{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:19:11Z","timestamp":1759335551594,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T00:00:00Z","timestamp":1691107200000},"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":[[2023,8,6]]},"DOI":"10.1145\/3580305.3599254","type":"proceedings-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T18:10:58Z","timestamp":1691172658000},"page":"2314-2325","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Adversarial Constrained Bidding via Minimax Regret Optimization with Causality-Aware Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9299-6305","authenticated-orcid":false,"given":"Haozhe","family":"Wang","sequence":"first","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1244-6336","authenticated-orcid":false,"given":"Chao","family":"Du","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6552-787X","authenticated-orcid":false,"given":"Panyan","family":"Fang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4729-0415","authenticated-orcid":false,"given":"LI","family":"He","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5112-7763","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5430-3890","authenticated-orcid":false,"given":"Bo","family":"Zheng","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2023,8,4]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Banach wasserstein gan. Advances in neural information processing systems 31","author":"Adler Jonas","year":"2018","unstructured":"Jonas Adler and Sebastian Lunz . 2018. Banach wasserstein gan. Advances in neural information processing systems 31 ( 2018 ). Jonas Adler and Sebastian Lunz. 2018. Banach wasserstein gan. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_2_2_1","volume-title":"Deep variational information bottleneck. arXiv preprint arXiv:1612.00410","author":"Alemi Alexander A","year":"2016","unstructured":"Alexander A Alemi , Ian Fischer , Joshua V Dillon , and Kevin Murphy . 2016. Deep variational information bottleneck. arXiv preprint arXiv:1612.00410 ( 2016 ). Alexander A Alemi, Ian Fischer, Joshua V Dillon, and Kevin Murphy. 2016. Deep variational information bottleneck. arXiv preprint arXiv:1612.00410 (2016)."},{"key":"e_1_3_2_2_3_1","unstructured":"Alimama 2022. Alimama. Retrieved 2022 from https:\/\/www.alimama.com\/  Alimama 2022. Alimama. Retrieved 2022 from https:\/\/www.alimama.com\/"},{"key":"e_1_3_2_2_4_1","volume-title":"International Conference on Machine Learning. PMLR, 354--363","author":"Balduzzi David","year":"2018","unstructured":"David Balduzzi , Sebastien Racaniere , James Martens , Jakob Foerster , Karl Tuyls , and Thore Graepel . 2018 . The mechanics of n-player differentiable games . In International Conference on Machine Learning. PMLR, 354--363 . David Balduzzi, Sebastien Racaniere, James Martens, Jakob Foerster, Karl Tuyls, and Thore Graepel. 2018. The mechanics of n-player differentiable games. In International Conference on Machine Learning. PMLR, 354--363."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"S. Balseiro A. Kim M. Mahdian and V. Mirrokni. 2021. Budget-Management Strategies in Repeated Auctions. Operations Research 69 3 (2021).  S. Balseiro A. Kim M. Mahdian and V. Mirrokni. 2021. Budget-Management Strategies in Repeated Auctions. Operations Research 69 3 (2021).","DOI":"10.1287\/opre.2020.2073"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2014.2022"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2018.3174"},{"volume-title":"Pattern recognition and machine learning","author":"Bishop Christopher M","key":"e_1_3_2_2_8_1","unstructured":"Christopher M Bishop and Nasser M Nasrabadi . 2006. Pattern recognition and machine learning . Vol. 4 . Springer . Christopher M Bishop and Nasser M Nasrabadi. 2006. Pattern recognition and machine learning. Vol. 4. Springer."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2004.05.012"},{"volume-title":"Convex optimization","author":"Boyd Stephen","key":"e_1_3_2_2_10_1","unstructured":"Stephen Boyd , Stephen P Boyd , and Lieven Vandenberghe . 2004. Convex optimization . Cambridge university press . Stephen Boyd, Stephen P Boyd, and Lieven Vandenberghe. 2004. Convex optimization. Cambridge university press."},{"key":"e_1_3_2_2_11_1","volume-title":"Multi-scale online learning and its applications to online auctions. arXiv preprint arXiv:1705.09700","author":"Bubeck S\u00e9bastien","year":"2017","unstructured":"S\u00e9bastien Bubeck , Nikhil R Devanur , Zhiyi Huang , and Rad Niazadeh . 