{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T21:05:39Z","timestamp":1783976739524,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,11,3]],"date-time":"2019-11-03T00:00:00Z","timestamp":1572739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["61632017"],"award-info":[{"award-number":["61632017"]}]},{"name":"National Natural Science Foundation of China","award":["61702327"],"award-info":[{"award-number":["61702327"]}]},{"name":"National Natural Science Foundation of China","award":["61772333"],"award-info":[{"award-number":["61772333"]}]},{"name":"National Natural Science Foundation of China","award":["61702362"],"award-info":[{"award-number":["61702362"]}]},{"name":"National Natural Science Foundation of China","award":["U1836214"],"award-info":[{"award-number":["U1836214"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,11,3]]},"DOI":"10.1145\/3357384.3357806","type":"proceedings-article","created":{"date-parts":[[2019,11,4]],"date-time":"2019-11-04T14:11:35Z","timestamp":1572876695000},"page":"2595-2603","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Learning Adaptive Display Exposure for Real-Time Advertising"],"prefix":"10.1145","author":[{"given":"Weixun","family":"Wang","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junqi","family":"Jin","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunjie","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuan","family":"Yu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weinan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"University College London, London, England UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaotian","family":"Hao","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixi","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Xu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Gai","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,11,3]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Joshua Achiam David Held Aviv Tamar and Pieter Abbeel. 2017. Constrained policy optimization. arXiv preprint arXiv: 1705.10528(2017).  Joshua Achiam David Held Aviv Tamar and Pieter Abbeel. 2017. Constrained policy optimization. arXiv preprint arXiv: 1705.10528(2017)."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of COLT. 4--18","author":"Agrawal Shipra","year":"2016"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","volume-title":"Constrained Markov decision processes","author":"Altman Eitan","DOI":"10.1201\/9781315140223"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of NIPS. 5048--5058","author":"Andrychowicz Marcin","year":"2017"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of AAAI. 1726--1734","author":"Bacon Pierre-Luc","year":"2017"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of COLT. 1109--1134","author":"Badanidiyuru Ashwinkumar","year":"2014"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018702"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186039"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220122"},{"key":"e_1_3_2_1_10_1","volume-title":"Deep learning","author":"Goodfellow Ian"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of AAAI.","author":"Hester Todd"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of SIGKDD.","author":"Hu Yujing","year":"2018"},{"key":"e_1_3_2_1_13_1","volume-title":"Tom Schaul, Joel Z Leibo, David Silver, and Koray Kavukcuoglu.","author":"Jaderberg Max","year":"2016"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3272021"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of NIPS. 3675--3683","author":"Kulkarni Tejas D","year":"2016"},{"key":"e_1_3_2_1_16_1","volume-title":"Deep learning. Nature 521, 7553","author":"LeCun Yann","year":"2015"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946684"},{"key":"e_1_3_2_1_18_1","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_1_19_1","first-page":"265","article-title":"Online matching and ad allocation","volume":"8","author":"Aranyak Mehta","year":"2013","journal-title":"Foundations and Trends in Theoretical Computer Science"},{"key":"e_1_3_2_1_20_1","volume-title":"2015. Human-level control through deep reinforcement learning. Nature 518, 7540","author":"Mnih Volodymyr","year":"2015"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5569-5"},{"key":"e_1_3_2_1_22_1","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).  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_1_23_1","volume-title":"1998. Reinforcement learning: An intro-duction","author":"Sutton Richard S"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of CIKM. ACM, 1587--1594","author":"Tang Liang","year":"2013"},{"key":"e_1_3_2_1_25_1","volume-title":"Reward Constrained Policy Optimization. arXiv preprint arXiv","author":"Tessler Chen","year":"1805"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of CIKM. ACM, 1443--1451","author":"Wu Di","year":"2018"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of NIPS. 433--441","author":"Wu Huasen","year":"2015"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of SIGKDD. ACM, 1077--1086","author":"Zhang Weinan","year":"2014"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of SIGKDD(2018)","author":"Zhao Jun","year":"2018"}],"event":{"name":"CIKM '19: The 28th ACM International Conference on Information and Knowledge Management","location":"Beijing China","acronym":"CIKM '19","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 28th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3357384.3357806","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3357384.3357806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:44:43Z","timestamp":1750203883000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3357384.3357806"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,3]]},"references-count":29,"alternative-id":["10.1145\/3357384.3357806","10.1145\/3357384"],"URL":"https:\/\/doi.org\/10.1145\/3357384.3357806","relation":{},"subject":[],"published":{"date-parts":[[2019,11,3]]},"assertion":[{"value":"2019-11-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}