{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T13:46:28Z","timestamp":1761659188675,"version":"build-2065373602"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:00:00Z","timestamp":1761609600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:00:00Z","timestamp":1761609600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Artif Intell"],"DOI":"10.1007\/s44163-025-00547-8","type":"journal-article","created":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T13:42:14Z","timestamp":1761658934000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on the implementation and effectiveness evaluation of deep reinforcement learning algorithms for portfolio optimisation"],"prefix":"10.1007","volume":"5","author":[{"given":"Gao","family":"Yunxiang","sequence":"first","affiliation":[]},{"given":"Tang","family":"Bangying","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,28]]},"reference":[{"key":"547_CR1","doi-asserted-by":"publisher","unstructured":"Wang Z, Schaul T, Hessel M, Hasselt HV, Lanctot M, Silver D. Dueling network architectures for deep reinforcement learning. In: Proceedings of the 33rd international conference on machine learning. 2016. pp. 1995\u20132003. https:\/\/doi.org\/10.48550\/arXiv.1511.06581","DOI":"10.48550\/arXiv.1511.06581"},{"key":"547_CR2","doi-asserted-by":"publisher","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D. Prioritized experience replay. In: Proceedings of the 4th international conference on learning representations (ICLR). 2016. pp. 1\u201321. https:\/\/doi.org\/10.48550\/arXiv.1511.05952","DOI":"10.48550\/arXiv.1511.05952"},{"key":"547_CR3","doi-asserted-by":"publisher","unstructured":"Mnih V, Badia AP, Mirza M, Graves A, Lillicrap T, Harley T, Kavukcuoglu K. Asynchronous methods for deep reinforcement learning. In: Proceedings of the 33rd international conference on machine learning. 2016. pp. 1928\u20131937. https:\/\/doi.org\/10.48550\/arXiv.1602.01783","DOI":"10.48550\/arXiv.1602.01783"},{"issue":"3","key":"547_CR4","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1109\/TNNLS.2016.2522401","volume":"28","author":"D Yue","year":"2017","unstructured":"Yue D, Feng B, Kong Y, Dong N. Deep direct reinforcement learning for financial signal representation and trading. IEEE Trans Neural Netw Learn Syst. 2017;28(3):653\u201364. https:\/\/doi.org\/10.1109\/TNNLS.2016.2522401.","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"547_CR5","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/j.eswa.2017.06.023","volume":"87","author":"S Almahdi","year":"2017","unstructured":"Almahdi S, Yang SY. An adaptive portfolio trading system: a risk-return portfolio optimization using recurrent reinforcement learning with expected maximum drawdown. Expert Syst Appl. 2017;87:267\u201379. https:\/\/doi.org\/10.1016\/j.eswa.2017.06.023.","journal-title":"Expert Syst Appl"},{"key":"547_CR6","doi-asserted-by":"publisher","unstructured":"Xiong Z, Liu XY, Shan Z, Zhang Y. Practical deep reinforcement learning approach for stock trading. 2018. arXiv preprint arXiv:1811.07522. https:\/\/doi.org\/10.48550\/arXiv.1811.07522","DOI":"10.48550\/arXiv.1811.07522"},{"issue":"8","key":"547_CR7","doi-asserted-by":"publisher","first-page":"1271","DOI":"10.1080\/14697688.2019.1571683","volume":"19","author":"H Buehler","year":"2019","unstructured":"Buehler H, Gonon L, Teichmann J, Wood B. Deep hedging. Quant Finance. 2019;19(8):1271\u201391. https:\/\/doi.org\/10.1080\/14697688.2019.1571683.","journal-title":"Quant Finance"},{"key":"547_CR8","doi-asserted-by":"publisher","unstructured":"Gao Z, Gao Y, Hu Y, Wang X. Application of deep Q-network in portfolio management. In: Proceedings of the 5th IEEE international conference on big data analytics. 2020. pp. 268\u2013275. https:\/\/doi.org\/10.1109\/ICBDA49040.2020.9101278","DOI":"10.1109\/ICBDA49040.2020.9101278"},{"key":"547_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ACCESS.2021.3050173","volume":"9","author":"DY Park","year":"2021","unstructured":"Park DY, Lee KH. Practical algorithmic trading using state representation learning and imitative reinforcement learning. IEEE Access. 2021;9:1\u20131. https:\/\/doi.org\/10.1109\/ACCESS.2021.3050173.","journal-title":"IEEE Access"},{"issue":"1","key":"547_CR10","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1609\/aaai.v35i1.16117","volume":"35","author":"Z Wang","year":"2021","unstructured":"Wang Z, Huang B, Tu S, Liu Z. Deeptrader: a deep reinforcement learning approach for risk-return balanced portfolio management with market conditions embedding. Proc AAAI Conf Artif Intell. 