{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T10:23:53Z","timestamp":1771669433189,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,8,14]],"date-time":"2021-08-14T00:00:00Z","timestamp":1628899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0106000"],"award-info":[{"award-number":["2020AAA0106000"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1936217, 61971267, 61972223, 61941117, 61861136003"],"award-info":[{"award-number":["U1936217, 61971267, 61972223, 61941117, 61861136003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["L182038"],"award-info":[{"award-number":["L182038"]}]},{"DOI":"10.13039\/501100017582","name":"Beijing National Research Center For Information Science And Technology","doi-asserted-by":"publisher","award":["20031887521"],"award-info":[{"award-number":["20031887521"]}],"id":[{"id":"10.13039\/501100017582","id-type":"DOI","asserted-by":"publisher"}]},{"name":"research fund of Tsinghua University - Tencent Joint Laboratory for Internet Innovation Technology"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,8,14]]},"DOI":"10.1145\/3447548.3467181","type":"proceedings-article","created":{"date-parts":[[2021,8,13]],"date-time":"2021-08-13T18:21:39Z","timestamp":1628878899000},"page":"2955-2963","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Hierarchical Reinforcement Learning for Scarce Medical Resource Allocation with Imperfect Information"],"prefix":"10.1145","author":[{"given":"Qianyue","family":"Hao","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengli","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, HongKong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"Hui","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, HongKong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1177\/0272989X12437247"},{"key":"e_1_3_2_2_2_1","volume-title":"Fethi Bougares, Holger Schwenk, and Yoshua Bengio.","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho , Bart van Merrienboer , cC aglar G\u00fc lcc ehre , Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014 . Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. CoRR , Vol. abs\/ 1406 .1078 (2014). Kyunghyun Cho, Bart van Merrienboer, cC aglar G\u00fc lcc ehre, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. CoRR, Vol. abs\/1406.1078 (2014)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.idm.2020.04.001"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMsb2005114"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.110599"},{"key":"e_1_3_2_2_6_1","volume-title":"Preferences for scarce medical resource allocation: Differences between experts and the general public and implications for the COVID-19 pandemic. British journal of health psychology","author":"Grover Simmy","year":"2020","unstructured":"Simmy Grover , Alastair McClelland , and Adrian Furnham . 2020. Preferences for scarce medical resource allocation: Differences between experts and the general public and implications for the COVID-19 pandemic. British journal of health psychology , Vol. 25 , 4 ( 2020 ), 889--901. Simmy Grover, Alastair McClelland, and Adrian Furnham. 2020. Preferences for scarce medical resource allocation: Differences between experts and the general public and implications for the COVID-19 pandemic. British journal of health psychology, Vol. 25, 4 (2020), 889--901."},{"key":"e_1_3_2_2_7_1","volume-title":"David SC Hui, et al","author":"Hu Yu","year":"2020","unstructured":"Wei-jie Guan, Zheng-yi Ni, Yu Hu , Wen-hua Liang, Chun-quan Ou, Jian-xing He, Lei Liu , Hong Shan , Chun-liang Lei , David SC Hui, et al . 2020 . Clinical characteristics of coronavirus disease 2019 in China. New England journal of medicine, Vol. 382 , 18 (2020), 1708--1720. Wei-jie Guan, Zheng-yi Ni, Yu Hu, Wen-hua Liang, Chun-quan Ou, Jian-xing He, Lei Liu, Hong Shan, Chun-liang Lei, David SC Hui, et al. 2020. Clinical characteristics of coronavirus disease 2019 in China. New England journal of medicine, Vol. 382, 18 (2020), 1708--1720."},{"key":"e_1_3_2_2_8_1","volume-title":"Peng Wu, Xilong Deng, Jian Wang, Xinxin Hao, Yiu Chung Lau, Jessica Y Wong, Yujuan Guan, Xinghua Tan, et al.","author":"He Xi","year":"2020","unstructured":"Xi He , Eric HY Lau , Peng Wu, Xilong Deng, Jian Wang, Xinxin Hao, Yiu Chung Lau, Jessica Y Wong, Yujuan Guan, Xinghua Tan, et al. 2020 . Temporal dynamics in viral shedding and transmissibility of COVID-19. Nature medicine, Vol. 26 , 5 (2020), 672--675. Xi He, Eric HY Lau, Peng Wu, Xilong Deng, Jian Wang, Xinxin Hao, Yiu Chung Lau, Jessica Y Wong, Yujuan Guan, Xinghua Tan, et al. 2020. Temporal dynamics in viral shedding and transmissibility of COVID-19. Nature medicine, Vol. 26, 5 (2020), 672--675."},{"key":"e_1_3_2_2_9_1","article-title":"Population density, call-response interval, and survival of out-of-hospital cardiac arrest","volume":"10","author":"Seizan Tanabe Manabu Akahane Hiromasa Horiguchi","year":"2011","unstructured":"Hiromasa Horiguchi Seizan Tanabe Manabu Akahane Toshio Ogawa Soichi Koike Tomoaki Imamura Hideo Yasunaga , Hiroaki Miyata . 2011 . Population density, call-response interval, and survival of out-of-hospital cardiac arrest . International Journal of Health Geographics , Vol. 10 , 26 (2011). Hiromasa Horiguchi Seizan Tanabe Manabu Akahane Toshio Ogawa Soichi Koike Tomoaki Imamura Hideo Yasunaga, Hiroaki Miyata. 