{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:32:08Z","timestamp":1740123128885,"version":"3.37.3"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T00:00:00Z","timestamp":1620086400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T00:00:00Z","timestamp":1620086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1007\/s10994-021-05978-9","type":"journal-article","created":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T21:07:50Z","timestamp":1620162470000},"page":"2577-2602","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Lessons on off-policy methods from a notification component of a chatbot"],"prefix":"10.1007","volume":"110","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0270-7192","authenticated-orcid":false,"given":"Scott","family":"Rome","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianwen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Kreisel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ding","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,4]]},"reference":[{"key":"5978_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, A., Basu, S., Schnabel, T., & Joachims, T. (2017). Effective evaluation using logged bandit feedback from multiple loggers. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 687\u2013696.","DOI":"10.1145\/3097983.3098155"},{"key":"5978_CR2","unstructured":"Aly, M. (2005). Survey on multiclass classification methods. Neural Networks, 19, 1\u20139."},{"key":"5978_CR3","unstructured":"Bottou, L., Peters, J., Qui\u00f1onero-Candela, J., Charles, D. X., Chickering, D. M., Ed Snelson, et\u00a0al. (2013). Counterfactual reasoning and learning systems: The example of computational advertising. Journal of Machine Learning Research 14(65), 3207\u20133260."},{"key":"5978_CR4","doi-asserted-by":"crossref","unstructured":"Cer, D., Yang, Y., Kong, S. Y., Hua, N., Limtiaco, N. L. U., St. John, R., Constant, N., Guajardo-C\u00e9spedes, M., Yuan, S., Tar, C., Hsuan Sung, Y., Strope, B., & Kurzweil, R. (2018). Universal sentence encoder. In EMNLP Demonstration. Brussels, Belgium. https:\/\/www.aclweb.org\/anthology\/D18-2.pdf.","DOI":"10.18653\/v1\/D18-2029"},{"key":"5978_CR5","doi-asserted-by":"crossref","unstructured":"Chen, M., Beutel, A., Covington, P., Jain, S., Belletti, F., & Ed\u00a0H. Chi. (2018). Top-k off-policy correction for a reinforce recommender system. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, WSDM \u201919, pages 456\u2013464, New York, NY, USA: ACM.","DOI":"10.1145\/3289600.3290999"},{"key":"5978_CR6","unstructured":"Chollet, F. et\u00a0al. (2015). Keras. https:\/\/keras.io."},{"issue":"2","key":"5978_CR7","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1145\/362007.362035","volume":"13","author":"J Earley","year":"1970","unstructured":"Earley, J. (1970). An efficient context-free parsing algorithm. Communication of the ACM, 13(2), 94\u2013102.","journal-title":"Communication of the ACM"},{"key":"5978_CR8","unstructured":"Hanna, J. P., Thomas, P. S., Stone, P., & Niekum, S. (2017). Data-efficient policy evaluation through behavior policy search. In D. Precup, Y. W. Teh (Eds.), InProceedings of the 34th International Conference on Machine Learning, volume\u00a070 of Proceedings of Machine Learning Research, pages 1394\u20131403, International Convention Centre, Sydney, Australia, 06\u201311. PMLR."},{"issue":"2","key":"5978_CR9","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1198\/106186008X320456","volume":"17","author":"EL Ionides","year":"2008","unstructured":"Ionides, E. L. (2008). Truncated importance sampling. Journal of Computational and Graphical Statistics, 17(2), 295\u2013311.","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"5978_CR10","unstructured":"Jeunen, O., Mykhaylov, D., Rohde, D., Vasile, F., Gilotte, A., & Martin, B. (2019). Learning from bandit feedback: An overview of the state-of-the-art."},{"key":"5978_CR11","doi-asserted-by":"crossref","unstructured":"Joachims, T., & Swaminathan, A. (2016). Sigir tutorial on counterfactual evaluation and learning for search, recommendation and ad placement. In Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 1199\u20131201. ACM.","DOI":"10.1145\/2911451.2914803"},{"key":"5978_CR12","unstructured":"Karampatziakis, N., Kochman, S., Huang, J., Mineiro, P., Osborne, K., & Chen, W. (2019). Lessons from contextual bandit learning in a customer support bot. arXiv preprint arXiv:1905.02219."},{"key":"5978_CR13","unstructured":"Lample, G., Conneau, A., Denoyer, L., & Ranzato, M. (2018). Unsupervised machine translation using monolingual corpora only. International Conference on Learning Representations."