{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:31:16Z","timestamp":1759883476811,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T00:00:00Z","timestamp":1746662400000},"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":[[2025,5,8]]},"DOI":"10.1145\/3701716.3715512","type":"proceedings-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T16:06:11Z","timestamp":1748016371000},"page":"1104-1108","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EBaReT: Expert-guided Bag Reward Transformer for Auto Bidding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4702-9754","authenticated-orcid":false,"given":"Kaiyuan","family":"Li","sequence":"first","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3740-3631","authenticated-orcid":false,"given":"Pengyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8943-7725","authenticated-orcid":false,"given":"Yunshan","family":"Peng","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3488-6151","authenticated-orcid":false,"given":"Pengjia","family":"Yuan","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3749-4019","authenticated-orcid":false,"given":"Yanxiang","family":"Zeng","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9711-9437","authenticated-orcid":false,"given":"Rui","family":"Xiang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8926-8605","authenticated-orcid":false,"given":"Yanhua","family":"Cheng","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7253-0674","authenticated-orcid":false,"given":"Xialong","family":"Liu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9266-0780","authenticated-orcid":false,"given":"Peng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3699824.3699838"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"e_1_3_2_1_3_1","unstructured":"Santiago R. Balseiro Yuan Deng Jieming Mao Vahab S. Mirrokni and Song Zuo. 2021. Robust Auction Design in the Auto-bidding World. In NeurIPS."},{"key":"e_1_3_2_1_4_1","volume-title":"Decision Transformer: Reinforcement Learning via Sequence Modeling. In NeurIPS.","author":"Chen Lili","year":"2021","unstructured":"Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, and Igor Mordatch. 2021. Decision Transformer: Reinforcement Learning via Sequence Modeling. In NeurIPS."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Jiayan Guo Yusen Huo Zhilin Zhang Tianyu Wang Chuan Yu Jian Xu Bo Zheng and Yan Zhang. 2024. Generative Auto-bidding via Conditional Diffusion Modeling. In KDD. ACM 5038--5049.","DOI":"10.1145\/3637528.3671526"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Yue He Xiujun Chen Di Wu Junwei Pan Qing Tan Chuan Yu Jian Xu and Xiaoqiang Zhu. 2021. A Unified Solution to Constrained Bidding in Online Display Advertising. In KDD. 2993--3001.","DOI":"10.1145\/3447548.3467199"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3606274.3606281"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Junqi Jin Chengru Song Han Li Kun Gai Jun Wang and Weinan Zhang. 2018. Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising. In CIKM. 2193--2201.","DOI":"10.1145\/3269206.3272021"},{"key":"e_1_3_2_1_9_1","volume-title":"Marthinus Christoffel du Plessis, and Masashi Sugiyama","author":"Kiryo Ryuichi","year":"2017","unstructured":"Ryuichi Kiryo, Gang Niu, Marthinus Christoffel du Plessis, and Masashi Sugiyama. 2017. Positive-Unlabeled Learning with Non-Negative Risk Estimator. In NeurIPS, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 1675--1685."},{"key":"e_1_3_2_1_10_1","unstructured":"Ilya Kostrikov Ashvin Nair and Sergey Levine. 2022. Offline Reinforcement Learning with Implicit Q-Learning. In ICLR."},{"key":"e_1_3_2_1_11_1","volume-title":"Xue Bin Peng, and Sergey Levine","author":"Kumar Aviral","year":"2019","unstructured":"Aviral Kumar, Xue Bin Peng, and Sergey Levine. 2019. Reward-Conditioned Policies. arxiv: 1912.13465 [cs.LG] https:\/\/arxiv.org\/abs\/1912.13465"},{"key":"e_1_3_2_1_12_1","unstructured":"Aviral Kumar Aurick Zhou George Tucker and Sergey Levine. 2020. Conservative Q-Learning for Offline Reinforcement Learning. In NeurIPS."},{"key":"e_1_3_2_1_13_1","unstructured":"Kuang-Huei Lee Ofir Nachum Mengjiao Yang Lisa Lee Daniel Freeman Sergio Guadarrama Ian Fischer Winnie Xu Eric Jang Henryk Michalewski and Igor Mordatch. 2022. Multi-Game Decision Transformers. In NeurIPS."},{"key":"e_1_3_2_1_14_1","unstructured":"Zhiyu Mou Yusen Huo Rongquan Bai Mingzhou Xie Chuan Yu Jian Xu and Bo Zheng. 2022. Sustainable Online Reinforcement Learning for Auto-bidding. In NeurIPS."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Weitong Ou Bo Chen Yingxuan Yang Xinyi Dai Weiwen Liu Weinan Zhang Ruiming Tang and Yong Yu. 2023. Deep Landscape Forecasting in Multi-Slot Real-Time Bidding. In KDD. 4685--4695.","DOI":"10.1145\/3580305.3599799"},{"key":"e_1_3_2_1_16_1","unstructured":"Kefan Su Yusen Huo Zhilin Zhang Shuai Dou Chuan Yu Jian Xu Zongqing Lu and Bo Zheng. 2024. AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games. In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track. https:\/\/arxiv.org\/abs\/2412.10798"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Faraz Torabi Garrett Warnell and Peter Stone. 2018. Behavioral Cloning from Observation. In IJCAI J\u00e9r\u00f4me Lang (Ed.). 4950--4957.","DOI":"10.24963\/ijcai.2018\/687"},{"key":"e_1_3_2_1_18_1","unstructured":"Kerong Wang Hanye Zhao Xufang Luo Kan Ren Weinan Zhang and Dongsheng Li. 2022. Bootstrapped Transformer for Offline Reinforcement Learning. In NeurIPS."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Haoqi Zhang Lvyin Niu Zhenzhe Zheng Zhilin Zhang Shan Gu Fan Wu Chuan Yu Jian Xu Guihai Chen and Bo Zheng. 2023. A Personalized Automated Bidding Framework for Fairness-aware Online Advertising. In KDD. 5544--5553.","DOI":"10.1145\/3580305.3599765"}],"event":{"name":"WWW '25: The ACM Web Conference 2025","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Sydney NSW Australia","acronym":"WWW '25"},"container-title":["Companion Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701716.3715512","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3701716.3715512","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T17:48:51Z","timestamp":1759859331000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701716.3715512"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,8]]},"references-count":19,"alternative-id":["10.1145\/3701716.3715512","10.1145\/3701716"],"URL":"https:\/\/doi.org\/10.1145\/3701716.3715512","relation":{},"subject":[],"published":{"date-parts":[[2025,5,8]]},"assertion":[{"value":"2025-05-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}