{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:19:53Z","timestamp":1756253993028,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T00:00:00Z","timestamp":1701302400000},"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":[[2023,11,30]]},"DOI":"10.1145\/3627676.3627680","type":"proceedings-article","created":{"date-parts":[[2023,12,30]],"date-time":"2023-12-30T06:05:14Z","timestamp":1703916314000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Adversarially Trained Environment Models Are Effective Policy Evaluators and Improvers - An Application to Information Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6731-460X","authenticated-orcid":false,"given":"Yao","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8726-3927","authenticated-orcid":false,"given":"Yifan","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3351-5401","authenticated-orcid":false,"given":"Xinyi","family":"Dai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8953-3203","authenticated-orcid":false,"given":"Jianghao","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1000-3232","authenticated-orcid":false,"given":"Hang","family":"Lai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6377-1513","authenticated-orcid":false,"given":"Yunfei","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0281-8271","authenticated-orcid":false,"given":"Yong","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,30]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.1145\/1148170.1148177"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_2_1","DOI":"10.1145\/1277741.1277902"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_3_1","DOI":"10.1007\/s10458-010-9148-z"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1145\/2872427.2883033"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.1145\/1102351.1102363"},{"key":"e_1_3_2_1_6_1","first-page":"23","article-title":"From ranknet to lambdarank to lambdamart: An overview","volume":"11","author":"Burges JC","year":"2010","unstructured":"Christopher\u00a0JC Burges. 2010. From ranknet to lambdarank to lambdamart: An overview. Learning 11, 23-581 (2010), 81.","journal-title":"Learning"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.1145\/1273496.1273513"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.1145\/2063576.2063668"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.1145\/1645953.1646033"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_10_1","DOI":"10.1145\/1526709.1526711"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.1145\/3357384.3358158"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.1145\/3336191.3371819"},{"key":"e_1_3_2_1_13_1","volume-title":"On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho, Bart Van\u00a0Merri\u00ebnboer, Dzmitry Bahdanau, and Yoshua Bengio. 2014. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)."},{"key":"e_1_3_2_1_14_1","volume-title":"Click models for web search. Synthesis lectures on information concepts, retrieval, and services 7, 3","author":"Chuklin Aleksandr","year":"2015","unstructured":"Aleksandr Chuklin, Ilya Markov, and Maarten\u00a0de Rijke. 2015. Click models for web search. Synthesis lectures on information concepts, retrieval, and services 7, 3 (2015), 1\u2013115."},{"key":"e_1_3_2_1_15_1","volume-title":"Machine Learning for Information Retrieval: TREC 2009 Web, Relevance Feedback and Legal Tracks.. In TREC.","author":"Cormack V","year":"2009","unstructured":"Gordon\u00a0V Cormack and Mona Mojdeh. 2009. Machine Learning for Information Retrieval: TREC 2009 Web, Relevance Feedback and Legal Tracks.. In TREC."