},{"key":"5978_CR14","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, S., Kleban, J., & Gupta, A. (2015). Counterfactual estimation and optimization of click metrics in search engines: A case study. In Proceedings of the 24th International Conference on World Wide Web, WWW \u201915 Companion, pages 929\u2013934, New York, NY, USA: ACM.","DOI":"10.1145\/2740908.2742562"},{"key":"5978_CR15","unstructured":"Li, L., Chu, W., Langford, J., Moon, T., & Wang, X. (2012) An unbiased offline evaluation of contextual bandit algorithms with generalized linear models. In D. Glowacka, L. Dorard, & J. Shawe-Taylor (Eds.), Proceedings of the Workshop on On-line Trading of Exploration and Exploitation 2, volume\u00a026 of Proceedings of Machine Learning Research, pages 19\u201336, Bellevue, Washington, USA, 02: PMLR."},{"key":"5978_CR16","doi-asserted-by":"crossref","unstructured":"Li, L., Chu, W., Langford, J., & Schapire, R.E. (2010). A contextual-bandit approach to personalized news article recommendation. In Proceedings of the 19th International Conference on World Wide Web, WWW \u201910, pages 661\u2013670, New York, NY, USA: ACM.","DOI":"10.1145\/1772690.1772758"},{"key":"5978_CR17","doi-asserted-by":"crossref","unstructured":"Li, L., Chu, W., Langford, J., & Wang, X. (2011). Unbiased offline evaluation of contextual-bandit-based news article recommendation algorithms. In Proceedings of the Fourth ACM International Conference on Web Search and Data Mining, WSDM \u201911, pages 297\u2013306, New York, NY, USA: ACM.","DOI":"10.1145\/1935826.1935878"},{"key":"5978_CR18","unstructured":"Li, L., Munos, R., & Szepesv\u00e1ri, C. (2015). Toward minimax off-policy value estimation. 01, pages 608\u2013616."},{"key":"5978_CR19","doi-asserted-by":"crossref","unstructured":"Patro, A., Govindan, S., & Banerjee, S. (2013). Observing home wireless experience through wifi aps. In Proceedings of the 19th Annual International Conference on Mobile Computing & Networking, MobiCom \u201913, page 339\u2013350, New York, NY, USA: Association for Computing Machinery.","DOI":"10.1145\/2500423.2500448"},{"key":"5978_CR20","unstructured":"Pinckernell, N., & Rome, S. (2020). Operationalizing streaming telemetry and machine learning model serving: Customer experience automation. In Proceedings of SCTE$$\\bullet$$ISBE Cable-Tec Expo, Fall Technical Forum."},{"key":"5978_CR21","unstructured":"Schulman, J., Levine, S., Moritz, P., Jordan, M.I., Abbeel, P. (2015). Trust region policy optimization. CoRR, abs\/1502.05477."},{"key":"5978_CR22","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. CoRR, abs\/1707.06347."},{"key":"5978_CR23","unstructured":"Strehl, A., Langford, J., Li, L., & Kakade, S.M. (2010). Learning from logged implicit exploration data. In J.\u00a0D. Lafferty, C.\u00a0K.\u00a0I. Williams, J.\u00a0Shawe-Taylor, R.\u00a0S. Zemel, and A.\u00a0Culotta (Eds.), Advances in Neural Information Processing Systems 23, pages 2217\u20132225. Curran Associates, Inc."},{"issue":"52","key":"5978_CR24","first-page":"1731","volume":"16","author":"A Swaminathan","year":"2015","unstructured":"Swaminathan, A., & Joachims, T. (2015). Batch learning from logged bandit feedback through counterfactual risk minimization. Journal of Machine Learning Research, 16(52), 1731\u20131755.","journal-title":"Journal of Machine Learning Research"},{"key":"5978_CR25","unstructured":"Swaminathan, A., & Joachims, T. (2015). The self-normalized estimator for counterfactual learning. In C.\u00a0Cortes, N.\u00a0D. Lawrence, D.\u00a0D. Lee, M.\u00a0Sugiyama, and R.\u00a0Garnett (Eds.), Advances in Neural Information Processing Systems 28, pages 3231\u20133239. Curran Associates, Inc."},{"key":"5978_CR26","unstructured":"Swaminathan, A., Krishnamurthy, A., Agarwal, A., Dud\u00edk, M., Langford, J., Jose, D., & Zitouni, I. (2016). Off-policy evaluation for slate recommendation. CoRR, abs\/1605.04812."},{"key":"5978_CR27","unstructured":"Vlassis, N., Bibaut, A., Dimakopoulou, M., & Jebara, T. (2019). On the design of estimators for bandit off-policy evaluation. In Kamalika Chaudhuri and Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, volume\u00a097 of Proceedings of Machine Learning Research, pages 6468\u20136476, Long Beach, California, USA, 09\u201315: PMLR."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-05978-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-021-05978-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-05978-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,4]],"date-time":"2022-05-04T00:06:41Z","timestamp":1651622801000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-021-05978-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,4]]},"references-count":27,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["5978"],"URL":"https:\/\/doi.org\/10.1007\/s10994-021-05978-9","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2021,5,4]]},"assertion":[{"value":"24 February 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 March 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}