{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:31:17Z","timestamp":1750221077449,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,12,29]],"date-time":"2018-12-29T00:00:00Z","timestamp":1546041600000},"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":[[2018,12,29]]},"DOI":"10.1145\/3301551.3301552","type":"proceedings-article","created":{"date-parts":[[2019,3,11]],"date-time":"2019-03-11T12:33:01Z","timestamp":1552307581000},"page":"284-290","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Addressing the Task of Rocket Recycling with Deep Reinforcement Learning"],"prefix":"10.1145","author":[{"given":"Guangyin","family":"Jin","sequence":"first","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jincai","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanghe","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangquan","family":"Cheng","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhong","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,12,29]]},"reference":[{"issue":"2","key":"e_1_3_2_1_1_1","article-title":"Mathematical model for sounding rockets, using attitude and rotation angles","volume":"3","author":"Chelaru T.-V.","year":"2009","unstructured":"T.-V. Chelaru , and C. Barbu , \" Mathematical model for sounding rockets, using attitude and rotation angles ,\" Int. J. Appl. Math. Inf , vol. 3 , no. 2 , 2009 . T.-V. Chelaru, and C. Barbu, \"Mathematical model for sounding rockets, using attitude and rotation angles,\" Int. J. Appl. Math. Inf, vol. 3, no. 2, 2009.","journal-title":"Int. J. Appl. Math. Inf"},{"key":"e_1_3_2_1_2_1","volume-title":"Addressing Complexities of Machine Learning in Big Data: Principles, Trends and Challenges from Systematical Perspectives","author":"Wang Q.","year":"2017","unstructured":"Q. Wang , X. Zhao , J. Huang , Y. Feng , J. Su , and Z. Luo , \" Addressing Complexities of Machine Learning in Big Data: Principles, Trends and Challenges from Systematical Perspectives ,\" 2017 . Q. Wang, X. Zhao, J. Huang, Y. Feng, J. Su, and Z. Luo, \"Addressing Complexities of Machine Learning in Big Data: Principles, Trends and Challenges from Systematical Perspectives,\" 2017."},{"key":"e_1_3_2_1_3_1","volume-title":"Continuous control with deep reinforcement learning,\" arXiv preprint arXiv:1509.02971","author":"Lillicrap T. P.","year":"2015","unstructured":"T. P. Lillicrap , J. J. Hunt , A. Pritzel , N. Heess , T. Erez , Y. Tassa , D. Silver , and D. Wierstra , \" Continuous control with deep reinforcement learning,\" arXiv preprint arXiv:1509.02971 , 2015 . T. P. Lillicrap, J. J. Hunt, A. Pritzel, N. Heess, T. Erez, Y. Tassa, D. Silver, and D. Wierstra, \"Continuous control with deep reinforcement learning,\" arXiv preprint arXiv:1509.02971, 2015."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3176653.3176699"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"e_1_3_2_1_6_1","volume-title":"Playing atari with deep reinforcement learning,\" arXiv preprint arXiv:1312.5602","author":"Mnih V.","year":"2013","unstructured":"V. Mnih , K. Kavukcuoglu , D. Silver , A. Graves , I. Antonoglou , D. Wierstra , and M. Riedmiller , \" Playing atari with deep reinforcement learning,\" arXiv preprint arXiv:1312.5602 , 2013 . V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller, \"Playing atari with deep reinforcement learning,\" arXiv preprint arXiv:1312.5602, 2013."},{"key":"e_1_3_2_1_7_1","first-page":"2094","volume-title":"Deep Reinforcement Learning with Double Q-Learning","author":"Van Hasselt H.","unstructured":"H. Van Hasselt , A. Guez , and D. Silver , \" Deep Reinforcement Learning with Double Q-Learning .\" pp. 2094 -- 2100 . H. Van Hasselt, A. Guez, and D. Silver, \"Deep Reinforcement Learning with Double Q-Learning.\" pp. 2094--2100."},{"key":"e_1_3_2_1_8_1","volume-title":"Memory-based control with recurrent neural networks,\" arXiv preprint arXiv:1512.04455","author":"Heess N.","year":"2015","unstructured":"N. Heess , J. J. Hunt , T. P. Lillicrap , and D. Silver , \" Memory-based control with recurrent neural networks,\" arXiv preprint arXiv:1512.04455 , 2015 . N. Heess, J. J. Hunt, T. P. Lillicrap, and D. Silver, \"Memory-based control with recurrent neural networks,\" arXiv preprint arXiv:1512.04455, 2015."