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1145\/1341531.1341545"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_17_1","DOI":"10.1145\/3340531.3412756"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1145\/3442381.3449913"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1145\/1390334.1390392"},{"key":"e_1_3_2_1_20_1","volume-title":"An F-shape Click Model for Information Retrieval on Multi-block Mobile Pages. arXiv preprint arXiv:2206.08604","author":"Fu Lingyue","year":"2022","unstructured":"Lingyue Fu, Jianghao Lin, Weiwen Liu, Ruiming Tang, Weinan Zhang, Rui Zhang, and Yong Yu. 2022. An F-shape Click Model for Information Retrieval on Multi-block Mobile Pages. arXiv preprint arXiv:2206.08604 (2022)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_21_1","DOI":"10.5555\/3104322.3104326"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_22_1","DOI":"10.1145\/1526709.1526712"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.1145\/1498759.1498818"},{"unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: A Factorization-Machine based Neural Network for CTR Prediction. In IJCAI.","key":"e_1_3_2_1_24_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_25_1","DOI":"10.1145\/3054912"},{"unstructured":"Michael Janner Justin Fu Marvin Zhang and Sergey Levine. 2019. When to trust your model: Model-based policy optimization. In Advances in Neural Information Processing Systems. 12519\u201312530.","key":"e_1_3_2_1_26_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_27_1","DOI":"10.1007\/978-3-540-78646-7_4"},{"key":"e_1_3_2_1_28_1","volume-title":"International Conference on Machine Learning. PMLR, 1215\u20131224","author":"Katariya Sumeet","year":"2016","unstructured":"Sumeet Katariya, Branislav Kveton, Csaba Szepesvari, and Zheng Wen. 2016. DCM bandits: Learning to rank with multiple clicks. In International Conference on Machine Learning. PMLR, 1215\u20131224."},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. PMLR, 767\u2013776","author":"Kveton Branislav","year":"2015","unstructured":"Branislav Kveton, Csaba Szepesvari, Zheng Wen, and Azin Ashkan. 2015. Cascading bandits: Learning to rank in the cascade model. In International conference on machine learning. PMLR, 767\u2013776."},{"key":"e_1_3_2_1_30_1","volume-title":"Multiple-play bandits in the position-based model. Advances in Neural Information Processing Systems 29","author":"Lagr\u00e9e Paul","year":"2016","unstructured":"Paul Lagr\u00e9e, Claire Vernade, and Olivier Cappe. 2016. Multiple-play bandits in the position-based model. Advances in Neural Information Processing Systems 29 (2016)."},{"key":"e_1_3_2_1_31_1","first-page":"3694","article-title":"On Effective Scheduling of Model-based Reinforcement Learning","volume":"34","author":"Lai Hang","year":"2021","unstructured":"Hang Lai, Jian Shen, Weinan Zhang, Yimin Huang, Xing Zhang, Ruiming Tang, Yong Yu, and Zhenguo Li. 2021. On Effective Scheduling of Model-based Reinforcement Learning. Advances in Neural Information Processing Systems 34 (2021), 3694\u20133705.","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_32_1","DOI":"10.1145\/3404835.3462895"},{"unstructured":"Tie-Yan Liu. 2011. Learning to rank for information retrieval. (2011).","key":"e_1_3_2_1_33_1"},{"key":"e_1_3_2_1_34_1","volume-title":"A cognitive analysis of information retrieval. Information Science: Integration in Perspective\u2014Proceedings of CoLIS2","author":"Mizzaro Stefano","year":"1996","unstructured":"Stefano Mizzaro. 1996. A cognitive analysis of information retrieval. Information Science: Integration in Perspective\u2014Proceedings of CoLIS2 (1996), 233\u2013250."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_35_1","DOI":"10.1145\/1416950.1416952"},{"key":"e_1_3_2_1_36_1","volume-title":"Amalthaea: An evolving multi-agent information filtering and discovery system for the WWW. Autonomous agents and multi-agent systems 1, 1","author":"Moukas Alexandros","year":"1998","unstructured":"Alexandros Moukas and Pattie Maes. 1998. Amalthaea: An evolving multi-agent information filtering and discovery system for the WWW. Autonomous agents and multi-agent systems 1, 1 (1998), 59\u201388."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_37_1","DOI":"10.1023\/A:1010022931168"},{"key":"e_1_3_2_1_38_1","volume-title":"Hyperparameter selection for offline reinforcement learning. arXiv preprint arXiv:2007.09055","author":"Paine Tom\u00a0Le","year":"2020","unstructured":"Tom\u00a0Le Paine, Cosmin Paduraru, Andrea Michi, Caglar Gulcehre, Konrad Zolna, Alexander Novikov, Ziyu Wang, and Nando de Freitas. 2020. Hyperparameter selection for offline reinforcement learning. arXiv preprint arXiv:2007.09055 (2020)."