{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T04:57:31Z","timestamp":1783573051352,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T00:00:00Z","timestamp":1677456000000},"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":[[2023,2,27]]},"DOI":"10.1145\/3539597.3570486","type":"proceedings-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T23:27:00Z","timestamp":1677108420000},"page":"186-194","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1503-6519","authenticated-orcid":false,"given":"Tianchi","family":"Cai","sequence":"first","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1083-2834","authenticated-orcid":false,"given":"Jiyan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3796-161X","authenticated-orcid":false,"given":"Wenpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0666-0769","authenticated-orcid":false,"given":"Shiji","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4580-1683","authenticated-orcid":false,"given":"Xierui","family":"Song","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3045-2775","authenticated-orcid":false,"given":"Li","family":"Yu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0706-3448","authenticated-orcid":false,"given":"Lihong","family":"Gu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7638-5443","authenticated-orcid":false,"given":"Xiaodong","family":"Zeng","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7596-4945","authenticated-orcid":false,"given":"Jinjie","family":"Gu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7091-2318","authenticated-orcid":false,"given":"Guannan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,2,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"e_1_3_2_2_2_1","volume-title":"Proceedings of the 24th Annual Conference on Learning Theory. 27--46","author":"Abernethy Jacob","year":"2011","unstructured":"Jacob Abernethy, Peter L Bartlett, and Elad Hazan. 2011. Blackwell approachability and no-regret learning are equivalent. In Proceedings of the 24th Annual Conference on Learning Theory. 27--46."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305384"},{"key":"e_1_3_2_2_4_1","volume-title":"Reinforcement learning based recommender systems: A survey. ACM Computing Surveys (CSUR)","author":"Afsar M Mehdi","year":"2021","unstructured":"M Mehdi Afsar, Trafford Crump, and Behrouz Far. 2021. Reinforcement learning based recommender systems: A survey. ACM Computing Surveys (CSUR) (2021)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623366"},{"key":"e_1_3_2_2_6_1","volume-title":"Constrained Markov decision processes","author":"Altman Eitan","unstructured":"Eitan Altman. 1999. Constrained Markov decision processes. Vol. 7. CRC Press."},{"key":"e_1_3_2_2_7_1","volume-title":"Value constrained model-free continuous control. arXiv preprint arXiv:1902.04623","author":"Bohez Steven","year":"2019","unstructured":"Steven Bohez, Abbas Abdolmaleki, Michael Neunert, Jonas Buchli, Nicolas Heess, and Raia Hadsell. 2019. Value constrained model-free continuous control. arXiv preprint arXiv:1902.04623 (2019)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482052"},{"key":"e_1_3_2_2_9_1","volume-title":"A survey of deep reinforcement learning in recommender systems: A systematic review and future directions. arXiv preprint arXiv:2109.03540","author":"Chen Xiaocong","year":"2021","unstructured":"Xiaocong Chen, Lina Yao, Julian McAuley, Guanglin Zhou, and Xianzhi Wang. 2021c. A survey of deep reinforcement learning in recommender systems: A systematic review and future directions. arXiv preprint arXiv:2109.03540 (2021)."},{"key":"e_1_3_2_2_10_1","volume-title":"A primal-dual approach to constrained Markov decision processes. arXiv preprint arXiv:2101.10895","author":"Chen Yi","year":"2021","unstructured":"Yi Chen, Jing Dong, and Zhaoran Wang. 2021a. A primal-dual approach to constrained Markov decision processes. arXiv preprint arXiv:2101.10895 (2021)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3242024"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1006\/game.1999.0738"},{"key":"e_1_3_2_2_13_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Fujimoto Scott","year":"2019","unstructured":"Scott Fujimoto, David Meger, and Doina Precup. 2019. Off-policy deep reinforcement learning without exploration. In International Conference on Machine Learning. PMLR, 2052--2062."},{"key":"e_1_3_2_2_14_1","volume-title":"Herke Van Hoof, and David Meger","author":"Fujimoto Scott","year":"2018","unstructured":"Scott Fujimoto, Herke Van Hoof, and David Meger. 2018. Addressing function approximation error in actor-critic methods. arXiv preprint arXiv:1802.09477 (2018)."},{"key":"e_1_3_2_2_15_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017)."},{"key":"e_1_3_2_2_16_1","volume-title":"International Conference on Machine Learning. PMLR, 2681--2691","author":"Hazan Elad","year":"2019","unstructured":"Elad Hazan, Sham Kakade, Karan Singh, and Abby Van Soest. 2019. Provably efficient maximum entropy exploration. In International Conference on Machine Learning. PMLR, 2681--2691."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.513.0421"},{"key":"e_1_3_2_2_18_1","volume-title":"International Conference on Machine Learning. 3703--3712","author":"Le Hoang","year":"2019","unstructured":"Hoang Le, Cameron Voloshin, and Yisong Yue. 2019. Batch Policy Learning under Constraints. In International Conference on Machine Learning. 