2011. Population density, call-response interval, and survival of out-of-hospital cardiac arrest. International Journal of Health Geographics, Vol. 10, 26 (2011).","journal-title":"International Journal of Health Geographics"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(20)30183-5"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2980158"},{"key":"e_1_3_2_2_12_1","volume-title":"Designing a hybrid reinforcement learning based algorithm with application in prediction of the COVID-19 pandemic in Quebec. Annals of Operations Research","author":"Khalilpourazari Soheyl","year":"2021","unstructured":"Soheyl Khalilpourazari and Hossein Hashemi Doulabi . 2021. Designing a hybrid reinforcement learning based algorithm with application in prediction of the COVID-19 pandemic in Quebec. Annals of Operations Research ( 2021 ), 1--45. Soheyl Khalilpourazari and Hossein Hashemi Doulabi. 2021. Designing a hybrid reinforcement learning based algorithm with application in prediction of the COVID-19 pandemic in Quebec. Annals of Operations Research (2021), 1--45."},{"key":"e_1_3_2_2_13_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0251550"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/0025-5564(95)92756-5"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2001316"},{"key":"e_1_3_2_2_17_1","volume-title":"Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971","author":"Lillicrap Timothy P","year":"2015","unstructured":"Timothy P Lillicrap , Jonathan J Hunt , Alexander Pritzel , Nicolas Heess , Tom Erez , Yuval Tassa , David Silver , and Daan Wierstra . 2015. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 ( 2015 ). Timothy P Lillicrap, Jonathan J Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. 2015. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei A Rusu Joel Veness Marc G Bellemare Alex Graves Martin Riedmiller Andreas K Fidjeland Georg Ostrovski etal 2015. Human-level control through deep reinforcement learning. nature Vol. 518 7540 (2015) 529--533.  Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei A Rusu Joel Veness Marc G Bellemare Alex Graves Martin Riedmiller Andreas K Fidjeland Georg Ostrovski et al. 2015. Human-level control through deep reinforcement learning. nature Vol. 518 7540 (2015) 529--533.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_2_19_1","volume-title":"Muhammad Mostafa Monowar, and Md Abdul Hamid","author":"Ohi Abu Quwsar","year":"2020","unstructured":"Abu Quwsar Ohi , MF Mridha , Muhammad Mostafa Monowar, and Md Abdul Hamid . 2020 . Exploring optimal control of epidemic spread using reinforcement learning. Scientific reports, Vol. 10 , 1 (2020), 1--19. Abu Quwsar Ohi, MF Mridha, Muhammad Mostafa Monowar, and Md Abdul Hamid. 2020. Exploring optimal control of epidemic spread using reinforcement learning. Scientific reports, Vol. 10, 1 (2020), 1--19."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(09)60137-9"},{"key":"e_1_3_2_2_21_1","volume-title":"Deep reinforcement learning for de novo drug design. Science advances","author":"Popova Mariya","year":"2018","unstructured":"Mariya Popova , Olexandr Isayev , and Alexander Tropsha . 2018. Deep reinforcement learning for de novo drug design. Science advances , Vol. 4 , 7 ( 2018 ), eaap7885. Mariya Popova, Olexandr Isayev, and Alexander Tropsha. 2018. Deep reinforcement learning for de novo drug design. Science advances, Vol. 4, 7 (2018), eaap7885."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp2006141"},{"key":"e_1_3_2_2_23_1","unstructured":"Sara J Rosenbaum etal 2011. Ethical considerations for decision making regarding allocation of mechanical ventilators during a severe influenza pandemic or other public health emergency. (2011).  Sara J Rosenbaum et al. 2011. Ethical considerations for decision making regarding allocation of mechanical ventilators during a severe influenza pandemic or other public health emergency. (2011)."},{"key":"e_1_3_2_2_24_1","volume-title":"The 2006 IEEE International Joint Conference on Neural Network Proceedings. IEEE, 511--517","author":"Sahba Farhang","year":"2006","unstructured":"Farhang Sahba , Hamid R Tizhoosh , and Magdy MA Salama . 2006 . A reinforcement learning framework for medical image segmentation . In The 2006 IEEE International Joint Conference on Neural Network Proceedings. IEEE, 511--517 . Farhang Sahba, Hamid R Tizhoosh, and Magdy MA Salama. 2006. A reinforcement learning framework for medical image segmentation. In The 2006 IEEE International Joint Conference on Neural Network Proceedings. IEEE, 511--517."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1258\/147775006779151201"},{"key":"e_1_3_2_2_26_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S","unstructured":"Richard S Sutton and Andrew G Barto . 2018. Reinforcement learning: An introduction . MIT press . Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction .MIT press."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(20)30260-9"}],"event":{"name":"KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Virtual Event Singapore","acronym":"KDD '21","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447548.3467181","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3447548.3467181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:27Z","timestamp":1750191507000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447548.3467181"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,14]]},"references-count":28,"alternative-id":["10.1145\/3447548.3467181","10.1145\/3447548"],"URL":"https:\/\/doi.org\/10.1145\/3447548.3467181","relation":{},"subject":[],"published":{"date-parts":[[2021,8,14]]},"assertion":[{"value":"2021-08-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}