{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T03:09:00Z","timestamp":1780369740652,"version":"3.54.1"},"reference-count":42,"publisher":"Informa UK Limited","issue":"6","funder":[{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai Municipality","doi-asserted-by":"publisher","award":["2408085MA019"],"award-info":[{"award-number":["2408085MA019"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"General Project of Humanities and Social Sciences Research of Ministry of Education","award":["12071146"],"award-info":[{"award-number":["12071146"]}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["25YJAZH200"],"award-info":[{"award-number":["25YJAZH200"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Control"],"published-print":{"date-parts":[[2026,6,3]]},"DOI":"10.1080\/00207179.2025.2610334","type":"journal-article","created":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T01:32:57Z","timestamp":1767835977000},"page":"1750-1768","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":0,"title":["Optimal investment and reinsurance in an entropy-regularised multidimensional reinforcement learning model"],"prefix":"10.1080","volume":"99","author":[{"given":"Yifan","family":"Wu","sequence":"first","affiliation":[{"name":"East China Normal University","place":["Shanghai, People's Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqin","family":"Wei","sequence":"additional","affiliation":[{"name":"East China Normal University","place":["Shanghai, People's Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Xu","sequence":"additional","affiliation":[{"name":"Anhui Normal University","place":["Wuhu, People's Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2026,1,7]]},"reference":[{"key":"e_1_3_5_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.insmatheco.2007.11.002"},{"key":"e_1_3_5_3_1","doi-asserted-by":"publisher","DOI":"10.1137\/20M1348856"},{"key":"e_1_3_5_4_1","doi-asserted-by":"publisher","DOI":"10.1111\/mafi.2007.17.issue-3"},{"key":"e_1_3_5_5_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.20.4.937"},{"key":"e_1_3_5_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"e_1_3_5_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/mafi.v33.4"},{"key":"e_1_3_5_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110177"},{"key":"e_1_3_5_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-9058-9"},{"key":"e_1_3_5_10_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2021.1238"},{"key":"e_1_3_5_11_1","unstructured":"Haarnoja T. Tang H. Abbeel P. & Levine S. (2017). Reinforcement learning with deep energy-based policies. In International Conference on Machine Learning (pp. 1352\u20131361). PMLR."},{"issue":"6","key":"e_1_3_5_12_1","first-page":"535","article-title":"Minimizing the lifetime ruin under borrowing and short-selling constraints","volume":"2014","author":"Haluk Y.","year":"2013","unstructured":"Haluk, Y. (2013). Minimizing the lifetime ruin under borrowing and short-selling constraints. Scandinavian Actuarial Journal, 2014(6), 535\u2013560.","journal-title":"Scandinavian Actuarial Journal"},{"key":"e_1_3_5_13_1","doi-asserted-by":"publisher","DOI":"10.1137\/22M1524734"},{"key":"e_1_3_5_14_1","doi-asserted-by":"publisher","DOI":"10.1093\/imaman\/dpu021"},{"key":"e_1_3_5_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.insmatheco.2011.09.002"},{"key":"e_1_3_5_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0255(88)90002-3"},{"key":"e_1_3_5_17_1","unstructured":"Liu J. Gu X. & Liu S. (2019). Policy optimization reinforcement learning with entropy regularization. arXiv preprint arXiv:1912.01557."},{"key":"e_1_3_5_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-020-01352-4"},{"key":"e_1_3_5_19_1","doi-asserted-by":"publisher","DOI":"10.3934\/jimo.2013.9.487"},{"key":"e_1_3_5_20_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017940631555"},{"key":"e_1_3_5_21_1","first-page":"2775","article-title":"Bridging the gap between value and policy based reinforcement learning","volume":"30","author":"Nachum O.","year":"2017","unstructured":"Nachum, O., Norouzi, M., Xu, K., & Schuurmans, D. (2017). Bridging the gap between value and policy based reinforcement learning. Advances in Neural Information Processing Systems, 30, 2775\u20132785.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_5_22_1","unstructured":"Neu G. Jonsson A. & G\u00f3mez V. (2017). A unified view of entropy-regularized markov decision processes. arXiv preprint arXiv:1705.07798."