3703--3712."},{"key":"e_1_3_2_2_19_1","volume-title":"Large-Scale Data-Driven Airline Market Influence Maximization. arXiv preprint arXiv:2105.15012","author":"Li Duanshun","year":"2021","unstructured":"Duanshun Li, Jing Liu, Jinsung Jeon, Seoyoung Hong, Thai Le, Dongwon Lee, and Noseong Park. 2021. Large-Scale Data-Driven Airline Market Influence Maximization. arXiv preprint arXiv:2105.15012 (2021)."},{"key":"e_1_3_2_2_20_1","volume-title":"Accelerated primal-dual policy optimization for safe reinforcement learning. arXiv preprint arXiv:1802.06480","author":"Liang Qingkai","year":"2018","unstructured":"Qingkai Liang, Fanyu Que, and Eytan Modiano. 2018. Accelerated primal-dual policy optimization for safe reinforcement learning. arXiv preprint arXiv:1802.06480 (2018)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371858"},{"key":"e_1_3_2_2_22_1","volume-title":"Deep reinforcement learning based recommendation with explicit user-item interactions modeling. arXiv preprint arXiv:1810.12027","author":"Liu Feng","year":"2018","unstructured":"Feng Liu, Ruiming Tang, Xutao Li, Weinan Zhang, Yunming Ye, Haokun Chen, Huifeng Guo, and Yuzhou Zhang. 2018. Deep reinforcement learning based recommendation with explicit user-item interactions modeling. arXiv preprint arXiv:1810.12027 (2018)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357835"},{"key":"e_1_3_2_2_24_1","volume-title":"Miro Dudik, and Robert E Schapire.","author":"Miryoosefi Sobhan","year":"2019","unstructured":"Sobhan Miryoosefi, Kiant\u00e9 Brantley, Hal Daume III, Miro Dudik, and Robert E Schapire. 2019. Reinforcement learning with convex constraints. In Advances in Neural Information Processing Systems. 14093--14102."},{"key":"e_1_3_2_2_25_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_2_26_1","unstructured":"Santiago Paternain Luiz Chamon Miguel Calvo-Fullana and Alejandro Ribeiro. 2019. Constrained reinforcement learning has zero duality gap. In Advances in Neural Information Processing Systems. 7555--7565."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Shai Shalev-Shwartz et al. 2011. Online learning and online convex optimization. Foundations and trends in Machine Learning Vol. 4 2 (2011) 107--194.","DOI":"10.1561\/2200000018"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"e_1_3_2_2_29_1","volume-title":"International Conference on Machine Learning. PMLR, 9133--9143","author":"Stooke Adam","year":"2020","unstructured":"Adam Stooke, Joshua Achiam, and Pieter Abbeel. 2020. Responsive safety in reinforcement learning by pid lagrangian methods. In International Conference on Machine Learning. PMLR, 9133--9143."},{"key":"e_1_3_2_2_30_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."},{"key":"e_1_3_2_2_31_1","volume-title":"Reward Constrained Policy Optimization. In International Conference on Learning Representations.","author":"Tessler Chen","year":"2018","unstructured":"Chen Tessler, Daniel J Mankowitz, and Shie Mannor. 2018. Reward Constrained Policy Optimization. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_32_1","volume-title":"Deep reinforcement learning with double q-learning. arXiv preprint arXiv:1509.06461","author":"Hasselt Hado Van","year":"2015","unstructured":"Hado Van Hasselt, Arthur Guez, and David Silver. 2015. Deep reinforcement learning with double q-learning. arXiv preprint arXiv:1509.06461 (2015)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271748"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358031"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788615"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i17.17760"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6150"},{"key":"e_1_3_2_2_38_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Zahavy Tom","year":"2021","unstructured":"Tom Zahavy, Brendan O'Donoghue, Guillaume Desjardins, and Satinder Singh. 2021. Reward is enough for convex MDPs. Advances in Neural Information Processing Systems, Vol. 34 (2021)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330700"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788565"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_2_2_42_1","volume-title":"Proceedings of the 20th international conference on machine learning (icml-03)","author":"Zinkevich Martin","year":"2003","unstructured":"Martin Zinkevich. 2003. Online convex programming and generalized infinitesimal gradient ascent. In Proceedings of the 20th international conference on machine learning (icml-03). 928--936."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371801"}],"event":{"name":"WSDM '23: The Sixteenth ACM International Conference on Web Search and Data Mining","location":"Singapore Singapore","acronym":"WSDM '23","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539597.3570486","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539597.3570486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:15Z","timestamp":1750186935000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539597.3570486"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,27]]},"references-count":43,"alternative-id":["10.1145\/3539597.3570486","10.1145\/3539597"],"URL":"https:\/\/doi.org\/10.1145\/3539597.3570486","relation":{},"subject":[],"published":{"date-parts":[[2023,2,27]]},"assertion":[{"value":"2023-02-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}