{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T09:35:45Z","timestamp":1782293745861,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,7,19]],"date-time":"2018-07-19T00:00:00Z","timestamp":1531958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1714741 and IIS-1715940"],"award-info":[{"award-number":["IIS-1714741 and IIS-1715940"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,7,19]]},"DOI":"10.1145\/3219819.3219886","type":"proceedings-article","created":{"date-parts":[[2018,7,19]],"date-time":"2018-07-19T13:05:12Z","timestamp":1532005512000},"page":"1040-1048","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":305,"title":["Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning"],"prefix":"10.1145","author":[{"given":"Xiangyu","family":"Zhao","sequence":"first","affiliation":[{"name":"Michigan State University, East Lansing, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Zhang","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuoye","family":"Ding","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Xia","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiliang","family":"Tang","sequence":"additional","affiliation":[{"name":"Michigan State University, East Lansing, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dawei","family":"Yin","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Knowledge-based systems","author":"Akerkar Rajendra"},{"key":"e_1_3_2_1_2_1","volume-title":"Dynamic programming","author":"Bellman Richard"},{"key":"e_1_3_2_1_3_1","volume-title":"Empirical analysis of predictive algorithms for collaborative filtering Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence","author":"Breese John S"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1021240730564"},{"key":"e_1_3_2_1_5_1","volume-title":"Off-policy actor-critic. arXiv preprint arXiv:1205.4839","author":"Degris Thomas","year":"2012"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390334.1390392"},{"key":"e_1_3_2_1_7_1","unstructured":"Milos Hauskrecht. 1997. Incremental methods for computing bounds in partially observable Markov decision processes. In AAAI\/IAAI. 734--739.   Milos Hauskrecht. 1997. Incremental methods for computing bounds in partially observable Markov decision processes. In AAAI\/IAAI. 734--739."},{"key":"e_1_3_2_1_8_1","volume-title":"Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939","author":"Hidasi Bal\u00e1zs","year":"2015"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017932429737"},{"key":"e_1_3_2_1_11_1","unstructured":"Omer Levy and Yoav Goldberg. 2014. Neural word embedding as implicit matrix factorization Advances in neural information processing systems. 2177--2185.   Omer Levy and Yoav Goldberg. 2014. Neural word embedding as implicit matrix factorization Advances in neural information processing systems. 2177--2185."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2003.1167344"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1282100.1282114"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1557914.1557930"},{"key":"e_1_3_2_1_16_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/336597.336662"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022635613229"},{"key":"e_1_3_2_1_19_1","volume-title":"PEGASUS: A policy search method for large MDPs and POMDPs Proceedings of the Sixteenth conference on Uncertainty in artificial intelligence","author":"Ng Andrew Y","year":"2000"},{"key":"e_1_3_2_1_20_1","volume-title":"Personalized Deep Learning for Tag Recommendation. In Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 186--197","author":"Nguyen Hanh TH","year":"2017"},{"key":"e_1_3_2_1_21_1","unstructured":"Pascal Poupart and Craig Boutilier. 2005. VDCBPI: an approximate scalable algorithm for large POMDPs Advances in Neural Information Processing Systems. 1081--1088.   Pascal Poupart and Craig Boutilier. 2005. VDCBPI: an approximate scalable algorithm for large POMDPs Advances in Neural Information Processing Systems. 1081--1088."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/245108.245121"},{"key":"e_1_3_2_1_24_1","volume-title":"Recommender systems handbook","author":"Ricci Francesco"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/1046920.1088715"},{"key":"e_1_3_2_1_26_1","volume-title":"Deep Reinforcement Learning with Attention for Slate Markov Decision Processes with High-Dimensional States and Actions. arXiv preprint arXiv:1512.01124","author":"Sunehag Peter","year":"2015"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1363686.1363954"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1297231.1297250"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148176"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133025"},{"key":"e_1_3_2_1_31_1","volume-title":"2016 IEEE 32nd International Conference on. IEEE, 1218--1229","author":"Wu Sai","year":"2016"},{"key":"e_1_3_2_1_32_1","volume-title":"Deep Learning based Recommender System: A Survey and New Perspectives. arXiv preprint arXiv:1707.07435","author":"Zhang Shuai","year":"2017"},{"key":"e_1_3_2_1_33_1","volume-title":"Deep Reinforcement Learning for Page-wise Recommendations. arXiv preprint arXiv:1805.02343","author":"Zhao Xiangyu","year":"2018"},{"key":"e_1_3_2_1_34_1","volume-title":"Deep Reinforcement Learning for List-wise Recommendations. arXiv preprint arXiv:1801.00209","author":"Zhao Xiangyu","year":"2017"}],"event":{"name":"KDD '18: The 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","location":"London United Kingdom","acronym":"KDD '18","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3219819.3219886","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3219819.3219886","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3219819.3219886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:07:20Z","timestamp":1750212440000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3219819.3219886"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,19]]},"references-count":33,"alternative-id":["10.1145\/3219819.3219886","10.1145\/3219819"],"URL":"https:\/\/doi.org\/10.1145\/3219819.3219886","relation":{},"subject":[],"published":{"date-parts":[[2018,7,19]]},"assertion":[{"value":"2018-07-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}