{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T21:23:59Z","timestamp":1776288239167,"version":"3.50.1"},"reference-count":64,"publisher":"Informa UK Limited","issue":"550","license":[{"start":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T00:00:00Z","timestamp":1728604800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Journal of the American Statistical Association"],"published-print":{"date-parts":[[2025,4,3]]},"DOI":"10.1080\/01621459.2024.2395593","type":"journal-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T11:20:35Z","timestamp":1725880835000},"page":"1102-1114","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":8,"title":["Off-Policy Evaluation in Doubly Inhomogeneous Environments"],"prefix":"10.1080","volume":"120","author":[{"given":"Zeyu","family":"Bian","sequence":"first","affiliation":[{"name":"Department of Management Science, University of Miami","place":["Coral Gables"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengchun","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Statistics, London School of Economics and Political Science","place":["London, UK"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0270-7969","authenticated-orcid":false,"given":"Zhengling","family":"Qi","sequence":"additional","affiliation":[{"name":"Department of Decision Sciences, The George Washington University","place":["Washington"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Management Science, University of Miami","place":["Coral Gables"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2024,10,11]]},"reference":[{"key":"e_1_3_5_2_1","doi-asserted-by":"publisher","DOI":"10.1515\/9781400829828"},{"key":"e_1_3_5_3_1","unstructured":"Arkhangelsky D. Imbens G. W. Lei L. and Luo X. (2021) \u201cDouble-Robust Two-Way-Fixed-Effects Regression for Panel Data \u201d arXiv preprint arXiv:2107.13737."},{"key":"e_1_3_5_4_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2014.4005"},{"key":"e_1_3_5_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/1468-0262.00273"},{"key":"e_1_3_5_6_1","doi-asserted-by":"publisher","DOI":"10.1214\/16-AOS1435"},{"key":"e_1_3_5_7_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.53.100901.135239"},{"key":"e_1_3_5_8_1","unstructured":"Chen E. Y. Song R. and Jordan M. I. (2022) \u201cReinforcement Learning with Heterogeneous Data: Estimation and Inference \u201d arXiv preprint arXiv:2202.00088."},{"key":"e_1_3_5_9_1","first-page":"1042","volume-title":"International Conference on Machine Learning","author":"Chen J.","year":"2019","unstructured":"Chen, J., and Jiang, N. (2019), \u201cInformation-Theoretic Considerations in Batch Reinforcement Learning,\u201d in International Conference on Machine Learning, pp. 1042\u20131051, PMLR."},{"key":"e_1_3_5_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jeconom.2015.03.010"},{"key":"e_1_3_5_11_1","first-page":"3558","volume-title":"International Conference on Machine Learning","author":"Chen X.","year":"2022","unstructured":"Chen, X., and Qi, Z. (2022), \u201cOn Well-Posedness and Minimax Optimal Rates of Nonparametric q-function Estimation in Off-Policy Evaluation,\u201d in International Conference on Machine Learning, pp. 3558\u20133582, PMLR."},{"key":"e_1_3_5_12_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"key":"e_1_3_5_13_1","doi-asserted-by":"publisher","DOI":"10.1137\/S0036144598338446"},{"key":"e_1_3_5_14_1","unstructured":"Dwivedi R. Tian K. Tomkins S. Klasnja P. Murphy S. and Shah D. (2022) \u201cCounterfactual Inference for Sequential Experiments \u201d arXiv preprint arXiv:2202.06891."},{"key":"e_1_3_5_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-021-06506-y"},{"key":"e_1_3_5_16_1","unstructured":"Fan J. Wang Z. Xie Y. and Yang Z. (2020) \u201cA Theoretical Analysis of Deep q-Learning \u201d in Learning for Dynamics and Control pp. 486\u2013489 PMLR."},{"key":"e_1_3_5_17_1","doi-asserted-by":"publisher","DOI":"10.2307\/1907330"},{"key":"e_1_3_5_18_1","unstructured":"Fu J. Kumar A. Nachum O. Tucker G. and Levine S. (2020) \u201cD4rl: Datasets for Deep Data-Driven Reinforcement Learning \u201d arXiv preprint arXiv:2004.07219."