{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T08:40:51Z","timestamp":1790757651667,"version":"4.1.0"},"reference-count":73,"publisher":"Informa UK Limited","issue":"533","funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Journal of the American Statistical Association"],"published-print":{"date-parts":[[2021,1,2]]},"DOI":"10.1080\/01621459.2020.1831925","type":"journal-article","created":{"date-parts":[[2020,10,6]],"date-time":"2020-10-06T14:29:06Z","timestamp":1601994546000},"page":"392-409","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":38,"title":["Learning When-to-Treat Policies"],"prefix":"10.1080","volume":"116","author":[{"given":"Xinkun","family":"Nie","sequence":"first","affiliation":[{"name":"Department of Computer Science, Stanford University, Stanford, CA;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emma","family":"Brunskill","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stanford University, Stanford, CA;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Wager","sequence":"additional","affiliation":[{"name":"Graduate School of Business, Stanford University, Stanford, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2020,11,30]]},"reference":[{"key":"CIT0001","first-page":"9","author":"Antos A.","year":"2008","journal-title":"Advances in Neural Information Processing Systems"},{"key":"CIT0002","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5038-2"},{"key":"CIT0003","doi-asserted-by":"crossref","unstructured":"Athey, S., and Imbens, G. (2018), \u201cDesign-Based Analysis in Difference-in-Differences Settings With Staggered Adoption,\u201d arXiv no. 1808.05293.","DOI":"10.3386\/w24963"},{"key":"CIT0004","doi-asserted-by":"publisher","DOI":"10.1214\/18-AOS1709"},{"key":"CIT0005","doi-asserted-by":"crossref","unstructured":"Athey, S., and Wager, S. (2020), \u201cPolicy Learning With Observational Data,\u201d Econometrica (forthcoming).","DOI":"10.3982\/ECTA15732"},{"key":"CIT0006","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2018.3253"},{"key":"CIT0007","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-7428-9"},{"key":"CIT0008","volume-title":"\u201cInformation-Theoretic Considerations in Batch Reinforcement Learning,\u201d in Proceedings of International Conference on Machine Learning","author":"Chen J.","year":"2019"},{"key":"CIT0009","doi-asserted-by":"publisher","DOI":"10.1111\/ectj.12097"},{"key":"CIT0010","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-031219-041220"},{"key":"CIT0011","volume-title":"\u201cImportance Sampling for Fair Policy Selection,\u201d in Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI)","author":"Doroudi S.","year":"2017"},{"key":"CIT0012","doi-asserted-by":"publisher","DOI":"10.1214\/14-STS500"},{"key":"CIT0013","unstructured":"Elmachtoub, A. N., and Grigas, P. (2017), \u201cSmart \u2018Predict, Then Optimize\u2019,\u201d arXiv no. 1710.08005."},{"key":"CIT0014","first-page":"503","volume":"6","author":"Ernst D.","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"CIT0015","first-page":"4809","volume":"17","author":"Farahmand A.-M.","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"CIT0016","doi-asserted-by":"crossref","unstructured":"Goel, K., Dann, C., and Brunskill, E. (2017), \u201cSample Efficient Policy Search for Optimal Stopping Domains,\u201d in Proceedings of the 26th International Joint Conference on Artificial Intelligence, pp. 1711\u20131717.","DOI":"10.24963\/ijcai.2017\/237"},{"key":"CIT0017","doi-asserted-by":"publisher","DOI":"10.1016\/0097-3165(95)90052-7"},{"key":"CIT0018","doi-asserted-by":"publisher","DOI":"10.1198\/016214501753168154"},{"key":"CIT0019","volume-title":"Social, and Biomedical Sciences","author":"Imbens G. W.","year":"2015"},{"key":"CIT0020","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9965.1991.tb00007.x"},{"key":"CIT0021","volume-title":"\u201cDoubly Robust Off-Policy Value Evaluation for Reinforcement Learning,\u201d in Proceedings of the 33rd International Conference on Machine Learning","author":"Jiang N.","year":"2016"},{"key":"CIT0022","unstructured":"Kakade, S. M. (2003), \u201cOn the Sample Complexity of Reinforcement Learning,\u201d PhD thesis, University of London, London, England."},{"key":"CIT0023","first-page":"8909","author":"Kallus N.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"CIT0024","volume-title":"\u201cStatistically Efficient Off-Policy Policy Gradients,\u201d in International Conference on Machine Learning","author":"Kallus N.","year":"2020"},{"key":"CIT0025","first-page":"9269","author":"Kallus N.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"CIT0026","doi-asserted-by":"publisher","DOI":"10.3982\/ECTA13288"},{"key":"CIT0027","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-030718-105251"},{"key":"CIT0028","doi-asserted-by":"publisher","DOI":"10.1111\/1467-985X.00154"},{"key":"CIT0029","first-page":"3703","author":"Le H.","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"CIT0030","unstructured":"Levine, S., Kumar, A., Tucker, G., and Fu, J. (2020), \u201cOffline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems,\u201d arXiv no. 2005.01643."},{"key":"CIT0031","first-page":"5361","author":"Liu Q.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"CIT0032","first-page":"2649","author":"Liu Y.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"CIT0033","unstructured":"Liu, Y., Swaminathan, A., Agarwal, A., and Brunskill, E. (2019), \u201cOff-Policy Policy Gradient With State Distribution Correction,\u201d in Proceedings of Uncertainty in AI."