{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:55:56Z","timestamp":1775325356051,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T00:00:00Z","timestamp":1635206400000},"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":[[2021,10,26]]},"DOI":"10.1145\/3459637.3482347","type":"proceedings-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T15:31:13Z","timestamp":1636990273000},"page":"201-210","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["Generative Inverse Deep Reinforcement Learning for Online Recommendation"],"prefix":"10.1145","author":[{"given":"Xiaocong","family":"Chen","sequence":"first","affiliation":[{"name":"University of New South Wales, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lina","family":"Yao","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aixin","family":"Sun","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiwei","family":"Xu","sequence":"additional","affiliation":[{"name":"Data 61, CSIRO, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liming","family":"Zhu","sequence":"additional","affiliation":[{"name":"Data 61, CSIRO, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455250"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040156"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013312"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220122"},{"key":"e_1_3_2_1_6_1","volume-title":"Knowledge-guided Deep Reinforcement Learning for Interactive Recommendation. arXiv preprint arXiv:2004.08068","author":"Chen Xiaocong","year":"2020"},{"key":"e_1_3_2_1_7_1","volume-title":"International Conference on Machine Learning. 1052--1061","author":"Chen Xinshi","year":"2019"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045397"},{"key":"e_1_3_2_1_9_1","unstructured":"Yang Gao Huazhe(Harry) Xu Ji Lin Fisher Yu Sergey Levine and Trevor Darrell. 2018. Reinforcement Learning from Imperfect Demonstrations. https:\/\/openreview.net\/forum?id=BJJ9bz-0-  Yang Gao Huazhe(Harry) Xu Ji Lin Fisher Yu Sergey Levine and Trevor Darrell. 2018. Reinforcement Learning from Imperfect Demonstrations. https:\/\/openreview.net\/forum?id=BJJ9bz-0-"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/1867406.1867520"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157608"},{"key":"e_1_3_2_1_13_1","volume-title":"Recsim: A configurable simulation platform for recommender systems. arXiv preprint arXiv:1909.04847","author":"Ie Eugene","year":"2019"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017932429737"},{"key":"e_1_3_2_1_15_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3009657.3009799"},{"key":"e_1_3_2_1_17_1","volume-title":"Debidatta Dwibedi, Sergey Levine, and Jonathan Tompson.","author":"Kostrikov Ilya","year":"2019"},{"key":"e_1_3_2_1_18_1","volume-title":"Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971","author":"Lillicrap Timothy P","year":"2015"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371858"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313616"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/2976040.2976176"},{"key":"e_1_3_2_1_22_1","volume-title":"Recogym: A reinforcement learning environment for the problem of product recommendation in online advertising. arXiv preprint arXiv:1808.00720","author":"Rohde David","year":"2018"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045319"},{"key":"e_1_3_2_1_24_1","volume-title":"High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438","author":"Schulman John","year":"2015"},{"key":"e_1_3_2_1_25_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330933"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401134"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401171"},{"key":"e_1_3_2_1_30_1","volume-title":"Deep reinforcement learning for list-wise recommendations. arXiv preprint arXiv:1801.00209","author":"Zhao Xiangyu","year":"2017"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371801"}],"event":{"name":"CIKM '21: The 30th ACM International Conference on Information and Knowledge Management","location":"Virtual Event Queensland Australia","acronym":"CIKM '21","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 30th ACM International Conference on Information & Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3482347","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3459637.3482347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:12:22Z","timestamp":1750191142000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3482347"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,26]]},"references-count":32,"alternative-id":["10.1145\/3459637.3482347","10.1145\/3459637"],"URL":"https:\/\/doi.org\/10.1145\/3459637.3482347","relation":{},"subject":[],"published":{"date-parts":[[2021,10,26]]},"assertion":[{"value":"2021-10-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}