{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T10:05:34Z","timestamp":1767261934205,"version":"3.37.3"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T00:00:00Z","timestamp":1728518400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T00:00:00Z","timestamp":1728518400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Training Project of Top Scientific Research Talents of Nantong Institute of Technology","award":["XBJRC2021005"],"award-info":[{"award-number":["XBJRC2021005"]}]},{"DOI":"10.13039\/501100018557","name":"Science and Technology Project of Nantong City","doi-asserted-by":"publisher","award":["JC2021132","MS22021028","JCZ21058","JCZ20172","JCZ20151","JCZ20148"],"award-info":[{"award-number":["JC2021132","MS22021028","JCZ21058","JCZ20172","JCZ20151","JCZ20148"]}],"id":[{"id":"10.13039\/501100018557","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Universities Natural Science Research Projects of Jiangsu Province","award":["17KJB520031","21KJD210004","22KJB520032","22KJD520007","22KJD520008","22KJD520009"],"award-info":[{"award-number":["17KJB520031","21KJD210004","22KJB520032","22KJD520007","22KJD520008","22KJD520009"]}]},{"DOI":"10.13039\/100016806","name":"Natural Science Foundation of Nantong City","doi-asserted-by":"crossref","award":["JC2023103"],"award-info":[{"award-number":["JC2023103"]}],"id":[{"id":"10.13039\/100016806","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s00521-024-10492-9","type":"journal-article","created":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T08:01:57Z","timestamp":1728547317000},"page":"1729-1739","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A manipulator control method based on deep deterministic policy gradient with parameter noise"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9881-8489","authenticated-orcid":false,"given":"Haifei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liting","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lanmei","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianlin","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,10]]},"reference":[{"key":"10492_CR1","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1007\/978-3-030-66645-3_25","volume-title":"Intelligent Robotics and Applications: 13th International Conference, ICIRA 2020, Kuala Lumpur, Malaysia, November 5\u20137, 2020, Proceedings","author":"Y Hou","year":"2020","unstructured":"Hou Y, Hao Xu, Luo J, Lei Y, Jinyu Xu, Zhang H-T (2020) Variable Impedance Control of Manipulator Based on DQN. In: Chan CS, Liu H, Zhu X, Lim CH, Liu X, Liu L, Goh KM (eds) Intelligent Robotics and Applications: 13th International Conference, ICIRA 2020, Kuala Lumpur, Malaysia, November 5\u20137, 2020, Proceedings. Springer International Publishing, Cham, pp 296\u2013307. https:\/\/doi.org\/10.1007\/978-3-030-66645-3_25"},{"key":"10492_CR2","first-page":"40","volume":"38","author":"HY Li","year":"2020","unstructured":"Li HY, Lin TY, Zeng B, Shi GQ (2020) Control method of space manipulator by using reinforcement learning. Aerosp Control 38:40\u201345","journal-title":"Aerosp Control"},{"issue":"011","key":"10492_CR3","first-page":"1262","volume":"040","author":"S Leng","year":"2019","unstructured":"Leng S, Wu K, Ju HH (2019) Overview of manipulator kinematics modeling and solving method. J Astronaut 040(011):1262\u20131273","journal-title":"J Astronaut"},{"issue":"5","key":"10492_CR4","first-page":"647","volume":"43","author":"J Yao","year":"2020","unstructured":"Yao J, Ke LT, Ren J (2020) Adaptive gain control algorithm based on deep reinforcement learning. J Zhejiang Sci-Tech Univ 43(5):647\u2013652","journal-title":"J Zhejiang Sci-Tech Univ"},{"key":"10492_CR5","doi-asserted-by":"crossref","first-page":"102324","DOI":"10.1016\/j.rcim.2022.102324","volume":"77","author":"XH Wang","year":"2022","unstructured":"Wang XH, Zhang L, Lin TY, Zhao C, Wang KY, Chen Z (2022) Solving job scheduling problems in a resource preemption environment with multi-agent reinforcement learning. Robot Comput-integr Manuf 77:102324","journal-title":"Robot Comput-integr Manuf"},{"key":"10492_CR6","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1145\/3528223.353009","volume":"41","author":"Q She","year":"2022","unstructured":"She Q, Ruizhen Hu, Juzhan Xu, Liu M, Kai Xu, Huang H (2022) Learning high-DOF reaching-and-grasping via dynamic representation of gripper-object interaction. ACM Trans Graph 41:14. https:\/\/doi.org\/10.1145\/3528223.353009","journal-title":"ACM Trans Graph"},{"key":"10492_CR7","first-page":"121","volume":"10","author":"XN Bai","year":"2019","unstructured":"Bai XN (2019) Research on robot arm control method based on hierarchical reinforcement learning. Autom Instrum 10:121\u2013123","journal-title":"Autom Instrum"},{"issue":"13","key":"10492_CR8","doi-asserted-by":"publisher","first-page":"2065","DOI":"10.3390\/electronics11132065","volume":"11","author":"T You","year":"2022","unstructured":"You T, Hao Wu, Xiangrong Xu, Petrovic PB, Rodi\u0107 A (2022) A proposed priority pushing and grasping strategy based on an improved actor-critic algorithm. Electronics 11(13):2065. https:\/\/doi.org\/10.3390\/electronics11132065","journal-title":"Electronics"},{"key":"10492_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.isatra.2021.08.005","volume":"126","author":"Y Ouyang","year":"2022","unstructured":"Ouyang Y, Sun C, Dong L (2022) Actor\u2013critic learning based coordinated control for a dual-arm robot with prescribed