{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T01:24:52Z","timestamp":1787880292966,"version":"build-2784847793"},"reference-count":25,"publisher":"Informa UK Limited","issue":"548","content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Journal of the American Statistical Association"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1080\/01621459.2024.2308317","type":"journal-article","created":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T12:26:46Z","timestamp":1705926406000},"page":"3113-3126","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":9,"title":["Reinforcement Learning in Latent Heterogeneous Environments"],"prefix":"10.1080","volume":"119","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7599-1828","authenticated-orcid":false,"given":"Elynn Y.","family":"Chen","sequence":"first","affiliation":[{"name":"New York University","place":["New York"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1875-2115","authenticated-orcid":false,"given":"Rui","family":"Song","sequence":"additional","affiliation":[{"name":"Amazon Inc","place":["Seattle"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael I.","family":"Jordan","sequence":"additional","affiliation":[{"name":"University of California","place":["Berkeley, Berkeley"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2024,6,11]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1573-4412(07)06069-2"},{"key":"e_1_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.3982\/ECTA15238"},{"key":"e_1_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/135048599352349"},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asy043"},{"key":"e_1_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1198\/016214501753382273"},{"key":"e_1_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1201\/9780429096280"},{"key":"e_1_3_3_8_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."},{"key":"e_1_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"e_1_3_3_10_1","unstructured":"Ke T. Fan J. and Wu Y. (2013) \u201cHomogeneity in Regression \u201d arXiv preprint arXiv:1303.7409."},{"key":"e_1_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0213-5"},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-092451"},{"key":"e_1_3_3_13_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_3_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2022.05.043"},{"key":"e_1_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2018.1537919"},{"key":"e_1_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2016.1148039"},{"key":"e_1_3_3_17_1","volume-title":"33rd Conference on Uncertainty in Artificial Intelligence, UAI 2017","author":"Prasad N.","year":"2017","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 33rd Conference on Uncertainty in Artificial Intelligence, UAI 2017."},{"key":"e_1_3_3_18_1","first-page":"5528","volume-title":"International Conference on Machine Learning","author":"Rowland M.","year":"2019","unstructured":"Rowland, M., Dadashi, R., Kumar, S., Munos, R., Bellemare, M. G., and Dabney, W. (2019), \u201cStatistics and Samples in Distributional Reinforcement Learning,\u201d in International Conference on Machine Learning, pp. 5528\u20135536."},{"key":"e_1_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1198\/jasa.2010.tm09380"},{"key":"e_1_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12465"},{"key":"e_1_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2022.2110878"},{"key":"e_1_3_3_22_1","first-page":"9744","volume-title":"International Conference on Machine Learning","author":"Singh G.","year":"2021","unstructured":"Singh, G., Peri, S., Kim, J., Kim, H., and Ahn, S. (2021), \u201cStructured World Belief for Reinforcement Learning in POMDP,\u201d in International Conference on Machine Learning, pp. 9744\u20139755, PMLR."},{"key":"e_1_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.2307\/3213832"},{"key":"e_1_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9541"},{"key":"e_1_3_3_25_1","unstructured":"Xu Z. Laber E. Staicu A.-M. and Severus E. (2020) \u201cLatent-State Models for Precision Medicine \u201d arXiv preprint arXiv:2005.13001."},{"key":"e_1_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1214\/09-AOS729"}],"container-title":["Journal of the American Statistical Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01621459.2024.2308317","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T23:23:45Z","timestamp":1740785025000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01621459.2024.2308317"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,11]]},"references-count":25,"journal-issue":{"issue":"548","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["10.1080\/01621459.2024.2308317"],"URL":"https:\/\/doi.org\/10.1080\/01621459.2024.2308317","relation":{},"ISSN":["0162-1459","1537-274X"],"issn-type":[{"value":"0162-1459","type":"print"},{"value":"1537-274X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,11]]},"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":"2022-02-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-05","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}