2017. Multi-scale online learning and its applications to online auctions. arXiv preprint arXiv:1705.09700 ( 2017 ). S\u00e9bastien Bubeck, Nikhil R Devanur, Zhiyi Huang, and Rad Niazadeh. 2017. Multi-scale online learning and its applications to online auctions. arXiv preprint arXiv:1705.09700 (2017)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018702"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1120.0548"},{"key":"e_1_3_2_2_14_1","volume-title":"International Conference on Machine Learning. PMLR, 2678--2689","author":"Drutsa Alexey","year":"2020","unstructured":"Alexey Drutsa . 2020 . Reserve pricing in repeated second-price auctions with strategic bidders . In International Conference on Machine Learning. PMLR, 2678--2689 . Alexey Drutsa. 2020. Reserve pricing in repeated second-price auctions with strategic bidders. In International Conference on Machine Learning. PMLR, 2678--2689."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467089"},{"key":"e_1_3_2_2_16_1","volume-title":"International Conference on Machine Learning. PMLR, 1706--1715","author":"D\u00fctting Paul","year":"2019","unstructured":"Paul D\u00fctting , Zhe Feng , Harikrishna Narasimhan , David Parkes , and Sai Srivatsa Ravindranath . 2019 . Optimal auctions through deep learning . In International Conference on Machine Learning. PMLR, 1706--1715 . Paul D\u00fctting, Zhe Feng, Harikrishna Narasimhan, David Parkes, and Sai Srivatsa Ravindranath. 2019. Optimal auctions through deep learning. In International Conference on Machine Learning. PMLR, 1706--1715."},{"key":"e_1_3_2_2_17_1","volume-title":"Internet advertising and the generalized second-price auction: Selling billions of dollars worth of keywords. American economic review 97, 1","author":"Edelman Benjamin","year":"2007","unstructured":"Benjamin Edelman , Michael Ostrovsky , and Michael Schwarz . 2007. Internet advertising and the generalized second-price auction: Selling billions of dollars worth of keywords. American economic review 97, 1 ( 2007 ), 242--259. Benjamin Edelman, Michael Ostrovsky, and Michael Schwarz. 2007. Internet advertising and the generalized second-price auction: Selling billions of dollars worth of keywords. American economic review 97, 1 (2007), 242--259."},{"key":"e_1_3_2_2_18_1","volume-title":"International Conference on Machine Learning. PMLR, 3230--3239","author":"Feng Zhe","year":"2021","unstructured":"Zhe Feng , S\u00e9bastien Lahaie , Jon Schneider , and Jinchao Ye . 2021 . Reserve price optimization for first price auctions in display advertising . In International Conference on Machine Learning. PMLR, 3230--3239 . Zhe Feng, S\u00e9bastien Lahaie, Jon Schneider, and Jinchao Ye. 2021. Reserve price optimization for first price auctions in display advertising. In International Conference on Machine Learning. PMLR, 3230--3239."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219166.3219208"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1080\/02522667.2017.1303946"},{"key":"e_1_3_2_2_21_1","volume-title":"Optimal real-time bidding strategies. Applied mathematics research express","author":"Fernandez-Tapia Joaquin","year":"2017","unstructured":"Joaquin Fernandez-Tapia , Olivier Gu\u00e9ant , and Jean-Michel Lasry . 2017. Optimal real-time bidding strategies. Applied mathematics research express 2017 , 1 (2017), 142--183. Joaquin Fernandez-Tapia, Olivier Gu\u00e9ant, and Jean-Michel Lasry. 2017. Optimal real-time bidding strategies. Applied mathematics research express 2017, 1 (2017), 142--183."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_2_23_1","unstructured":"Google 2022. Google. Retrieved 2022 from https:\/\/ads.google.com\/  Google 2022. Google. Retrieved 2022 from https:\/\/ads.google.com\/"},{"key":"e_1_3_2_2_24_1","volume-title":"Optimal bidding strategies and equilibria in dynamic auctions with budget constraints. Available at SSRN 2066175","author":"Gummadi Ramki","year":"2013","unstructured":"Ramki Gummadi , Peter Key , and Alexandre Proutiere . 2013. Optimal bidding strategies and equilibria in dynamic auctions with budget constraints. Available at SSRN 2066175 ( 2013 ). Ramki Gummadi, Peter Key, and Alexandre Proutiere. 2013. Optimal bidding strategies and equilibria in dynamic auctions with budget constraints. Available at SSRN 2066175 (2013)."},{"key":"e_1_3_2_2_25_1","unstructured":"Tuomas Haarnoja Aurick Zhou Kristian Hartikainen George Tucker Sehoon Ha Jie Tan Vikash Kumar Henry Zhu Abhishek Gupta Pieter Abbeel etal 2018. Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018).  