{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:10:54Z","timestamp":1750219854811,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T00:00:00Z","timestamp":1685059200000},"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":[[2023,5,26]]},"DOI":"10.1145\/3603781.3603897","type":"proceedings-article","created":{"date-parts":[[2023,7,27]],"date-time":"2023-07-27T18:02:29Z","timestamp":1690480949000},"page":"658-662","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Reinforcement Learning Based UAV Mission Planning with Charging Module"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5881-938X","authenticated-orcid":false,"given":"Yanfan","family":"Zhang","sequence":"first","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0527-5103","authenticated-orcid":false,"given":"Hongyuan","family":"Zheng","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8939-199X","authenticated-orcid":false,"given":"Xiangping","family":"Zhai","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,, China"}]}],"member":"320","published-online":{"date-parts":[[2023,7,27]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.3233\/JIFS-179130"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_2_1","DOI":"10.1063\/1.5114366"},{"key":"e_1_3_2_1_3_1","volume-title":"Energy","author":"Qin Haosen","year":"2023","unstructured":"Qin Haosen Energy-efficient heating control for nearly zero energy residential buildings with deep reinforcement learning[J] . Energy , 2023 , 264 Qin Haosen Energy-efficient heating control for nearly zero energy residential buildings with deep reinforcement learning[J]. Energy, 2023, 264"},{"key":"e_1_3_2_1_4_1","volume-title":"`Deep reinforcement learning that matters.'' arXiv preprint arXiv:1709.06560","author":"Henderson","year":"2017","unstructured":"Henderson , Peter , ` `Deep reinforcement learning that matters.'' arXiv preprint arXiv:1709.06560 ( 2017 ). Henderson, Peter, ``Deep reinforcement learning that matters.'' arXiv preprint arXiv:1709.06560 (2017)."},{"key":"e_1_3_2_1_5_1","volume-title":"Barto","author":"Sutton R.S.","year":"1998","unstructured":"Sutton , R.S. , Barto , A.G. : Reinforcement Learning: an Introduction. MIT Press , Cambridge ( 1998 ). Sutton, R.S., Barto, A.G.: Reinforcement Learning: an Introduction. MIT Press, Cambridge (1998)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.1007\/BF00992698"},{"key":"e_1_3_2_1_7_1","first-page":"3402","volume-title":"Proceedings of Chinese Control Conference (CCC)","author":"Zhao Y.","year":"2017","unstructured":"Zhao , Y. , Zheng , Z. , Zhang , X. , Liu , Y. : Q learning algorithm based UAV path learning and obstacle avoidance approach . In: Proceedings of Chinese Control Conference (CCC) , pp. 3397\u2013 3402 ( 2017 ). Zhao, Y., Zheng, Z., Zhang, X., Liu, Y.: Q learning algorithm based UAV path learning and obstacle avoidance approach. In: Proceedings of Chinese Control Conference (CCC), pp. 3397\u20133402 (2017)."},{"unstructured":"Li Y.: Deep Reinforcement Learning: an Overview. arXiv: 1701.07274(2017).  Li Y.: Deep Reinforcement Learning: an Overview. arXiv: 1701.07274(2017).","key":"e_1_3_2_1_8_1"},{"key":"e_1_3_2_1_9_1","volume-title":"Riedmiller","author":"Mnih V.","year":"2013","unstructured":"Mnih , V. , Kavukcuoglu , K. , Silver , D. , Graves , A. , Antonoglou , I. , Wierstra , D. , Riedmiller , M. : Playing atari with deep reinforcement learning. arXiv:1312.5602( 2013 ). Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. arXiv:1312.5602(2013)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_10_1","DOI":"10.1038\/nature14236"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.1109\/TWC.2016.2633522"},{"key":"e_1_3_2_1_12_1","first-page":"1","article-title":"`Path Planning for UAV Ground Target Tracking via Deep Reinforcement Learning","volume":"99","author":"Li B.","year":"2020","unstructured":"Li , B. , and Y. Wu . ` `Path Planning for UAV Ground Target Tracking via Deep Reinforcement Learning .'' IEEE Access PP . 