},{"key":"e_1_3_2_1_39_1","volume-title":"MySpiders: Evolve your own intelligent Web crawlers. Autonomous agents and multi-agent systems 5","author":"Pant Gautam","year":"2002","unstructured":"Gautam Pant and Filippo Menczer. 2002. MySpiders: Evolve your own intelligent Web crawlers. Autonomous agents and multi-agent systems 5 (2002), 221\u2013229."},{"key":"e_1_3_2_1_40_1","volume-title":"The probability ranking principle in IR. Journal of documentation","author":"Robertson E","year":"1977","unstructured":"Stephen\u00a0E Robertson. 1977. The probability ranking principle in IR. Journal of documentation (1977)."},{"key":"e_1_3_2_1_41_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_42_1","DOI":"10.1145\/1148170.1148176"},{"key":"e_1_3_2_1_43_1","volume-title":"Visualizing data using t-SNE.Journal of machine learning research 9, 11","author":"Maaten Laurens Van\u00a0der","year":"2008","unstructured":"Laurens Van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE.Journal of machine learning research 9, 11 (2008)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_44_1","DOI":"10.1007\/s10458-007-9021-x"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_45_1","DOI":"10.1145\/2484028.2484068"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_46_1","DOI":"10.1145\/1571941.1572005"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_47_1","DOI":"10.1145\/3539597.3570399"},{"key":"e_1_3_2_1_48_1","volume-title":"On Value Discrepancy of Imitation Learning. arXiv preprint arXiv:1911.07027","author":"Xu Tian","year":"2019","unstructured":"Tian Xu, Ziniu Li, and Yang Yu. 2019. On Value Discrepancy of Imitation Learning. arXiv preprint arXiv:1911.07027 (2019)."},{"key":"e_1_3_2_1_49_1","volume-title":"Dynamic information retrieval modeling. Synthesis lectures on information concepts, retrieval, and services 8, 3","author":"Yang Grace\u00a0Hui","year":"2016","unstructured":"Grace\u00a0Hui Yang, Marc Sloan, and Jun Wang. 2016. Dynamic information retrieval modeling. Synthesis lectures on information concepts, retrieval, and services 8, 3 (2016), 1\u2013144."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_50_1","DOI":"10.1145\/1871437.1871672"},{"key":"e_1_3_2_1_51_1","volume-title":"Learning to rank using user clicks and visual features for image retrieval","author":"Yu Jun","year":"2014","unstructured":"Jun Yu, Dacheng Tao, Meng Wang, and Yong Rui. 2014. Learning to rank using user clicks and visual features for image retrieval. IEEE transactions on cybernetics 45, 4 (2014), 767\u2013779."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_52_1","DOI":"10.1145\/3442381.3449918"},{"key":"e_1_3_2_1_53_1","volume-title":"Deep Learning for Click-Through Rate Estimation. arXiv preprint arXiv:2104.10584","author":"Zhang Weinan","year":"2021","unstructured":"Weinan Zhang, Jiarui Qin, Wei Guo, Ruiming Tang, and Xiuqiang He. 2021. Deep Learning for Click-Through Rate Estimation. arXiv preprint arXiv:2104.10584 (2021)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_54_1","DOI":"10.1007\/978-3-030-86486-6_7"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_55_1","DOI":"10.1145\/3397271.3401467"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_56_1","DOI":"10.1145\/2020408.2020613"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_57_1","DOI":"10.5121\/ijcsit.2012.4304"}],"event":{"acronym":"DAI '23","name":"DAI '23: The Fifth International Conference on Distributed Artificial Intelligence","location":"Singapore Singapore"},"container-title":["The Fifth International Conference on Distributed Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627676.3627680","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627676.3627680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T19:25:53Z","timestamp":1756236353000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627676.3627680"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,30]]},"references-count":57,"alternative-id":["10.1145\/3627676.3627680","10.1145\/3627676"],"URL":"https:\/\/doi.org\/10.1145\/3627676.3627680","relation":{},"subject":[],"published":{"date-parts":[[2023,11,30]]},"assertion":[{"value":"2023-12-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}