{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T22:03:56Z","timestamp":1767650636197,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2060, U21B2036, 61971267"],"award-info":[{"award-number":["U20B2060, U21B2036, 61971267"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3542679","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:12Z","timestamp":1660331172000},"page":"4684-4694","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Reinforcement Learning Enhances the Experts"],"prefix":"10.1145","author":[{"given":"Qianyue","family":"Hao","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Wenzhen","family":"Huang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Fengli","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, IL, USA"}]},{"given":"Kun","family":"Tang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Yong","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Nature","volume":"599","author":"Bastani Hamsa","year":"2021","unstructured":"Hamsa Bastani, Kimon Drakopoulos, Vishal Gupta, Ioannis Vlachogiannis, Christos Hadjicristodoulou, Pagona Lagiou, Gkikas Magiorkinis, Dimitrios Paraskevis, and Sotirios Tsiodras. 2021. Efficient and targeted COVID-19 border testing via reinforcement learning. Nature, Vol. 599, 7883 (2021), 108--113."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa324"},{"key":"e_1_3_2_2_3_1","volume-title":"Science","volume":"371","author":"Bubar Kate M","year":"2021","unstructured":"Kate M Bubar, Kyle Reinholt, Stephen M Kissler, Marc Lipsitch, Sarah Cobey, Yonatan H Grad, and Daniel B Larremore. 2021. Model-informed COVID-19 vaccine prioritization strategies by age and serostatus. Science, Vol. 371, 6532 (2021), 916--921."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1177\/0272989X12437247"},{"key":"e_1_3_2_2_5_1","volume-title":"Jaline Gerardin, Beth Redbird, David Grusky, and Jure Leskovec.","author":"Chang Serina","year":"2021","unstructured":"Serina Chang, Emma Pierson, Pang Wei Koh, Jaline Gerardin, Beth Redbird, David Grusky, and Jure Leskovec. 2021. Mobility network models of COVID-19 explain inequities and inform reopening. Nature, Vol. 589, 7840 (2021), 82--87."},{"volume-title":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.","author":"Chang Serina","key":"e_1_3_2_2_6_1","unstructured":"Serina Chang, Mandy L Wilson, Bryan Lewis, Zakaria Mehrab, Komal K Dudakiya, Emma Pierson, Pang Wei Koh, Jaline Gerardin, Beth Redbird, David Grusky, et almbox. [n.d.]. Supporting covid-19 policy response with large-scale mobility-based modeling. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining."},{"key":"e_1_3_2_2_7_1","volume-title":"Strategic COVID-19 vaccine distribution can simultaneously elevate social utility and equity. arXiv preprint arXiv:2111.06689","author":"Chen Lin","year":"2021","unstructured":"Lin Chen, Fengli Xu, Zhenyu Han, Kun Tang, Pan Hui, James Evans, and Yong Li. 2021. Strategic COVID-19 vaccine distribution can simultaneously elevate social utility and equity. arXiv preprint arXiv:2111.06689 (2021)."},{"key":"e_1_3_2_2_8_1","volume-title":"Winter of omicron-the evolving COVID-19 pandemic. JAMA","author":"Rio Carlos Del","year":"2021","unstructured":"Carlos Del Rio, Saad B Omer, and Preeti N Malani. 2021. Winter of omicron-the evolving COVID-19 pandemic. JAMA (2021)."},{"key":"e_1_3_2_2_9_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.abe2803"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Jim AC Everett Clara Colombatto Edmond Awad Paulo Boggio Bj\u00f6rn Bos William J Brady Megha Chawla Vladimir Chituc Dongil Chung Moritz A Drupp et al. 2021. Moral dilemmas and trust in leaders during a global health crisis. Nature human behaviour Vol. 5 8 (2021) 1074--1088.","DOI":"10.1038\/s41562-021-01156-y"},{"key":"e_1_3_2_2_12_1","volume-title":"International conference on machine learning. PMLR, 1792--1801","author":"Greydanus Samuel","year":"2018","unstructured":"Samuel Greydanus, Anurag Koul, Jonathan Dodge, and Alan Fern. 2018. Visualizing and understanding atari agents. In International conference on machine learning. PMLR, 1792--1801."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3412860"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_2_15_1","unstructured":"Yuanshuang Jiang Linfang Hou Yuxiang Liu Zhuoye Ding Yong Zhang and Shengzhong Feng. 2020. Epidemic Control Based on Reinforcement Learning Approaches. (2020)."},{"key":"e_1_3_2_2_16_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."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0251550"},{"key":"e_1_3_2_2_18_1","volume-title":"Science Advances","volume":"7","author":"Matrajt Laura","year":"2021","unstructured":"Laura Matrajt, Julia Eaton, Tiffany Leung, and Elizabeth R Brown. 2021. Vaccine optimization for COVID-19: Who to vaccinate first? Science Advances, Vol. 7, 6 (2021), eabf1374."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"John N Nkengasong Nicaise Ndembi Akhona Tshangela and Tajudeen Raji. 2020. COVID-19 vaccines: how to ensure Africa has access.","DOI":"10.1038\/d41586-020-02774-8"},{"key":"e_1_3_2_2_20_1","volume-title":"Md Hamid, et al.","author":"Ohi Abu Quwsar","year":"2020","unstructured":"Abu Quwsar Ohi, MF Mridha, Muhammad Mostafa Monowar, Md Hamid, et al. 2020. Exploring optimal control of epidemic spread using reinforcement learning. Scientific reports, Vol. 10, 1 (2020), 1--19."