99 ( 2020 ): 1 - 1 . Li, B. , and Y. Wu . ``Path Planning for UAV Ground Target Tracking via Deep Reinforcement Learning.'' IEEE Access PP.99(2020):1-1.","journal-title":"IEEE Access PP"},{"key":"e_1_3_2_1_13_1","first-page":"98","article-title":"`Towards Real-Time Path Planning through Deep Reinforcement Learning for a UAV in Dynamic Environments","volume":"2","author":"Yan C. , X.","year":"2020","unstructured":"Yan , C. , X. Xiang , and C. Wang . ` `Towards Real-Time Path Planning through Deep Reinforcement Learning for a UAV in Dynamic Environments .'' Journal of Intelligent & Robotic Systems: Theory & Application 2 ( 2020 ): 98 . Yan, C. , X. Xiang , and C. Wang . ``Towards Real-Time Path Planning through Deep Reinforcement Learning for a UAV in Dynamic Environments.'' Journal of Intelligent & Robotic Systems: Theory & Application 2(2020):98.","journal-title":"Journal of Intelligent & Robotic Systems: Theory & Application"},{"unstructured":"Sutton R S McAllester D A Singh S P Policy gradient methods for reinforcement learning with function approximation[C]\/\/Advances in neural information processing systems. 2000: 1057-1063.  Sutton R S McAllester D A Singh S P Policy gradient methods for reinforcement learning with function approximation[C]\/\/Advances in neural information processing systems. 2000: 1057-1063.","key":"e_1_3_2_1_14_1"},{"key":"e_1_3_2_1_15_1","first-page":"1","article-title":"`3D UAV Trajectory Design and Frequency Band Allocation for Energy-Efficient and Fair Communication: A Deep Reinforcement Learning Approach","volume":"99","author":"Ding R. , F.","year":"2020","unstructured":"Ding , R. , F. Gao , and X. S. Shen . ` `3D UAV Trajectory Design and Frequency Band Allocation for Energy-Efficient and Fair Communication: A Deep Reinforcement Learning Approach .'' IEEE Transactions on Wireless Communications PP . 99 ( 2020 ): 1 - 1 . Ding, R. , F. Gao , and X. S. Shen . ``3D UAV Trajectory Design and Frequency Band Allocation for Energy-Efficient and Fair Communication: A Deep Reinforcement Learning Approach.'' IEEE Transactions on Wireless Communications PP.99(2020):1-1.","journal-title":"IEEE Transactions on Wireless Communications PP"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1109\/TSMCC.2012.2218595"},{"unstructured":"Raghuram Bharadwaj Diddigi Actor-Critic Algorithms for Constrained Multi-agent Reinforcement Learning.[J]. CoRR 2019 abs\/1905.02907  Raghuram Bharadwaj Diddigi Actor-Critic Algorithms for Constrained Multi-agent Reinforcement Learning.[J]. CoRR 2019 abs\/1905.02907","key":"e_1_3_2_1_17_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1016\/j.conb.2008.08.003"},{"key":"e_1_3_2_1_19_1","volume-title":"CoRR","author":"Timothy P.","year":"2015","unstructured":"Timothy P. Lillicrap Continuous control with deep reinforcement learning.[J] . CoRR , 2015 , abs\/1509.02971 Timothy P. Lillicrap Continuous control with deep reinforcement learning.[J]. CoRR, 2015, abs\/1509.02971"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.1063\/1.5114366"},{"key":"e_1_3_2_1_21_1","first-page":"11","volume":"2022","author":"Novel Feature-Selection Method","unstructured":"A Novel Feature-Selection Method for Human Activity Recognition in Videos\u201d , Electronics Journal 2022 , 11 , 732 A Novel Feature-Selection Method for Human Activity Recognition in Videos\u201d, Electronics Journal 2022, 11, 732","journal-title":"Electronics Journal"}],"event":{"acronym":"CNIOT'23","name":"CNIOT'23: 2023 4th International Conference on Computing, Networks and Internet of Things","location":"Xiamen China"},"container-title":["Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603781.3603897","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3603781.3603897","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:11Z","timestamp":1750178831000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603781.3603897"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,26]]},"references-count":21,"alternative-id":["10.1145\/3603781.3603897","10.1145\/3603781"],"URL":"https:\/\/doi.org\/10.1145\/3603781.3603897","relation":{},"subject":[],"published":{"date-parts":[[2023,5,26]]},"assertion":[{"value":"2023-07-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}