.2020.04.019","volume":"403","author":"J Moreno-Valenzuela","year":"2020","unstructured":"Moreno-Valenzuela J, Montoya-Ch\u00e1irez J, Santib\u00e1\u00f1ez V (2020) Robust trajectory tracking control of an underactuated control moment gyroscope via neural network-based feedback linearization. Neurocomputing 403:314\u2013324. https:\/\/doi.org\/10.1016\/j.neucom.2020.04.019","journal-title":"Neurocomputing"},{"issue":"26","key":"9341_CR19","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1016\/j.ifacol.2015.11.142","volume":"48","author":"Z Emedi","year":"2015","unstructured":"Emedi Z, Karimi A (2015) Fixed-order linear parameter varying controller design for a 2dof gyroscope. IFAC-PapersOnLine 48(26):230\u2013235. https:\/\/doi.org\/10.1016\/j.ifacol.2015.11.142","journal-title":"IFAC-PapersOnLine"},{"key":"9341_CR20","doi-asserted-by":"publisher","unstructured":"Kammer C, Karimi A (2018) A data-driven fixed-structure control design method with application to a 2-dof gyroscope. In: 2018 IEEE conference on control technology and applications (CCTA), pp 915\u2013920. https:\/\/doi.org\/10.1109\/CCTA.2018.8511429. IEEE","DOI":"10.1109\/CCTA.2018.8511429"},{"key":"9341_CR21","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5559","author":"R Wang","year":"2021","unstructured":"Wang R, Koelewijn PJ, Manchester IR, T\u00f3th R (2021) Nonlinear parameter-varying state-feedback design for a gyroscope using virtual control contraction metrics. Int J Robust Nonlinear Control. https:\/\/doi.org\/10.1002\/rnc.5559","journal-title":"Int J Robust Nonlinear Control"},{"issue":"2","key":"9341_CR22","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1016\/j.asr.2014.10.036","volume":"55","author":"Z Wei","year":"2015","unstructured":"Wei Z, Li D, Luo Q, Jiang J (2015) Modeling and analysis of a flywheel microvibration isolation system for spacecrafts. Adv Space Res 55(2):761\u2013777. https:\/\/doi.org\/10.1016\/j.asr.2014.10.036","journal-title":"Adv Space Res"},{"issue":"2","key":"9341_CR23","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1109\/TAES.2013.120543","volume":"50","author":"Y Zhang","year":"2014","unstructured":"Zhang Y, Zhang J (2014) Disturbance characteristics analysis of cmg due to imbalances and installation errors. IEEE Trans Aerospace Electronic Syst 50(2):1017\u20131026. https:\/\/doi.org\/10.1109\/TAES.2013.120543","journal-title":"IEEE Trans Aerospace Electronic Syst"},{"issue":"3","key":"9341_CR24","doi-asserted-by":"publisher","first-page":"7043","DOI":"10.3182\/20140824-6-ZA-1003.02042","volume":"47","author":"J-M Engel","year":"2014","unstructured":"Engel J-M, Babu\u0161ka R (2014) On-line reinforcement learning for nonlinear motion control: quadratic and non-quadratic reward functions. IFAC Proc Vol 47(3):7043\u20137048. https:\/\/doi.org\/10.3182\/20140824-6-ZA-1003.02042","journal-title":"IFAC Proc Vol"},{"issue":"7540","key":"9341_CR25","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 et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533. https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"9341_CR26","unstructured":"G\u00f3mez\u00a0Berdugo DF (2017) Application of reinforcement learning for the control of a control moment gyroscope. B.S. thesis, Uniandes, Colombia"},{"key":"9341_CR27","doi-asserted-by":"publisher","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M (2013) Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602. https:\/\/doi.org\/10.48550\/arXiv.1312.5602","DOI":"10.48550\/arXiv.1312.5602"},{"key":"9341_CR28","doi-asserted-by":"publisher","unstructured":"Silver D, Lever G, Heess N, Degris T, Wierstra D, Riedmiller M (2014) Deterministic policy gradient algorithms. In: International conference on machine learning, pp 387\u2013395. https:\/\/doi.org\/10.5555\/3044805.3044850. PMLR","DOI":"10.5555\/3044805.3044850"},{"key":"9341_CR29","unstructured":"Mnih V, Badia