Tuomas Haarnoja Aurick Zhou Kristian Hartikainen George Tucker Sehoon Ha Jie Tan Vikash Kumar Henry Zhu Abhishek Gupta Pieter Abbeel et al. 2018. Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018)."},{"key":"e_1_3_2_2_26_1","volume-title":"Learning to bid optimally and efficiently in adversarial first-price auctions. arXiv preprint arXiv:2007.04568","author":"Han Yanjun","year":"2020","unstructured":"Yanjun Han , Zhengyuan Zhou , Aaron Flores , Erik Ordentlich , and Tsachy Weissman . 2020. Learning to bid optimally and efficiently in adversarial first-price auctions. arXiv preprint arXiv:2007.04568 ( 2020 ). Yanjun Han, Zhengyuan Zhou, Aaron Flores, Erik Ordentlich, and Tsachy Weissman. 2020. Learning to bid optimally and efficiently in adversarial first-price auctions. arXiv preprint arXiv:2007.04568 (2020)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467199"},{"key":"e_1_3_2_2_28_1","volume-title":"Kullback-Leibler divergence constrained distributionally robust optimization. Available at Optimization Online","author":"Hu Zhaolin","year":"2013","unstructured":"Zhaolin Hu and L Jeff Hong . 2013. Kullback-Leibler divergence constrained distributionally robust optimization. Available at Optimization Online ( 2013 ), 1695--1724. Zhaolin Hu and L Jeff Hong. 2013. Kullback-Leibler divergence constrained distributionally robust optimization. Available at Optimization Online (2013), 1695--1724."},{"key":"e_1_3_2_2_29_1","volume-title":"A Review. Entropy 22 (12","author":"Jamin Antoine","year":"2019","unstructured":"Antoine Jamin and Anne Humeau-Heurtier . 2019. (Multiscale) Cross-Entropy Methods : A Review. Entropy 22 (12 2019 ). https:\/\/doi.org\/10.3390\/e22010045 10.3390\/e22010045 Antoine Jamin and Anne Humeau-Heurtier. 2019. (Multiscale) Cross-Entropy Methods: A Review. Entropy 22 (12 2019). https:\/\/doi.org\/10.3390\/e22010045"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Olivier Jeunen Sean Murphy and Ben Allison. 2022. Learning to bid with AuctionGym. (2022).  Olivier Jeunen Sean Murphy and Ben Allison. 2022. Learning to bid with AuctionGym. (2022).","DOI":"10.1145\/3580305.3599877"},{"key":"e_1_3_2_2_31_1","volume-title":"Batch reinforcement learning. Reinforcement learning: State-of-the-art","author":"Lange Sascha","year":"2012","unstructured":"Sascha Lange , Thomas Gabel , and Martin Riedmiller . 2012. Batch reinforcement learning. Reinforcement learning: State-of-the-art ( 2012 ), 45--73. Sascha Lange, Thomas Gabel, and Martin Riedmiller. 2012. Batch reinforcement learning. Reinforcement learning: State-of-the-art (2012), 45--73."},{"key":"e_1_3_2_2_32_1","volume-title":"Optimal auction design. Mathematics of operations research 6, 1","author":"Myerson Roger B","year":"1981","unstructured":"Roger B Myerson . 1981. Optimal auction design. Mathematics of operations research 6, 1 ( 1981 ), 58--73. Roger B Myerson. 1981. Optimal auction design. Mathematics of operations research 6, 1 (1981), 58--73."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/3463952.3464064"},{"key":"e_1_3_2_2_34_1","volume-title":"Vianney Perchet, et al.","author":"Nedelec Thomas","year":"2022","unstructured":"Thomas Nedelec , Cl\u00e9ment Calauz\u00e8nes , Noureddine El Karoui , Vianney Perchet, et al. 2022 . Learning in repeated auctions. Foundations and Trends\u00ae in Machine Learning 15, 3 (2022), 176--334. Thomas Nedelec, Cl\u00e9ment Calauz\u00e8nes, Noureddine El Karoui, Vianney Perchet, et al. 2022. Learning in repeated auctions. Foundations and Trends\u00ae in Machine Learning 15, 3 (2022), 176--334."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1993574.1993585"},{"key":"e_1_3_2_2_36_1","volume-title":"Cambridge, UK: Cam-bridgeUniversityPress 19, 2","author":"Judea Pearl","year":"2000","unstructured":"Judea Pearl et al. 2000 . Models , reasoning and inference. Cambridge, UK: Cam-bridgeUniversityPress 19, 2 (2000). Judea Pearl et al. 2000. Models, reasoning and inference. Cambridge, UK: Cam-bridgeUniversityPress 19, 2 (2000)."},{"key":"e_1_3_2_2_37_1","volume-title":"Auction learning as a two-player game. arXiv preprint arXiv:2006.05684","author":"Rahme Jad","year":"2020","unstructured":"Jad Rahme , Samy Jelassi , and S Matthew Weinberg . 2020. Auction learning as a two-player game. arXiv preprint arXiv:2006.05684 ( 2020 ). Jad Rahme, Samy Jelassi, and S Matthew Weinberg. 2020. Auction learning as a two-player game. arXiv preprint arXiv:2006.05684 (2020)."