2021;35(1):643\u201350. https:\/\/doi.org\/10.1609\/aaai.v35i1.16117.","journal-title":"Proc AAAI Conf Artif Intell"},{"issue":"1","key":"547_CR11","doi-asserted-by":"publisher","first-page":"335","DOI":"10.30574\/ijsra.2022.6.1.0131","volume":"6","author":"M Faheem","year":"2022","unstructured":"Faheem M, Aslam M, Kakolu S. Artificial intelligence in investment portfolio optimization: a comparative study of machine learning algorithms. Int J Sci Res Arch. 2022;6(1):335\u201342.","journal-title":"Int J Sci Res Arch"},{"issue":"5","key":"547_CR12","doi-asserted-by":"publisher","first-page":"3847","DOI":"10.1007\/s10462-022-10235-5","volume":"56","author":"A Gunjan","year":"2023","unstructured":"Gunjan A, Bhattacharyya S. A brief review of portfolio optimization techniques. Artif Intell Rev. 2023;56(5):3847\u201386. https:\/\/doi.org\/10.1007\/s10462-022-10235-5.","journal-title":"Artif Intell Rev"},{"issue":"9","key":"547_CR13","doi-asserted-by":"publisher","first-page":"7125","DOI":"10.1007\/s00521-021-06198-2","volume":"34","author":"QYE Lim","year":"2022","unstructured":"Lim QYE, Cao Q, Quek C. Dynamic portfolio rebalancing through reinforcement learning. Neural Comput Appl. 2022;34(9):7125\u201339. https:\/\/doi.org\/10.1007\/s00521-021-06198-2.","journal-title":"Neural Comput Appl"},{"key":"547_CR14","doi-asserted-by":"publisher","first-page":"93564","DOI":"10.1109\/ACCESS.2022.3204042","volume":"10","author":"T Kabbani","year":"2022","unstructured":"Kabbani T, Duman E. Deep reinforcement learning approach for trading automation in the stock market. IEEE Access. 2022;10:93564\u201374. https:\/\/doi.org\/10.1109\/ACCESS.2022.3204042.","journal-title":"IEEE Access"},{"issue":"6","key":"547_CR15","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1080\/14697688.2021.2011279","volume":"22","author":"AM Aboussalah","year":"2022","unstructured":"Aboussalah AM, Xu Z, Lee CG. What is the value of the cross-sectional approach to deep reinforcement learning? Quant Financ. 2022;22(6):1091\u2013111. https:\/\/doi.org\/10.1080\/14697688.2021.2011279.","journal-title":"Quant. Financ"},{"issue":"4","key":"547_CR16","doi-asserted-by":"publisher","first-page":"848","DOI":"10.1016\/j.jestch.2020.11.011","volume":"24","author":"P Koratamaddi","year":"2021","unstructured":"Koratamaddi P, Wadhwani K, Gupta M, Sanjeevi SG. Market sentiment-aware deep reinforcement learning approach for stock portfolio allocation. Eng Sci Technol Int J. 2021;24(4):848\u201359. https:\/\/doi.org\/10.1016\/j.jestch.2020.11.011.","journal-title":"Eng Sci Technol Int J"},{"key":"547_CR17","doi-asserted-by":"publisher","unstructured":"Guan M, Liu XY. Explainable deep reinforcement learning for portfolio management: an empirical approach. In: Proceedings of the second ACM international conference on AI in finance. 2021. pp. 1\u20139. https:\/\/doi.org\/10.1145\/3490354.3494363","DOI":"10.1145\/3490354.3494363"},{"issue":"11","key":"547_CR18","doi-asserted-by":"publisher","first-page":"8119","DOI":"10.1007\/s10489-021-02277-9","volume":"51","author":"ME Wu","year":"2021","unstructured":"Wu ME, Syu JH, Lin JCW, Lin YT. Portfolio management system in equity market neutral using reinforcement learning. Appl Intell. 2021;51(11):8119\u201331. https:\/\/doi.org\/10.1007\/s10489-021-02277-9.","journal-title":"Appl Intell"},{"key":"547_CR19","doi-asserted-by":"publisher","unstructured":"Liu XY, Yang H, Gao J, Wang CD. FinRL: deep reinforcement learning framework to automate trading in quantitative finance. In: Proceedings of the second ACM international conference on AI in finance. 2021. pp. 1\u20139. https:\/\/doi.org\/10.1145\/3490354.3494366","DOI":"10.1145\/3490354.3494366"},{"issue":"3","key":"547_CR20","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1108\/JM2-10-2020-0259","volume":"17","author":"MAM Al Janabi","year":"2022","unstructured":"Al Janabi MAM. Optimization algorithms and investment portfolio analytics with machine learning techniques under time-varying liquidity constraints. J Model Manag. 2022;17(3):864\u201395. https:\/\/doi.org\/10.1108\/JM2-10-2020-0259.","journal-title":"J Model Manag"}],"container-title":["Discover Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-025-00547-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44163-025-00547-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-025-00547-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T13:42:15Z","timestamp":1761658935000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44163-025-00547-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,28]]},"references-count":20,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["547"],"URL":"https:\/\/doi.org\/10.1007\/s44163-025-00547-8","relation":{},"ISSN":["2731-0809"],"issn-type":[{"value":"2731-0809","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,28]]},"assertion":[{"value":"25 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The Study was approved by the Strategic Assessments and Consultation Institute.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human participants"}},{"value":"The authors declare no competing interests.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"291"}}