{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:28:27Z","timestamp":1783736907310,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T00:00:00Z","timestamp":1665964800000},"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":[[2022,10,17]]},"DOI":"10.1145\/3511808.3557611","type":"proceedings-article","created":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T01:29:57Z","timestamp":1665883797000},"page":"4560-4564","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Hybrid Transfer in Deep Reinforcement Learning for Ads Allocation"],"prefix":"10.1145","author":[{"given":"Ze","family":"Wang","sequence":"first","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guogang","family":"Liao","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowen","family":"Shi","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxu","family":"Wu","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingqi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongkang","family":"Wang","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingxing","family":"Wang","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,17]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467089"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186165"},{"key":"e_1_3_2_2_4_1","first-page":"1605","article-title":"An Empirical Analysis of Search Engine Advertising","volume":"55","author":"Ghose A.","year":"2009","unstructured":"A. Ghose and Sha Yang . 2009 . An Empirical Analysis of Search Engine Advertising : Sponsored Search in Electronic Markets. Manag. Sci. , Vol. 55 (2009), 1605 -- 1622 . A. Ghose and Sha Yang. 2009. An Empirical Analysis of Search Engine Advertising: Sponsored Search in Electronic Markets. Manag. Sci., Vol. 55 (2009), 1605--1622.","journal-title":"Sponsored Search in Electronic Markets. Manag. Sci."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3113501"},{"key":"e_1_3_2_2_6_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411952"},{"key":"e_1_3_2_2_8_1","volume-title":"Cross DQN: Cross Deep Q Network for Ads Allocation in Feed. arXiv preprint arXiv:2109.04353","author":"Liao Guogang","year":"2021","unstructured":"Guogang Liao , Ze Wang , Xiaoxu Wu , Xiaowen Shi , Chuheng Zhang , Yongkang Wang , Xingxing Wang , and Dong Wang . 2021. Cross DQN: Cross Deep Q Network for Ads Allocation in Feed. arXiv preprint arXiv:2109.04353 ( 2021 ). Guogang Liao, Ze Wang, Xiaoxu Wu, Xiaowen Shi, Chuheng Zhang, Yongkang Wang, Xingxing Wang, and Dong Wang. 2021. Cross DQN: Cross Deep Q Network for Ads Allocation in Feed. arXiv preprint arXiv:2109.04353 (2021)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Yong Liu Yujing Hu Yang Gao Yingfeng Chen and Changjie Fan. 2019. Value Function Transfer for Deep Multi-Agent Reinforcement Learning Based on N-Step Returns. In IJCAI. 457--463.  Yong Liu Yujing Hu Yang Gao Yingfeng Chen and Changjie Fan. 2019. Value Function Transfer for Deep Multi-Agent Reinforcement Learning Based on N-Step Returns. In IJCAI. 457--463.","DOI":"10.24963\/ijcai.2019\/65"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1561\/0400000057"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0016-0032(96)00063-4"},{"key":"e_1_3_2_2_12_1","volume-title":"Summer school on machine learning","author":"Rasmussen Carl Edward","unstructured":"Carl Edward Rasmussen . 2003. Gaussian processes in machine learning . In Summer school on machine learning . Springer , 63--71. Carl Edward Rasmussen. 2003. Gaussian processes in machine learning. In Summer school on machine learning. Springer, 63--71."},{"key":"e_1_3_2_2_13_1","volume-title":"Doubly stochastic variational inference for deep Gaussian processes. Advances in neural information processing systems","author":"Salimbeni Hugh","year":"2017","unstructured":"Hugh Salimbeni and Marc Deisenroth . 2017. Doubly stochastic variational inference for deep Gaussian processes. Advances in neural information processing systems , Vol. 30 ( 2017 ). Hugh Salimbeni and Marc Deisenroth. 2017. Doubly stochastic variational inference for deep Gaussian processes. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_14_1","unstructured":"Richard S Sutton Andrew G Barto etal 1998. Introduction to reinforcement learning. Vol. 135. MIT press Cambridge.  Richard S Sutton Andrew G Barto et al. 1998. Introduction to reinforcement learning. Vol. 135. MIT press Cambridge."},{"key":"e_1_3_2_2_15_1","volume-title":"REPAINT: Knowledge Transfer in Deep Reinforcement Learning. In International Conference on Machine Learning. PMLR, 10141--10152","author":"Tao Yunzhe","year":"2021","unstructured":"Yunzhe Tao , Sahika Genc , Jonathan Chung , Tao Sun , and Sunil Mallya . 2021 . REPAINT: Knowledge Transfer in Deep Reinforcement Learning. In International Conference on Machine Learning. PMLR, 10141--10152 . Yunzhe Tao, Sahika Genc, Jonathan Chung, Tao Sun, and Sunil Mallya. 2021. REPAINT: Knowledge Transfer in Deep Reinforcement Learning. In International Conference on Machine Learning. PMLR, 10141--10152."},{"key":"e_1_3_2_2_16_1","volume-title":"International Conference on Machine Learning. PMLR, 4936--4945","author":"Tirinzoni Andrea","year":"2018","unstructured":"Andrea Tirinzoni , Andrea Sessa , Matteo Pirotta , and Marcello Restelli . 2018 . Importance weighted transfer of samples in reinforcement learning . In International Conference on Machine Learning. PMLR, 4936--4945 . Andrea Tirinzoni, Andrea Sessa, Matteo Pirotta, and Marcello Restelli. 2018. Importance weighted transfer of samples in reinforcement learning. In International Conference on Machine Learning. PMLR, 4936--4945."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"B. Wang Zhaonan Li Jie Tang Kuo Zhang Songcan Chen and Liyun Ru. 2011. Learning to Advertise: How Many Ads Are Enough?. In PAKDD.  B. Wang Zhaonan Li Jie Tang Kuo Zhang Songcan Chen and Liyun Ru. 2011. Learning to Advertise: How Many Ads Are Enough?. In PAKDD.","DOI":"10.1007\/978-3-642-20847-8_42"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16580"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403391"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3191584"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16156"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403384"},{"key":"e_1_3_2_2_23_1","volume-title":"Transfer learning in deep reinforcement learning: A survey. arXiv preprint arXiv:2009.07888","author":"Zhu Zhuangdi","year":"2020","unstructured":"Zhuangdi Zhu , Kaixiang Lin , and Jiayu Zhou . 2020. Transfer learning in deep reinforcement learning: A survey. arXiv preprint arXiv:2009.07888 ( 2020 ). Zhuangdi Zhu, Kaixiang Lin, and Jiayu Zhou. 2020. Transfer learning in deep reinforcement learning: A survey. arXiv preprint arXiv:2009.07888 (2020)."}],"event":{"name":"CIKM '22: The 31st ACM International Conference on Information and Knowledge Management","location":"Atlanta GA USA","acronym":"CIKM '22","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 31st ACM International Conference on Information & Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3511808.3557611","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3511808.3557611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:09Z","timestamp":1750182669000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3511808.3557611"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,17]]},"references-count":23,"alternative-id":["10.1145\/3511808.3557611","10.1145\/3511808"],"URL":"https:\/\/doi.org\/10.1145\/3511808.3557611","relation":{},"subject":[],"published":{"date-parts":[[2022,10,17]]},"assertion":[{"value":"2022-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}