},{"key":"e_1_3_5_23_1","doi-asserted-by":"publisher","DOI":"10.1137\/20M1312435"},{"key":"e_1_3_5_24_1","unstructured":"Schulman J. Wolski F. Dhariwal P. Radford A. & Klimov O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347."},{"key":"e_1_3_5_25_1","unstructured":"\u0160i\u0161ka D. & Szpruch \u0141. (2020). Gradient flows for regularized stochastic control problems. arXiv preprint arXiv:2006.05956."},{"key":"e_1_3_5_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.03.017"},{"key":"e_1_3_5_27_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton R. S.","year":"2018","unstructured":"Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. MIT Press."},{"key":"e_1_3_5_28_1","doi-asserted-by":"publisher","DOI":"10.1137\/21M1448185"},{"key":"e_1_3_5_29_1","first-page":"1350","article-title":"Distributional policy optimization: An alternative approach for continuous control","volume":"32","author":"Tessler C.","year":"2019","unstructured":"Tessler, C., Tennenholtz, G., & Mannor, S. (2019). Distributional policy optimization: An alternative approach for continuous control. Advances in Neural Information Processing Systems, 32, 1350\u20131360.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"e_1_3_5_30_1","first-page":"8145","article-title":"Reinforcement learning in continuous time and space: A stochastic control approach","volume":"21","author":"Wang H.","year":"2020","unstructured":"Wang, H., Zariphopoulou, T., & Zhou, X. Y. (2020). Reinforcement learning in continuous time and space: A stochastic control approach. The Journal of Machine Learning Research, 21(1), 8145\u20138178.","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_5_31_1","doi-asserted-by":"publisher","DOI":"10.1111\/mafi.v30.4"},{"key":"e_1_3_5_32_1","doi-asserted-by":"crossref","unstructured":"Wang Q. & Zhan Z. (2011). Reinforcement learning model algorithms and its application. In 2011 International Conference on Mechatronic Science Electric Engineering and Computer (MEC) (pp. 1143\u20131146). IEEE.","DOI":"10.1109\/MEC.2011.6025669"},{"key":"e_1_3_5_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.insmatheco.2012.06.002"},{"key":"e_1_3_5_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.insmatheco.2020.02.006"},{"key":"e_1_3_5_35_1","unstructured":"Wiltzer H. E. Meger D. & Bellemare M. G. (2022). Distributional Hamilton-Jacobi-Bellman equations for continuous-time reinforcement learning. In International Conference on Machine Learning (pp. 23832\u201323856). PMLR."},{"key":"e_1_3_5_36_1","doi-asserted-by":"publisher","DOI":"10.1137\/0306023"},{"key":"e_1_3_5_37_1","first-page":"2505","article-title":"Distributionally robust markov decision processes","volume":"23","author":"Xu H.","year":"2010","unstructured":"Xu, H., & Mannor, S. (2010). Distributionally robust markov decision processes. Advances in Neural Information Processing Systems, 23, 2505\u20132513.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_5_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.insmatheco.2005.06.009"},{"key":"e_1_3_5_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.027"},{"key":"e_1_3_5_40_1","doi-asserted-by":"publisher","DOI":"10.1080\/10920277.2004.10596174"},{"key":"e_1_3_5_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s001860050098"},{"key":"e_1_3_5_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.insmatheco.2013.08.004"},{"key":"e_1_3_5_43_1","unstructured":"Ziebart B. D. Maas A. L. Bagnell J. A. & Dey A. K. (2008). Maximum entropy inverse reinforcement learning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 8 pp. 1433\u20131438). AAAI Press."}],"container-title":["International Journal of Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/00207179.2025.2610334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T02:57:34Z","timestamp":1780369054000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/00207179.2025.2610334"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,7]]},"references-count":42,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6,3]]}},"alternative-id":["10.1080\/00207179.2025.2610334"],"URL":"https:\/\/doi.org\/10.1080\/00207179.2025.2610334","relation":{},"ISSN":["0020-7179","1366-5820"],"issn-type":[{"value":"0020-7179","type":"print"},{"value":"1366-5820","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,7]]},"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=tcon20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tcon20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2025-07-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}