},{"key":"e_1_3_2_2_38_1","volume-title":"Certifiable distributional robustness with principled adversarial training. arXiv preprint arXiv:1710.10571 2","author":"Sinha Aman","year":"2017","unstructured":"Aman Sinha , Hongseok Namkoong , and John Duchi . 2017. Certifiable distributional robustness with principled adversarial training. arXiv preprint arXiv:1710.10571 2 ( 2017 ). Aman Sinha, Hongseok Namkoong, and John Duchi. 2017. Certifiable distributional robustness with principled adversarial training. arXiv preprint arXiv:1710.10571 2 (2017)."},{"key":"e_1_3_2_2_39_1","volume-title":"Distributionally robust optimization and generalization in kernel methods. Advances in Neural Information Processing Systems 32","author":"Staib Matthew","year":"2019","unstructured":"Matthew Staib and Stefanie Jegelka . 2019. Distributionally robust optimization and generalization in kernel methods. Advances in Neural Information Processing Systems 32 ( 2019 ). Matthew Staib and Stefanie Jegelka. 2019. Distributionally robust optimization and generalization in kernel methods. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2020.2061"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539211"},{"key":"e_1_3_2_2_42_1","volume-title":"Learning context-aware task rea- soning for efficient meta-reinforcement learning. arXiv preprint arXiv:2003.01373","author":"Wang Haozhe","year":"2020","unstructured":"Haozhe Wang , Jiale Zhou , and Xuming He. 2020. Learning context-aware task rea- soning for efficient meta-reinforcement learning. arXiv preprint arXiv:2003.01373 ( 2020 ). Haozhe Wang, Jiale Zhou, and Xuming He. 2020. Learning context-aware task rea- soning for efficient meta-reinforcement learning. arXiv preprint arXiv:2003.01373 (2020)."},{"key":"e_1_3_2_2_43_1","volume-title":"Conference on Learning Theory. PMLR, 1562--1583","author":"Weed Jonathan","year":"2016","unstructured":"Jonathan Weed , Vianney Perchet , and Philippe Rigollet . 2016 . Online learning in repeated auctions . In Conference on Learning Theory. PMLR, 1562--1583 . Jonathan Weed, Vianney Perchet, and Philippe Rigollet. 2016. Online learning in repeated auctions. In Conference on Learning Theory. PMLR, 1562--1583."},{"key":"e_1_3_2_2_44_1","volume-title":"Mechanism design for value maximizers. arXiv preprint arXiv:1607.04362","author":"Wilkens Christopher A","year":"2016","unstructured":"Christopher A Wilkens , Ruggiero Cavallo , Rad Niazadeh , and Samuel Taggart . 2016. Mechanism design for value maximizers. arXiv preprint arXiv:1607.04362 ( 2016 ). Christopher A Wilkens, Ruggiero Cavallo, Rad Niazadeh, and Samuel Taggart. 2016. Mechanism design for value maximizers. arXiv preprint arXiv:1607.04362 (2016)."},{"key":"e_1_3_2_2_45_1","volume-title":"Deep reinforcement learning amidst lifelong non-stationarity. arXiv preprint arXiv:2006.10701","author":"Xie Annie","year":"2020","unstructured":"Annie Xie , James Harrison , and Chelsea Finn . 2020. Deep reinforcement learning amidst lifelong non-stationarity. arXiv preprint arXiv:2006.10701 ( 2020 ). Annie Xie, James Harrison, and Chelsea Finn. 2020. Deep reinforcement learning amidst lifelong non-stationarity. arXiv preprint arXiv:2006.10701 (2020)."},{"key":"e_1_3_2_2_46_1","first-page":"15737","article-title":"Error bounds of imitating policies and environments","volume":"33","author":"Xu Tian","year":"2020","unstructured":"Tian Xu , Ziniu Li , and Yang Yu . 2020 . Error bounds of imitating policies and environments . Advances in Neural Information Processing Systems 33 (2020), 15737 -- 15749 . Tian Xu, Ziniu Li, and Yang Yu. 2020. Error bounds of imitating policies and environments. Advances in Neural Information Processing Systems 33 (2020), 15737--15749.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330681"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.5555\/3546258.3546547"}],"event":{"name":"KDD '23: The 29th 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":"Long Beach CA USA","acronym":"KDD '23"},"container-title":["Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599254","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580305.3599254","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:15Z","timestamp":1750182675000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599254"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,4]]},"references-count":48,"alternative-id":["10.1145\/3580305.3599254","10.1145\/3580305"],"URL":"https:\/\/doi.org\/10.1145\/3580305.3599254","relation":{},"subject":[],"published":{"date-parts":[[2023,8,4]]},"assertion":[{"value":"2023-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}