},{"key":"e_1_3_5_19_1","first-page":"2366","volume-title":"International Conference on Machine Learning","author":"Gottesman O.","year":"2019","unstructured":"Gottesman, O., Liu, Y., Sussex, S., Brunskill, E., and Doshi-Velez, F. (2019), \u201cCombining Parametric and Nonparametric Models for Off-Policy Evaluation,\u201d in International Conference on Machine Learning, pp. 2366\u20132375, PMLR."},{"key":"e_1_3_5_20_1","doi-asserted-by":"publisher","DOI":"10.1162\/00208180151140630"},{"key":"e_1_3_5_21_1","doi-asserted-by":"publisher","DOI":"10.1257\/aer.101.5.1775"},{"key":"e_1_3_5_22_1","unstructured":"Hu L. Li M. Shi C. Wu Z. and Fryzlewicz P. (2022) \u201cDoubly Inhomogeneous Reinforcement Learning \u201d arXiv preprint arXiv:2211.03983."},{"key":"e_1_3_5_23_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1030563984"},{"key":"e_1_3_5_24_1","doi-asserted-by":"publisher","DOI":"10.1111\/ajps.12417"},{"key":"e_1_3_5_25_1","doi-asserted-by":"publisher","DOI":"10.1017\/pan.2020.33"},{"key":"e_1_3_5_26_1","first-page":"652","volume-title":"International Conference on Machine Learning","author":"Jiang N.","year":"2016","unstructured":"Jiang, N., and Li, L. (2016), \u201cDoubly Robust Off-Policy Value Evaluation for Reinforcement Learning,\u201d in International Conference on Machine Learning, pp. 652\u2013661, PMLR."},{"key":"e_1_3_5_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"e_1_3_5_28_1","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0b013e31819def97"},{"key":"e_1_3_5_29_1","first-page":"1","article-title":"\u201cDouble Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes,\u201d","volume":"21","author":"Kallus N.","year":"2020","unstructured":"Kallus, N., and Uehara, M. (2020), \u201cDouble Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes,\u201d Journal of Machine Learning Research, 21, 1\u201363.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_5_30_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2021.2249"},{"key":"e_1_3_5_31_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974188"},{"key":"e_1_3_5_32_1","first-page":"3703","volume-title":"International Conference on Machine Learning","author":"Le H.","year":"2019","unstructured":"Le, H., Voloshin, C., and Yue, Y. (2019), \u201cBatch Policy Learning Under Constraints,\u201d in International Conference on Machine Learning, pp. 3703\u20133712, PMLR."},{"key":"e_1_3_5_33_1","unstructured":"Levine S. Kumar A. Tucker G. and Fu J. (2020) \u201cOffline Reinforcement Learning: Tutorial Review and Perspectives on Open Problems \u201d arXiv preprint arXiv:2005.01643."},{"key":"e_1_3_5_34_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2023.2450"},{"key":"e_1_3_5_35_1","unstructured":"Li M. Shi C. Wu Z. and Fryzlewicz P. (2022) \u201cReinforcement Learning in Possibly Nonstationary Environments \u201d arXiv preprint arXiv:2203.01707."},{"key":"e_1_3_5_36_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2020.1807993"},{"key":"e_1_3_5_37_1","doi-asserted-by":"publisher","DOI":"10.1214\/22-AOS2231"},{"key":"e_1_3_5_38_1","article-title":"\u201cBreaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation,\u201d in","volume":"31","author":"Liu Q.","year":"2018","unstructured":"Liu, Q., Li, L., Tang, Z., and Zhou, D. (2018), \u201cBreaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation,\u201d in Advances in Neural Information Processing Systems (Vol. 31).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_5_39_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10480682"},{"key":"e_1_3_5_40_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2018.1537919"},{"key":"e_1_3_5_41_1","doi-asserted-by":"publisher","DOI":"10.1214\/aop\/1176996608"},{"key":"e_1_3_5_42_1","doi-asserted-by":"publisher","DOI":"10.1214\/009053606000000281"},{"key":"e_1_3_5_43_1","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00389"},{"key":"e_1_3_5_44_1","unstructured":"Perdomo J. C. Krishnamurthy A. Bartlett P. and Kakade S. (2022) \u201cA Sharp Characterization of Linear Estimators for Offline Policy Evaluation \u201d arXiv preprint arXiv:2203.04236."