},{"key":"e_1_3_2_1_9_1","unstructured":"Z. Wang T. Schaul M. Hessel H. Van Hasselt M. Lanctot and N. De Freitas \"Dueling network architectures for deep reinforcement learning \" arXiv preprint arXiv:1511.06581 2015.  Z. Wang T. Schaul M. Hessel H. Van Hasselt M. Lanctot and N. De Freitas \"Dueling network architectures for deep reinforcement learning \" arXiv preprint arXiv:1511.06581 2015."},{"key":"e_1_3_2_1_10_1","volume-title":"Compatible value gradients for reinforcement learning of continuous deep policies,\" arXiv preprint arXiv:1509.03005","author":"Balduzzi D.","year":"2015","unstructured":"D. Balduzzi , and M. Ghifary , \" Compatible value gradients for reinforcement learning of continuous deep policies,\" arXiv preprint arXiv:1509.03005 , 2015 . D. Balduzzi, and M. Ghifary, \"Compatible value gradients for reinforcement learning of continuous deep policies,\" arXiv preprint arXiv:1509.03005, 2015."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.05.011"},{"key":"e_1_3_2_1_12_1","first-page":"1928","volume-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih V.","unstructured":"V. Mnih , A. P. Badia , M. Mirza , A. Graves , T. Lillicrap , T. Harley , D. Silver , and K. Kavukcuoglu , \" Asynchronous methods for deep reinforcement learning .\" pp. 1928 -- 1937 . V. Mnih, A. P. Badia, M. Mirza, A. Graves, T. Lillicrap, T. Harley, D. Silver, and K. Kavukcuoglu, \"Asynchronous methods for deep reinforcement learning.\" pp. 1928--1937."},{"key":"e_1_3_2_1_13_1","volume-title":"Proximal policy optimization algorithms,\" arXiv preprint arXiv:1707.06347","author":"Schulman J.","year":"2017","unstructured":"J. Schulman , F. Wolski , P. Dhariwal , A. Radford , and O. Klimov , \" Proximal policy optimization algorithms,\" arXiv preprint arXiv:1707.06347 , 2017 . J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, \"Proximal policy optimization algorithms,\" arXiv preprint arXiv:1707.06347, 2017."},{"key":"e_1_3_2_1_14_1","volume-title":"Emergence of locomotion behaviours in rich environments,\" arXiv preprint arXiv:1707.02286","author":"Heess N.","year":"2017","unstructured":"N. Heess , S. Sriram , J. Lemmon , J. Merel , G. Wayne , Y. Tassa , T. Erez , Z. Wang , A. Eslami , and M. Riedmiller , \" Emergence of locomotion behaviours in rich environments,\" arXiv preprint arXiv:1707.02286 , 2017 . N. Heess, S. Sriram, J. Lemmon, J. Merel, G. Wayne, Y. Tassa, T. Erez, Z. Wang, A. Eslami, and M. Riedmiller, \"Emergence of locomotion behaviours in rich environments,\" arXiv preprint arXiv:1707.02286, 2017."},{"key":"e_1_3_2_1_15_1","volume-title":"Rainbow: Combining Improvements in Deep Reinforcement Learning,\" arXiv preprint arXiv:1710.02298","author":"Hessel M.","year":"2017","unstructured":"M. Hessel , J. Modayil , H. Van Hasselt , T. Schaul , G. Ostrovski , W. Dabney , D. Horgan , B. Piot , M. Azar , and D. Silver , \" Rainbow: Combining Improvements in Deep Reinforcement Learning,\" arXiv preprint arXiv:1710.02298 , 2017 . M. Hessel, J. Modayil, H. Van Hasselt, T. Schaul, G. Ostrovski, W. Dabney, D. Horgan, B. Piot, M. Azar, and D. Silver, \"Rainbow: Combining Improvements in Deep Reinforcement Learning,\" arXiv preprint arXiv:1710.02298, 2017."}],"event":{"name":"ICIT 2018: IoT and Smart City","sponsor":["The Hong Kong Polytechnic The Hong Kong Polytechnic University","TU Tianjin University"],"location":"Hong Kong Hong Kong","acronym":"ICIT 2018"},"container-title":["Proceedings of the 6th International Conference on Information Technology: IoT and Smart City"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3301551.3301552","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3301551.3301552","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:57:35Z","timestamp":1750208255000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3301551.3301552"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,29]]},"references-count":15,"alternative-id":["10.1145\/3301551.3301552","10.1145\/3301551"],"URL":"https:\/\/doi.org\/10.1145\/3301551.3301552","relation":{},"subject":[],"published":{"date-parts":[[2018,12,29]]},"assertion":[{"value":"2018-12-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}