{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:09:21Z","timestamp":1750219761953,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T00:00:00Z","timestamp":1689897600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"The Key Project of the 2022 College Students Innovation and Entrepreneurship Training Program","award":["202210060030"],"award-info":[{"award-number":["202210060030"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,21]]},"DOI":"10.1145\/3611450.3611457","type":"proceedings-article","created":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T01:59:46Z","timestamp":1692583186000},"page":"44-49","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on Control Strategy of Manipulator Based on Deep Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5346-6270","authenticated-orcid":false,"given":"Nuo","family":"Xu","sequence":"first","affiliation":[{"name":"National Demonstration Center for Experimental Mechanical and Electrical Engineering Educatio, Tianjin University of Technology, China and \rTianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control, Tianjin University of Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4735-4981","authenticated-orcid":false,"given":"Yanpeng","family":"Shao","sequence":"additional","affiliation":[{"name":"National Demonstration Center for Experimental Mechanical and Electrical Engineering Educatio, Tianjin University of Technology, China and \rTianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control, Tianjin University of Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3834-5009","authenticated-orcid":false,"given":"Xiaoyan","family":"Fan","sequence":"additional","affiliation":[{"name":"National Demonstration Center for Experimental Mechanical and Electrical Engineering Educatio, Tianjin University of Technology, China and \rTianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control, Tianjin University of Technology, China"}]}],"member":"320","published-online":{"date-parts":[[2023,8,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.3866\/PKU.WHXB201112303"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23073762"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3866\/PKU.WHXB201112303"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2010.43"},{"key":"e_1_3_2_1_6_1","unstructured":"Zhao Liyang Chang Tianqing 2023. A Review of Deep Reinforcement Learning for Fully Cooperative Classes of Multiple Intelligences. Computer Engineering and Applications: 1-17[2023-05-05]. http:\/\/kns.cnki.net\/kcms\/detail\/11.2127.TP.20230118.1659.012.html.  Zhao Liyang Chang Tianqing 2023. A Review of Deep Reinforcement Learning for Fully Cooperative Classes of Multiple Intelligences. Computer Engineering and Applications: 1-17[2023-05-05]. http:\/\/kns.cnki.net\/kcms\/detail\/11.2127.TP.20230118.1659.012.html."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.27005\/d.cnki.gdzku.2020.000549"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1509.06461"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.13462\/j.cnki.mmtamt.2022.07.004"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1507.06527"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2013.2264575"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2020.07.001"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"e_1_3_2_1_15_1","volume-title":"International conference on machine learning. PMLR","author":"Silver D","year":"2014","unstructured":"Silver D , Lever G , 2014 . Deterministic policy gradient algorithms . International conference on machine learning. PMLR , 2014: 6387-6395. http:\/\/dl.acm.org\/doi\/abs\/10.5555\/3044805.3044850 Silver D, Lever G, 2014. Deterministic policy gradient algorithms. International conference on machine learning. PMLR, 2014: 6387-6395. http:\/\/dl.acm.org\/doi\/abs\/10.5555\/3044805.3044850"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.05477"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1708.05144"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1098-3015(10)67722-4"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.27517\/d.cnki.gzkju.2020.000575"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.27061\/d.cnki.ghgdu.2020.001154"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.13462\/j.cnki.mmtamt.2021.12.009"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-021-00366-1"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.16356\/j.1005-2615.2022.01.005"},{"key":"e_1_3_2_1_24_1","unstructured":"FUJIMOTO S VAN HOOF H MEGER D. 2021. Addressing function approximation error in actor-critic methods.\u0f3b2021-02-25\u0f3d. http:\/\/arxiv.org\/abs\/1802.09477v1  FUJIMOTO S VAN HOOF H MEGER D. 2021. Addressing function approximation error in actor-critic methods.\u0f3b2021-02-25\u0f3d. http:\/\/arxiv.org\/abs\/1802.09477v1"},{"key":"e_1_3_2_1_25_1","first-page":"223","article-title":"Research on the manipulator intelligent trajectory planning method based on the improved TD3 algorithm","volume":"2022","author":"Zhang Qiang","year":"2022","unstructured":"Zhang Qiang , Wen Wen , 2022 . Research on the manipulator intelligent trajectory planning method based on the improved TD3 algorithm . Chinese Journal of Intelligent Science and Technology , 2022 ,4(02): 223 - 232 . http:\/\/qikan.cqvip.com\/Qikan\/Article\/Detail?id=7107433093 Zhang Qiang, Wen Wen, 2022. Research on the manipulator intelligent trajectory planning method based on the improved TD3 algorithm. Chinese Journal of Intelligent Science and Technology,2022,4(02):223-232. http:\/\/qikan.cqvip.com\/Qikan\/Article\/Detail?id=7107433093","journal-title":"Chinese Journal of Intelligent Science and Technology"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1602.01783"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2022.102918"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1801.01290"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.13398\/j.cnki.issn1673-260x.2020.10.008"},{"key":"e_1_3_2_1_30_1","volume-title":"The complexity of decentralized control of Markov decision processes. Mathematics of operations research","author":"Bernstein D S","year":"2002","unstructured":"Bernstein D S , Givan R , 2002. The complexity of decentralized control of Markov decision processes. Mathematics of operations research , 2002 , 27(4): 819-840. https:\/\/www.nstl.gov.cn\/paper_detail.html?id=c8a1e23b2458ff9ff0cc0ee9a21ff00a Bernstein D S, Givan R, 2002. The complexity of decentralized control of Markov decision processes. Mathematics of operations research, 2002, 27(4): 819-840. https:\/\/www.nstl.gov.cn\/paper_detail.html?id=c8a1e23b2458ff9ff0cc0ee9a21ff00a"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.27272\/d.cnki.gshdu.2022.005843"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3056903"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.3390\/app12199837"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20123515"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.3390\/app11041816"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.26969\/d.cnki.gbydu.2020.001762"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103535"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.13225\/j.cnki.jccs.2022.1589"}],"event":{"name":"AI2A '23: 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms","acronym":"AI2A '23","location":"Beijing China"},"container-title":["Proceedings of the 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3611450.3611457","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3611450.3611457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:09Z","timestamp":1750178229000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3611450.3611457"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,21]]},"references-count":39,"alternative-id":["10.1145\/3611450.3611457","10.1145\/3611450"],"URL":"https:\/\/doi.org\/10.1145\/3611450.3611457","relation":{},"subject":[],"published":{"date-parts":[[2023,7,21]]},"assertion":[{"value":"2023-08-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}