performance and unknown backlash-like hysteresis. ISA Trans 126:1\u201313. https:\/\/doi.org\/10.1016\/j.isatra.2021.08.005","journal-title":"ISA Trans"},{"issue":"10","key":"10492_CR10","doi-asserted-by":"publisher","first-page":"5204","DOI":"10.3390\/app12105204","volume":"12","author":"Y Wang","year":"2022","unstructured":"Wang Y, Wang L, Zhao Y (2022) Research on door opening operation of mobile robotic arm based on reinforcement learning. Appl Sci 12(10):5204. https:\/\/doi.org\/10.3390\/app12105204","journal-title":"Appl Sci"},{"key":"10492_CR11","first-page":"169","volume":"37","author":"QJ Zhou","year":"2020","unstructured":"Zhou QJ, Liu ML, Li XM (2020) Research on solid radioactive waste grasping method. Appl Res Comput 37:169\u2013173","journal-title":"Appl Res Comput"},{"issue":"11","key":"10492_CR12","first-page":"278","volume":"31","author":"HY Li","year":"2019","unstructured":"Li HY, Zhao ZL, Gu L et al (2019) Robot arm control method based on deep reinforcement learning. J Syst Simul 31(11):278\u2013283","journal-title":"J Syst Simul"},{"issue":"2","key":"10492_CR13","first-page":"341","volume":"7","author":"TQ Ngo","year":"2012","unstructured":"Ngo TQ, Wang YN, Mai TL et al (2012) Robust adaptive neural-fuzzy network tracking control for robot manipulator. Int J Comput Commun Control 7(2):341\u2013352","journal-title":"Int J Comput Commun Control"},{"issue":"5","key":"10492_CR14","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1163\/016918611X558261","volume":"25","author":"P Kormushev","year":"2011","unstructured":"Kormushev P, Calinon S, Caldwell DG (2011) Imitation learning of positional and force skills demonstrated via kinesthetic teaching and haptic input. Adv Robot 25(5):581\u2013603","journal-title":"Adv Robot"},{"key":"10492_CR15","unstructured":"Zhang F Y., Leitner J., Milford M., et al. (2015) Towards vision-based deep reinforcement learning for robotic motion control. In: Australasian Conference on Robotics and Automation 2015 (ACRA 2015). https:\/\/arxiv.org\/pdf\/1511.03791.pdf."},{"key":"10492_CR16","unstructured":"Mnih V, Kavukcuoglu K, Silverd, et al. (2013) Playing Atari with deep reinforcement learning. https:\/\/arxiv.org\/pdf\/1312.5602.pdf."},{"issue":"7540","key":"10492_CR17","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"M Volodymyr","year":"2015","unstructured":"Volodymyr M, Koray K, David S et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"issue":"6","key":"10492_CR18","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1177\/0278364908091463","volume":"27","author":"J Nakanishi","year":"2008","unstructured":"Nakanishi J, Cory R, Mistry M et al (2008) Operational space control: a theoretical and empirical comparison. Int J Robot Res 27(6):737\u2013757","journal-title":"Int J Robot Res"},{"issue":"11","key":"10492_CR19","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1177\/0278364913495721","volume":"32","author":"J Kober","year":"2013","unstructured":"Kober J, Bagnell JA, Peters J (2013) Reinforcement learning in robotics: a survey. Int J Robot Res 32(11):1238\u20131274","journal-title":"Int J Robot Res"},{"key":"10492_CR20","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, et al. (2016). Continuous control with deep reinforcement learning. In: 4th International Conference on Learning Representations (ICLR 2016). https:\/\/arxiv.org\/pdf\/1509.02971v2.pdf."},{"key":"10492_CR21","doi-asserted-by":"publisher","unstructured":"Sehgal A, Ward N, La1 H, Louis S (2022) Automatic parameter optimization using genetic algorithm in deep reinforcement learning. https:\/\/doi.org\/10.48550\/arXiv.2204.03656.","DOI":"10.48550\/arXiv.2204.03656"},{"key":"10492_CR22","unstructured":"Heess N, Dhruva TB, Sriram S, Lemmon J, Silver D (2017) Emergence of locomotion behaviours in rich environments. https:\/\/arxiv.org\/pdf\/1707.02286."},{"key":"10492_CR23","unstructured":"Schulman J, Wolski F, Dhariwal P, et al. (2017) Proximal policy optimization algorithms. https:\/\/arxiv.org\/pdf\/1707.06347.pdf."},{"key":"10492_CR24","unstructured":"Schulman J, Levine S, Moritz P, et al. (2015) Trust Region Policy Optimization. In: ICML\u201915: Proceedings of the 32nd International Conference on International Conference on Machine Learning. 37:1889\u20131897. https:\/\/arxiv.org\/pdf\/1502.05477.pdf."}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10492-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-10492-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10492-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,5]],"date-time":"2025-02-05T21:56:15Z","timestamp":1738792575000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-10492-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,10]]},"references-count":24,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["10492"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-10492-9","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2024,10,10]]},"assertion":[{"value":"23 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 October 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 conflicts of interest to report regarding the present study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The problems and experiments studied in this paper do not involve ethical issues.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The author\u2019s research institutions are known and have approved the authors to do this study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}