},{"key":"e_1_3_5_45_1","unstructured":"Precup D. (2000) \u201cEligibility Traces for Off-Policy Policy Evaluation \u201d Computer Science Department Faculty Publication Series p. 80."},{"key":"e_1_3_5_46_1","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman M. L.","year":"2014","unstructured":"Puterman, M. L. (2014), Markov Decision Processes: Discrete Stochastic Dynamic Programming, Hoboken, NJ: Wiley."},{"key":"e_1_3_5_47_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2018.1529597"},{"key":"e_1_3_5_48_1","doi-asserted-by":"publisher","DOI":"10.1214\/10-AOS864"},{"key":"e_1_3_5_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9076-1_11"},{"key":"e_1_3_5_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/0022-0531(76)90046-6"},{"key":"e_1_3_5_51_1","doi-asserted-by":"publisher","DOI":"10.1214\/17-AOS1570"},{"key":"e_1_3_5_52_1","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12465"},{"key":"e_1_3_5_53_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"e_1_3_5_54_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.0287"},{"key":"e_1_3_5_55_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton R. S.","year":"2018","unstructured":"Sutton, R. S., and Barto, A. G. (2018), Reinforcement Learning: An Introduction, Cambridge, MA: MIT Press."},{"key":"e_1_3_5_56_1","doi-asserted-by":"publisher","DOI":"10.1201\/9780429192692"},{"key":"e_1_3_5_57_1","first-page":"9659","volume-title":"International Conference on Machine Learning","author":"Uehara M.","year":"2020","unstructured":"Uehara, M., Huang, J., and Jiang, N. (2020), \u201cMinimax Weight and q-function Learning for Off-Policy Evaluation,\u201d in International Conference on Machine Learning, pp. 9659\u20139668, PMLR."},{"key":"e_1_3_5_58_1","unstructured":"Uehara M. Shi C. and Kallus N. (2022) \u201cA Review of Off-Policy Evaluation in Reinforcement Learning \u201d arXiv preprint arXiv:2212.06355."},{"key":"e_1_3_5_59_1","unstructured":"Wang J. Qi Z. and Wong R. K. (2021) \u201cProjected State-Action Balancing Weights for Offline Reinforcement Learning \u201d arXiv preprint arXiv:2109.04640."},{"key":"e_1_3_5_60_1","first-page":"36355","volume-title":"International Conference on Machine Learning","author":"Wang J.","year":"2023","unstructured":"Wang, J., Shi, C., and Wu, Z. (2023), \u201cA Robust Test for the Stationarity Assumption in Sequential Decision Making,\u201d in International Conference on Machine Learning, pp. 36355\u201336379, PMLR."},{"key":"e_1_3_5_61_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176346060"},{"key":"e_1_3_5_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219824"},{"key":"e_1_3_5_63_1","volume-title":"International Conference on Learning Representations","author":"Zhang M. R.","year":"2020","unstructured":"Zhang, M. R., Paine, T. L., Nachum, O., Paduraru, C., Tucker, G., Wang, Z., and Norouzi, M. (2020), \u201cAutoregressive Dynamics Models for Offline Policy Evaluation and Optimization,\u201d in International Conference on Learning Representations."},{"key":"e_1_3_5_64_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2022.2138760"},{"key":"e_1_3_5_65_1","unstructured":"Zhou Y. Qi Z. Shi C. and Li L. (2022) \u201cOptimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach \u201d arXiv preprint arXiv:2210.14420."}],"container-title":["Journal of the American Statistical Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01621459.2024.2395593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:11:10Z","timestamp":1772723470000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01621459.2024.2395593"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,11]]},"references-count":64,"journal-issue":{"issue":"550","published-print":{"date-parts":[[2025,4,3]]}},"alternative-id":["10.1080\/01621459.2024.2395593"],"URL":"https:\/\/doi.org\/10.1080\/01621459.2024.2395593","relation":{},"ISSN":["0162-1459","1537-274X"],"issn-type":[{"value":"0162-1459","type":"print"},{"value":"1537-274X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,11]]},"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":"2023-06-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-27","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}