},{"key":"CIT0034","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2018.1537919"},{"key":"CIT0035","unstructured":"Luedtke, A., and Chambaz, A. (2017), \u201cFaster Rates for Policy Learning,\u201d arXiv no. 1704.06431."},{"key":"CIT0036","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-0262.2004.00530.x"},{"key":"CIT0037","doi-asserted-by":"publisher","DOI":"10.1198\/jasa.2009.0011"},{"key":"CIT0038","doi-asserted-by":"publisher","DOI":"10.1007\/s007800200070"},{"key":"CIT0039","first-page":"560","volume":"3","author":"Munos R.","year":"2003","journal-title":"\u201d in ICML"},{"key":"CIT0040","first-page":"815","volume":"9","author":"Munos R.","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"CIT0041","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00389"},{"key":"CIT0042","first-page":"1073","volume":"6","author":"Murphy S. A.","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"CIT0043","first-page":"1","volume":"10","author":"Neyman J.","year":"1923","journal-title":"\u201d Roczniki Nauk Rolniczych"},{"key":"CIT0044","unstructured":"Prasad, N., Cheng, L.F., Chivers, C., Draugelis, M., and Engelhardt, B. E. (2017), \u201cA Reinforcement Learning Approach to Weaning of Mechanical Ventilation in Intensive Care Units,\u201d in Conference on Uncertainty in Artificial Intelligence."},{"key":"CIT0045","unstructured":"Precup, D. (2000), \u201cEligibility Traces for Off-Policy Policy Evaluation,\u201d Computer Science Department Faculty Publication Series, p. 80."},{"key":"CIT0046","doi-asserted-by":"publisher","DOI":"10.1016\/0270-0255(86)90088-6"},{"key":"CIT0047","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9076-1_11"},{"key":"CIT0048","doi-asserted-by":"publisher","DOI":"10.1097\/00001648-200009000-00011"},{"key":"CIT0049","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1995.10476494"},{"key":"CIT0050","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1994.10476818"},{"key":"CIT0051","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/70.1.41"},{"key":"CIT0052","doi-asserted-by":"publisher","DOI":"10.1037\/h0037350"},{"key":"CIT0053","doi-asserted-by":"publisher","DOI":"10.2307\/1911259"},{"key":"CIT0054","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176350055"},{"key":"CIT0055","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton R. S.","year":"2018"},{"key":"CIT0056","first-page":"1731","volume":"16","author":"Swaminathan A.","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"CIT0057","unstructured":"Thomas, P., and Brunskill, E. (2016), \u201cData-Efficient Off-Policy Policy Evaluation for Reinforcement Learning,\u201d in International Conference on Machine Learning, pp. 2139\u20132148."},{"key":"CIT0058","doi-asserted-by":"publisher","DOI":"10.1201\/9780429192692"},{"key":"CIT0059","unstructured":"Uehara, M., and Jiang, N. (2019), \u201cMinimax Weight and Q-Function Learning for Off-Policy Evaluation,\u201d arXiv no. 1910.12809."},{"key":"CIT0060","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-65304-4"},{"key":"CIT0061","doi-asserted-by":"publisher","DOI":"10.1007\/BF00250676"},{"key":"CIT0062","doi-asserted-by":"publisher","DOI":"10.1214\/14-STS493"},{"key":"CIT0063","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"CIT0064","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(09)60612-7"},{"key":"CIT0065","unstructured":"Zanette, A., and Brunskill, E. (2019), \u201cTighter Problem-Dependent Regret Bounds in Reinforcement Learning Without Domain Knowledge Using Value Function Bounds,\u201d in International Conference on Machine Learning, pp. 7304\u20137312."},{"key":"CIT0066","doi-asserted-by":"publisher","DOI":"10.1002\/sta.411"},{"key":"CIT0067","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/ast014"},{"key":"CIT0068","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1345743"},{"key":"CIT0069","doi-asserted-by":"publisher","DOI":"10.1111\/biom.12354"},{"key":"CIT0070","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2014.937488"},{"key":"CIT0071","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2012.695674"},{"key":"CIT0072","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2015.1093947"},{"key":"CIT0073","unstructured":"Zhou, Z., Athey, S., and Wager, S. (2018), \u201cOffline Multi-Action Policy Learning: Generalization and Optimization,\u201d arXiv no. 1810.04778."}],"container-title":["Journal of the American Statistical Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01621459.2020.1831925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T16:51:04Z","timestamp":1670518264000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01621459.2020.1831925"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,30]]},"references-count":73,"journal-issue":{"issue":"533","published-print":{"date-parts":[[2021,1,2]]}},"alternative-id":["10.1080\/01621459.2020.1831925"],"URL":"https:\/\/doi.org\/10.1080\/01621459.2020.1831925","relation":{},"ISSN":["0162-1459","1537-274X"],"issn-type":[{"value":"0162-1459","type":"print"},{"value":"1537-274X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,30]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=uasa20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=uasa20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2019-06-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-09-15","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-09-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-11-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}