AP, Mirza M, Graves A, Lillicrap T, Harley T, Silver D, Kavukcuoglu K (2016) Asynchronous methods for deep reinforcement learning. In: International conference on machine learning, pp 1928\u20131937. arxiv:1602.01783. PMLR"},{"key":"9341_CR30","doi-asserted-by":"publisher","unstructured":"Fujimoto S, Hoof H, Meger D (2018) Addressing function approximation error in actor-critic methods. In: International conference on machine learning, pp 1587\u20131596. https:\/\/doi.org\/10.48550\/arXiv.1802.09477. PMLR","DOI":"10.48550\/arXiv.1802.09477"},{"key":"9341_CR31","doi-asserted-by":"publisher","unstructured":"Wang JX, Kurth-Nelson Z, Tirumala D, Soyer H, Leibo JZ, Munos R, Blundell C, Kumaran D, Botvinick M (2016) Learning to reinforcement learn. arXiv preprint arXiv:1611.05763. https:\/\/doi.org\/10.48550\/arXiv.1611.05763","DOI":"10.48550\/arXiv.1611.05763"},{"key":"9341_CR32","unstructured":"Kersandt K (2018) Deep reinforcement learning as control method for autonomous uavs. Master\u2019s thesis, Universitat Polit\u00e8cnica de Catalunya, Barcelona. http:\/\/hdl.handle.net\/2117\/113948"},{"key":"9341_CR33","unstructured":"Agu CC (2021) Hybridized spacecraft attitude control via reinforcement learning using control moment gyroscope arrays. Theses and Dissertations, 4983"},{"key":"9341_CR34","unstructured":"Li L, Jamieson K, Rostamizadeh A, Gonina E, Hardt M, Recht B, Talwalkar A (2018) A system for massively parallel hyperparameter tuning. arXiv preprint. arXiv:1810.05934. Accessed 21 Aug 2021"},{"key":"9341_CR35","unstructured":"Thrun S, Schwartz A (1993) Issues in using function approximation for reinforcement learning. In: Proceedings of the fourth connectionist models summer school, pp 255\u2013263 . Hillsdale, NJ. https:\/\/www.semanticscholar.org\/paper\/Issues-in-Using-Function-Approximation-for-Learning-Thrun-Schwartz\/26b8747eb4d7fb4d4fc45707606d5e969b9afb0c"},{"key":"9341_CR36","unstructured":"Quanser (2012) User manual 3-dof gyroscope experiment set up and configuration. Technical Report Technical Report, Quanser inc, Markham . https:\/\/www.quanser.com\/products\/3-dof-gyroscope\/. Accessed August 15, 2021"},{"key":"9341_CR37","unstructured":"Agram Y (2018) Identification and control of a gyroscope. EPFL Semester Project"},{"key":"9341_CR38","doi-asserted-by":"publisher","unstructured":"Lofberg J (2004) Yalmip: A toolbox for modeling and optimization in matlab. In: 2004 IEEE international conference on robotics and automation (IEEE Cat. No. 04CH37508), pp 284\u2013289. https:\/\/doi.org\/10.1109\/CACSD.2004.1393890. IEEE","DOI":"10.1109\/CACSD.2004.1393890"},{"key":"9341_CR39","doi-asserted-by":"publisher","unstructured":"Toh KC, Todd MJ, T\u00fct\u00fcnc\u00fc RH (1999) Sdpt3 - a matlab software package for semidefinite programming, version 1.3. Optimization Methods and Software 11(1-4), 545\u2013581 https:\/\/doi.org\/10.1080\/10556789908805762","DOI":"10.1080\/10556789908805762"},{"key":"9341_CR40","doi-asserted-by":"publisher","unstructured":"T\u00f3th R (2010) Modeling and identification of linear parameter-varying systems, vol 403. Springer, Berlin. https:\/\/doi.org\/10.1007\/978-3-642-13812-6","DOI":"10.1007\/978-3-642-13812-6"},{"issue":"2","key":"9341_CR41","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1109\/TCST.2014.2327584","volume":"23","author":"C Hoffmann","year":"2014","unstructured":"Hoffmann C, Werner H (2014) A survey of linear parameter-varying control applications validated by experiments or high-fidelity simulations. IEEE Trans Control Syst Technol 23(2):416\u2013433. https:\/\/doi.org\/10.1109\/TCST.2014.2327584","journal-title":"IEEE Trans Control Syst Technol"},{"issue":"28","key":"9341_CR42","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.ifacol.2019.12.351","volume":"52","author":"D Rotondo","year":"2019","unstructured":"Rotondo D, Witczak M (2019) Analysis and design of quadratically