{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:02:42Z","timestamp":1750309362770,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":13,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T00:00:00Z","timestamp":1705622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1,19]]},"DOI":"10.1145\/3674225.3674388","type":"proceedings-article","created":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T18:23:05Z","timestamp":1722450185000},"page":"907-911","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Reinforcement Learning Based Quadrotor Control with Low Function Approximation Errors"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8881-6722","authenticated-orcid":false,"given":"Zihao","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing Microelectronics Technology Institute, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4766-3040","authenticated-orcid":false,"given":"Zhenlin","family":"Lu","sequence":"additional","affiliation":[{"name":"Beijing Microelectronics Technology Institute, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4794-713X","authenticated-orcid":false,"given":"Yongzheng","family":"Ren","sequence":"additional","affiliation":[{"name":"Beijing Microelectronics Technology Institute, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0831-9723","authenticated-orcid":false,"given":"Jinye","family":"Rong","sequence":"additional","affiliation":[{"name":"Beijing Microelectronics Technology Institute, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8732-7977","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7479-5910","authenticated-orcid":false,"given":"Shikai","family":"Sun","sequence":"additional","affiliation":[{"name":"Beijing Microelectronics Technology Institute, China"}]}],"member":"320","published-online":{"date-parts":[[2024,7,31]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10090999"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3312221"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340934"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2971780"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1142\/S2737480721500059"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2023.3265214"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635857"},{"key":"e_1_3_2_1_8_1","volume-title":"Accessed","author":"Pentaliotis A.","year":"2024","unstructured":"A. Pentaliotis, \u201cInvestigating Overestimation Bias in Reinforcement Learning,\u201d master, 2020. Accessed: Jan. 16, 2024. [Online]. Available: https:\/\/fse.studenttheses.ub.rug.nl\/22173\/"},{"key":"e_1_3_2_1_9_1","first-page":"1596","volume-title":"Proceedings of the 35th International Conference on Machine Learning, PMLR","author":"Fujimoto S.","year":"2018","unstructured":"S. Fujimoto, H. Hoof, and D. Meger, \u201cAddressing Function Approximation Error in Actor-Critic Methods,\u201d in Proceedings of the 35th International Conference on Machine Learning, PMLR, Jul. 2018, pp. 1587\u20131596. Accessed: Jan. 16, 2024. [Online]. Available: https:\/\/proceedings.mlr.press\/v80\/fujimoto18a.html"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"e_1_3_2_1_11_1","first-page":"2100","volume-title":"AAAI Conference on Artificial Intelligence. Palo Alto: Assoc Advancement Artificial Intelligence","author":"van Hasselt H.","year":"2016","unstructured":"H. van Hasselt, A. Guez, and D. Silver, \u201cDeep Reinforcement Learning with Double Q-Learning,\u201d in THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, in AAAI Conference on Artificial Intelligence. Palo Alto: Assoc Advancement Artificial Intelligence, 2016, pp. 2094\u20132100. Accessed: Jan. 16, 2024. [Online]. Available: https:\/\/www.webofscience.com\/wos\/alldb\/full-record\/WOS:000485474202019"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1707.06347"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1509.02971"}],"event":{"name":"PEAI 2024: 2024 International Conference on Power Electronics and Artificial Intelligence","acronym":"PEAI 2024","location":"Xiamen China"},"container-title":["2024 International Conference on Power Electronics and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674225.3674388","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3674225.3674388","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:03Z","timestamp":1750291563000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674225.3674388"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,19]]},"references-count":13,"alternative-id":["10.1145\/3674225.3674388","10.1145\/3674225"],"URL":"https:\/\/doi.org\/10.1145\/3674225.3674388","relation":{},"subject":[],"published":{"date-parts":[[2024,1,19]]},"assertion":[{"value":"2024-07-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}