{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T22:40:17Z","timestamp":1769294417509,"version":"3.49.0"},"reference-count":39,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T00:00:00Z","timestamp":1768089600000},"content-version":"vor","delay-in-days":10,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFA1008903"],"award-info":[{"award-number":["2023YFA1008903"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12271303"],"award-info":[{"award-number":["12271303"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Concurrency and Computation"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Financial markets exhibit high levels of non\u2010stationarity and structural heterogeneity, which pose significant challenges to reinforcement learning (RL)\u2010based portfolio optimization methods. To address these challenges, this paper proposes a Structure\u2010Aware Deep Reinforcement Learning (SADRL) framework for cross\u2010market portfolio optimization. The proposed framework explicitly models market structural dynamics through a structure encoder that identifies latent market regimes, while a policy learner adapts investment strategies accordingly. This dual\u2010level learning mechanism enables the model to generalize across heterogeneous markets and remain stable under regime shifts. Extensive experiments on multiple cross\u2010market datasets demonstrate that SADRL achieves superior risk\u2010adjusted returns and improved robustness compared with conventional RL\u2010based baselines. These findings highlight the potential of structure\u2010aware learning for developing intelligent and adaptive decision\u2010making systems in financial markets.<\/jats:p>","DOI":"10.1002\/cpe.70540","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T05:55:49Z","timestamp":1768197349000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross\u2010Market Portfolio Optimization via Structure\u2010Aware Deep Reinforcement Learning"],"prefix":"10.1002","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1059-4162","authenticated-orcid":false,"given":"Yiliang","family":"Qiao","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics, Qilu University of Technology (Shandong Academy of Sciences)  Jinan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9823-7031","authenticated-orcid":false,"given":"Yan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Geotechnical and Structural Research Center Shandong University  Jinan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8349-1674","authenticated-orcid":false,"given":"Xu","family":"Guo","sequence":"additional","affiliation":[{"name":"Geotechnical and Structural Research Center Shandong University  Jinan China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,1,11]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9230-7_2"},{"key":"e_1_2_11_3_1","doi-asserted-by":"crossref","unstructured":"A.Alameer H.Saleh andK.Alshehri \u201cReinforcement Learning in Quantitative Trading: A Survey \u201d2022 Authorea https:\/\/doi.org\/10.36227\/techrxiv.19303853.v1.","DOI":"10.36227\/techrxiv.19303853"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.22214\/ijraset.2023.50170"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21196571"},{"key":"e_1_2_11_6_1","volume-title":"World Scientific Reference on Contingent Claims Analysis in Corporate Finance","author":"Black F.","year":"2018"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1093\/rfs\/6.2.327"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2022.111896"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41109\u2010017\u20100031\u20106"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2014.946660"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.3390\/jrfm16020111"},{"key":"e_1_2_11_12_1","unstructured":"J.Hwang \u201cModeling Financial Time Series Using LSTM With Trainable Initial Hidden States \u201d2020 arXiv https:\/\/doi.org\/10.48550\/arXiv.2007.06848."},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1057\/s41599\u2010023\u201002042\u2010w"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-84460-7_33"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4375798"},{"key":"e_1_2_11_16_1","unstructured":"H.Emami X.\u2010H.Dang Y.Shah andP.Zerfos \u201cModality\u2010Aware Transformer for Financial Time Series Forecasting \u201d2024 arXiv:2310.01232 https:\/\/doi.org\/10.48550\/arXiv.2310.01232."},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.935097"},{"key":"e_1_2_11_18_1","unstructured":"Z.Jiang D.Xu andJ.Liang \u201cA Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem \u201d2017 arXiv https:\/\/doi.org\/10.48550\/arXiv.1706.10059."},{"key":"e_1_2_11_19_1","unstructured":"Z.Liang H.Chen J.Zhu K.Jiang andY.Li \u201cAdversarial Deep Reinforcement Learning in Portfolio Management \u201d2018 arXiv.Org https:\/\/arxiv.org\/abs\/1808.09940v3."},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.06.023"},{"key":"e_1_2_11_21_1","unstructured":"R.Wang H.Wei B.An Z.Feng andJ.Yao \u201cDeep Stock Trading: A Hierarchical Reinforcement Learning Framework for Portfolio Optimization and Order Execution \u201d2021 arXiv:2012.12620 https:\/\/doi.org\/10.48550\/arXiv.2012.12620."},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.3934\/era.2024239"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.3390\/a17120570"},{"key":"e_1_2_11_24_1","unstructured":"X.\u2010Y.Liu Z.Xiong S.Zhong H.Yang andA.Walid \u201cPractical Deep Reinforcement Learning Approach for Stock Trading \u201d2022 arXiv https:\/\/doi.org\/10.48550\/arXiv.1811.07522."},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2013.814923"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.2307\/1912559"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.matcom.2022.09.006"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1142\/S021902491100653X"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121502"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004\u20103702(98)00023\u2010X"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.3905\/jpm.2010.36.4.060"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1111\/jofi.12080"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1111\/mafi.12382"},{"key":"e_1_2_11_34_1","unstructured":"A.Vaswani N.Shazeer N.Parmar et al. \u201cAttention Is All You Need \u201d2017 Advances in Neural Information Processing Systems 30 https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa\u2010Abstract.html."},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2021.03.012"},{"key":"e_1_2_11_36_1","unstructured":"Y.Nie N. H.Nguyen P.Sinthong andJ.Kalagnanam \u201cA Time Series Is Worth 64 Words: Long\u2010Term Forecasting With Transformers \u201d2023 arXiv:2211.14730 https:\/\/doi.org\/10.48550\/arXiv.2211.14730."},{"key":"e_1_2_11_37_1","unstructured":"Y.ZhangandJ.Yan \u201cCrossformer: Transformer Utilizing Cross\u2010Dimension Dependency for Multivariate Time Series Forecasting \u201dinThe Eleventh International Conference on Learning Representations September 29 2022 https:\/\/openreview.net\/forum?id=vSVLM2j9eie."},{"key":"e_1_2_11_38_1","unstructured":"S.Fujimoto H.Hoof andD.Meger \u201cAddressing Function Approximation Error in Actor\u2010Critic Methods \u201dinProceedings of the 35th International Conference on Machine Learning July 3 2018 1587\u201396 https:\/\/proceedings.mlr.press\/v80\/fujimoto18a.html."},{"key":"e_1_2_11_39_1","unstructured":"M.Jaderberg V.Mnih W. M.Czarnecki et al. \u201cReinforcement Learning With Unsupervised Auxiliary Tasks \u201d2016 arXiv:1611.05397 https:\/\/doi.org\/10.48550\/arXiv.1611.05397."},{"key":"e_1_2_11_40_1","unstructured":"T. P.Lillicrap J. J.Hunt A.Pritzel et al. \u201cContinuous Control With Deep Reinforcement Learning \u201d2019 arXiv:1509.02971 https:\/\/doi.org\/10.48550\/arXiv.1509.02971."}],"container-title":["Concurrency and Computation: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70540","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/cpe.70540","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T12:29:07Z","timestamp":1769171347000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.70540"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":39,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1002\/cpe.70540"],"URL":"https:\/\/doi.org\/10.1002\/cpe.70540","archive":["Portico"],"relation":{},"ISSN":["1532-0626","1532-0634"],"issn-type":[{"value":"1532-0626","type":"print"},{"value":"1532-0634","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-10-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70540"}}