bounded qpv control systems. IFAC-PapersOnLine 52(28):76\u201381. https:\/\/doi.org\/10.1016\/j.ifacol.2019.12.351","journal-title":"IFAC-PapersOnLine"},{"key":"9341_CR43","unstructured":"Wang R, T\u00f3th R, Manchester IR (2020) Virtual control contraction metrics: Convex nonlinear feedback design via behavioral embedding. arXiv preprint arXiv:2003.08513"},{"issue":"6","key":"9341_CR44","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1016\/S0005-1098(98)00019-3","volume":"34","author":"W Lohmiller","year":"1998","unstructured":"Lohmiller W, Slotine J-JE (1998) On contraction analysis for non-linear systems. Automatica 34(6):683\u2013696. https:\/\/doi.org\/10.1016\/S0005-1098(98)00019-3","journal-title":"Automatica"},{"key":"9341_CR45","doi-asserted-by":"publisher","unstructured":"van\u00a0der Schaft A (2015) A geometric approach to differential hamiltonian systems and differential riccati equations. In: 2015 54th IEEE conference on decision and control (CDC), pp 7151\u20137156. https:\/\/doi.org\/10.1109\/CDC.2015.7403347. IEEE","DOI":"10.1109\/CDC.2015.7403347"},{"key":"9341_CR46","unstructured":"Hill A, Raffin A, Ernestus M, Gleave A, Kanervisto A, Traore R, Dhariwal P, Hesse C, Klimov O, Nichol A, Plappert M, Radford A, Schulman J, Sidor S, Wu Y (2018) Stable baselines. GitHub"},{"key":"9341_CR47","unstructured":"Huang Z (2021) Control of a gyroscope using reinforcement learning methods. EPFL Semester Project"},{"key":"9341_CR48","unstructured":"Liaw R, Liang E, Nishihara R, Moritz P, Gonzalez JE, Stoica I (2018) Tune: a research platform for distributed model selection and training. arXiv preprint. arXiv:1807.05118. Accessed 21 Aug 2021"},{"key":"9341_CR49","doi-asserted-by":"publisher","first-page":"230","DOI":"10.48550\/arXiv.1810.05934","volume":"2","author":"L Li","year":"2020","unstructured":"Li L, Jamieson K, Rostamizadeh A, Gonina E, Ben-Tzur J, Hardt M, Recht B, Talwalkar A (2020) A system for massively parallel hyperparameter tuning. Proc Mach Learn Syst 2:230\u2013246. https:\/\/doi.org\/10.48550\/arXiv.1810.05934","journal-title":"Proc Mach Learn Syst"},{"key":"9341_CR50","doi-asserted-by":"publisher","unstructured":"Pelikan M (2005) Bayesian optimization algorithm. In: Hierarchical Bayesian optimization algorithm, pp 31\u201348. Springer, Berlin. https:\/\/doi.org\/10.1007\/978-3-540-32373-0_3","DOI":"10.1007\/978-3-540-32373-0_3"},{"issue":"1","key":"9341_CR51","doi-asserted-by":"publisher","first-page":"6765","DOI":"10.48550\/arXiv.1603.06560","volume":"18","author":"L Li","year":"2017","unstructured":"Li L, Jamieson K, DeSalvo G, Rostamizadeh A, Talwalkar A (2017) Hyperband: a novel bandit-based approach to hyperparameter optimization. J Mach Learn Res 18(1):6765\u20136816. https:\/\/doi.org\/10.48550\/arXiv.1603.06560","journal-title":"J Mach Learn Res"},{"key":"9341_CR52","unstructured":"Corp. NI (2021) National instruments myrio board. Webpage. https:\/\/www.ni.com\/de-ch\/support\/model.myrio-1900.html. Accessed 21 Aug 2021"},{"key":"9341_CR53","unstructured":"Achiam J (2018) Spinning up in deep reinforcement learning. URL https:\/\/spinningup.openai.com"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-09341-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-09341-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-09341-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,19]],"date-time":"2024-03-19T21:29:09Z","timestamp":1710883749000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-09341-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,23]]},"references-count":53,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["9341"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-09341-y","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,23]]},"assertion":[{"value":"17 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 November 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}