},{"key":"e_1_3_2_2_21_1","unstructured":"World Health Organization et al. 2020. WHO SAGE values framework for the allocation and prioritization of COVID-19 vaccination 14 September 2020. Technical Report. World Health Organization."},{"key":"e_1_3_2_2_22_1","volume-title":"International conference on complex networks and their applications. Springer, 229--240","author":"Par\u00e9s Ferran","year":"2017","unstructured":"Ferran Par\u00e9s, Dario Garcia Gasulla, Armand Vilalta, Jonatan Moreno, Eduard Ayguad\u00e9, Jes\u00fas Labarta, Ulises Cort\u00e9s, and Toyotaro Suzumura. 2017. Fluid communities: a competitive, scalable and diverse community detection algorithm. In International conference on complex networks and their applications. Springer, 229--240."},{"key":"e_1_3_2_2_23_1","volume-title":"Public perspectives on COVID-19 vaccine prioritization. JAMA network open","author":"Persad Govind","year":"2021","unstructured":"Govind Persad, Ezekiel J Emanuel, Samantha Sangenito, Aaron Glickman, Steven Phillips, and Emily A Largent. 2021. Public perspectives on COVID-19 vaccine prioritization. JAMA network open, Vol. 4, 4 (2021), e217943--e217943."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2020.18513"},{"key":"e_1_3_2_2_25_1","unstructured":"Stefano Giovanni Rizzo. 2020. Balancing precision and recall for costeffective epidemic containment. (2020)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01379-6"},{"key":"e_1_3_2_2_27_1","volume-title":"High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438","author":"Schulman John","year":"2015","unstructured":"John Schulman, Philipp Moritz, Sergey Levine, Michael Jordan, and Pieter Abbeel. 2015. High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438 (2015)."},{"key":"e_1_3_2_2_28_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_2_29_1","volume-title":"Data-efficient reinforcement learning with self-predictive representations. arXiv preprint arXiv:2007.05929","author":"Schwarzer Max","year":"2020","unstructured":"Max Schwarzer, Ankesh Anand, Rishab Goel, R Devon Hjelm, Aaron Courville, and Philip Bachman. 2020. Data-efficient reinforcement learning with self-predictive representations. arXiv preprint arXiv:2007.05929 (2020)."},{"key":"e_1_3_2_2_30_1","volume-title":"Curl: Contrastive unsupervised representations for reinforcement learning. arXiv preprint arXiv:2004.04136","author":"Srinivas Aravind","year":"2020","unstructured":"Aravind Srinivas, Michael Laskin, and Pieter Abbeel. 2020. Curl: Contrastive unsupervised representations for reinforcement learning. arXiv preprint arXiv:2004.04136 (2020)."},{"key":"e_1_3_2_2_31_1","volume-title":"COVID-19 attack rate increases with city size. arXiv preprint arXiv:2003.10376","author":"Stier Andrew J","year":"2020","unstructured":"Andrew J Stier, Marc G Berman, and Luis Bettencourt. 2020. COVID-19 attack rate increases with city size. arXiv preprint arXiv:2003.10376 (2020)."},{"key":"e_1_3_2_2_32_1","volume-title":"International Conference on Machine Learning. PMLR, 9870--9879","author":"Stooke Adam","year":"2021","unstructured":"Adam Stooke, Kimin Lee, Pieter Abbeel, and Michael Laskin. 2021. Decoupling representation learning from reinforcement learning. In International Conference on Machine Learning. PMLR, 9870--9879."},{"key":"e_1_3_2_2_33_1","volume-title":"Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853","author":"Xu Bing","year":"2015","unstructured":"Bing Xu, Naiyan Wang, Tianqi Chen, and Mu Li. 2015. Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 (2015)."},{"key":"e_1_3_2_2_34_1","volume-title":"Improving sample efficiency in model-free reinforcement learning from images. arXiv preprint arXiv:1910.01741","author":"Yarats Denis","year":"2019","unstructured":"Denis Yarats, Amy Zhang, Ilya Kostrikov, Brandon Amos, Joelle Pineau, and Rob Fergus. 2019. Improving sample efficiency in model-free reinforcement learning from images. arXiv preprint arXiv:1910.01741 (2019)."},{"key":"e_1_3_2_2_35_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Yu Tao","year":"2021","unstructured":"Tao Yu, Cuiling Lan, Wenjun Zeng, Mingxiao Feng, Zhizheng Zhang, and Zhibo Chen. 2021. Playvirtual: Augmenting cycle-consistent virtual trajectories for reinforcement learning. Advances in Neural Information Processing Systems, Vol. 34 (2021)."}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Washington DC USA","acronym":"KDD '22"},"container-title":["Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3542679","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3542679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:53Z","timestamp":1750186973000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3542679"}},"subtitle":["Large-scale COVID-19 Vaccine Allocation with Multi-factor Contact Network"],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":35,"alternative-id":["10.1145\/3534678.3542679","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3542679","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}