{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T19:02:50Z","timestamp":1781550170941,"version":"3.54.5"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T00:00:00Z","timestamp":1669248000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T00:00:00Z","timestamp":1669248000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976174"],"award-info":[{"award-number":["61976174"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s00521-022-08011-9","type":"journal-article","created":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T13:05:36Z","timestamp":1669381536000},"page":"6589-6601","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Multi-agent deep reinforcement learning algorithm with trend consistency regularization for portfolio management"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9367-5685","authenticated-orcid":false,"given":"Cong","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangshe","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongxin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,24]]},"reference":[{"key":"8011_CR1","volume-title":"Portfolio selection: efficient diversification of investments","author":"HM Markovitz","year":"1959","unstructured":"Markowitz HM (1959) Portfolio selection: efficient diversification of investments. John Wiley, New York"},{"issue":"7587","key":"8011_CR2","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison CJ, Guez A, Sifre L, Van Den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M et al (2016) Mastering the game of go with deep neural networks and tree search. Nature 529(7587):484\u2013489","journal-title":"Nature"},{"issue":"7","key":"8011_CR3","doi-asserted-by":"publisher","first-page":"1704","DOI":"10.1109\/TMM.2019.2960636","volume":"22","author":"R Furuta","year":"2019","unstructured":"Furuta R, Inoue N, Yamasaki T (2019) Pixelrl: fully convolutional network with reinforcement learning for image processing. IEEE Trans Multimed 22(7):1704\u20131719","journal-title":"IEEE Trans Multimed"},{"key":"8011_CR4","unstructured":"Gamrian S, Goldberg Y (2019) Transfer learning for related reinforcement learning tasks via image-to-image translation. In: International Conference on Machine Learning, pp 2063\u20132072 . PMLR"},{"key":"8011_CR5","doi-asserted-by":"crossref","unstructured":"Pan B, Yang Y, Zhao Z, Zhuang Y, Cai D, He X (2018) Discourse marker augmented network with reinforcement learning for natural language inference. In: Proceedings of the 56th annual meeting of the association for computational linguistics (volume 1: long papers), pp 989\u2013999","DOI":"10.18653\/v1\/P18-1091"},{"key":"8011_CR6","unstructured":"Zhong V, Xiong C, Socher R (2017) Seq2sql: generating structured queries from natural language using reinforcement learning. arXiv preprint arXiv:1709.00103"},{"key":"8011_CR7","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1016\/j.ins.2018.01.032","volume":"436","author":"H Shi","year":"2018","unstructured":"Shi H, Lin Z, Zhang S, Li X, Hwang K-S (2018) An adaptive decision-making method with fuzzy Bayesian reinforcement learning for robot soccer. Inf Sci 436:268\u2013281","journal-title":"Inf Sci"},{"key":"8011_CR8","doi-asserted-by":"crossref","unstructured":"Johannink T, Bahl S, Nair A, Luo J, Kumar A, Loskyll M, Ojea JA, Solowjow E, Levine S (2019) Residual reinforcement learning for robot control. In: 2019 international conference on robotics and automation (ICRA), pp 6023\u20136029. IEEE","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"8011_CR9","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.neucom.2020.04.070","volume":"402","author":"C Ma","year":"2020","unstructured":"Ma C, Li Z, Lin D, Zhang J (2020) Parallel multi-environment shaping algorithm for complex multi-step task. Neurocomputing 402:323\u2013335","journal-title":"Neurocomputing"},{"key":"8011_CR10","doi-asserted-by":"crossref","unstructured":"Zha D, Lai K.-H, Huang S, Cao Y, Reddy K, Vargas J, Nguyen A, Wei R, Guo J, Hu X (2020) RLCard: a platform for reinforcement learning in card games. In: IJCAI, pp 5264\u20135266","DOI":"10.24963\/ijcai.2020\/764"},{"key":"8011_CR11","doi-asserted-by":"crossref","unstructured":"Liu Y, Liu Q, Zhao H, Pan Z, Liu C (2020) Adaptive quantitative trading: an imitative deep reinforcement learning approach. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 2128\u20132135","DOI":"10.1609\/aaai.v34i02.5587"},{"issue":"23","key":"8011_CR12","doi-asserted-by":"publisher","first-page":"17229","DOI":"10.1007\/s00521-020-05359-8","volume":"32","author":"G Lucarelli","year":"2020","unstructured":"Lucarelli G, Borrotti M (2020) A deep Q-learning portfolio management framework for the cryptocurrency market. Neural Comput Appl 32(23):17229\u201317244","journal-title":"Neural Comput Appl"},{"issue":"5\u20136","key":"8011_CR13","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1002\/(SICI)1099-131X(1998090)17:5\/6<441::AID-FOR707>3.0.CO;2-#","volume":"17","author":"J Moody","year":"1998","unstructured":"Moody J, Wu L, Liao Y, Saffell M (1998) Performance functions and reinforcement learning for trading systems and portfolios. J Forecast 17(5\u20136):441\u2013470","journal-title":"J Forecast"},{"key":"8011_CR14","unstructured":"Gao X, Chan L (2000) An algorithm for trading and portfolio management using q-learning and sharpe ratio maximization. In: Proceedings of the international conference on neural information processing, pp 832\u2013837"},{"key":"8011_CR15","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 (2017) An adaptive portfolio trading system: a risk-return portfolio optimization using recurrent reinforcement learning with expected maximum drawdown. Expert Syst Appl 87:267\u2013279","journal-title":"Expert Syst Appl"},{"key":"8011_CR16","doi-asserted-by":"crossref","unstructured":"Jiang Z, Liang J (2017) Cryptocurrency portfolio management with deep reinforcement learning. In: 2017 intelligent systems conference (IntelliSys), pp 905\u2013913 . IEEE","DOI":"10.1109\/IntelliSys.2017.8324237"},{"key":"8011_CR17","unstructured":"Jiang Z, Xu D, Liang J (2017) A deep reinforcement learning framework for the financial portfolio management problem. arXiv preprint arXiv:1706.10059"},{"key":"8011_CR18","unstructured":"Liang Z, Chen H, Zhu J, Jiang K, Li Y (2018) Adversarial deep reinforcement learning in portfolio management. arXiv preprint arXiv:1808.09940"},{"key":"8011_CR19","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.eswa.2019.04.013","volume":"130","author":"S Almahdi","year":"2019","unstructured":"Almahdi S, Yang SY (2019) A constrained portfolio trading system using particle swarm algorithm and recurrent reinforcement learning. Expert Syst Appl 130:145\u2013156","journal-title":"Expert Syst Appl"},{"key":"8011_CR20","doi-asserted-by":"crossref","unstructured":"Koratamaddi P, Wadhwani K, Gupta M, Sanjeevi DSG (2021) A multi-agent reinforcement learning approach for stock portfolio allocation. In: 8th ACM IKDD CODS and 26th COMAD, pp 410\u2013410","DOI":"10.1145\/3430984.3431045"},{"key":"8011_CR21","doi-asserted-by":"crossref","unstructured":"Lee J, Kim R, Yi SW, Kang J (2020) Maps: multi-agent reinforcement learning-based portfolio management system. In: 29th international joint conference on artificial intelligence, IJCAI 2020, pp 4520\u20134526. International joint conferences on artificial intelligence","DOI":"10.24963\/ijcai.2020\/623"},{"issue":"1","key":"8011_CR22","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s10614-020-10038-w","volume":"57","author":"J Lussange","year":"2021","unstructured":"Lussange J, Lazarevich I, Bourgeois-Gironde S, Palminteri S, Gutkin B (2021) Modelling stock markets by multi-agent reinforcement learning. Comput Econ 57(1):113\u2013147","journal-title":"Comput Econ"},{"issue":"2","key":"8011_CR23","doi-asserted-by":"publisher","first-page":"e0263689","DOI":"10.1371\/journal.pone.0263689","volume":"17","author":"Z Huang","year":"2022","unstructured":"Huang Z, Tanaka F(2022) MSPM: A modularized and scalable multi-agent reinforcement learning-based system for financial portfolio management. Plos one 17(2): e0263689","journal-title":"Plos one"},{"key":"8011_CR24","unstructured":"JoinQuant. https:\/\/www.joinquant.com"},{"issue":"9","key":"8011_CR25","doi-asserted-by":"publisher","first-page":"2480","DOI":"10.1109\/TKDE.2016.2563433","volume":"28","author":"D Huang","year":"2016","unstructured":"Huang D, Zhou J, Li B, Hoi SC, Zhou S (2016) Robust median reversion strategy for online portfolio selection. IEEE Trans Knowl Data Eng 28(9):2480\u20132493","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"8011_CR26","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.artint.2015.01.006","volume":"222","author":"B Li","year":"2015","unstructured":"Li B, Hoi SC, Sahoo D, Liu Z-Y (2015) Moving average reversion strategy for on-line portfolio selection. Artif Intell 222:104\u2013123","journal-title":"Artif Intell"},{"issue":"2","key":"8011_CR27","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s10994-012-5281-z","volume":"87","author":"B Li","year":"2012","unstructured":"Li B, Zhao P, Hoi SC, Gopalkrishnan V (2012) PAMR: passive aggressive mean reversion strategy for portfolio selection. Mach Learn 87(2):221\u2013258","journal-title":"Mach Learn"},{"key":"8011_CR28","doi-asserted-by":"crossref","unstructured":"Shi S, Li J, Li G, Pan P (2019) A multi-scale temporal feature aggregation convolutional neural network for portfolio management. In: Proceedings of the 28th ACM international conference on information and knowledge management, pp 1613\u20131622","DOI":"10.1145\/3357384.3357961"},{"issue":"9","key":"8011_CR29","doi-asserted-by":"publisher","first-page":"7125","DOI":"10.1007\/s00521-021-06853-3","volume":"34","author":"QYE Lim","year":"2022","unstructured":"Lim QYE, Cao Q, Quek C (2022) Dynamic portfolio rebalancing through reinforcement learning. Neural Comput Appl 34(9):7125\u20137139","journal-title":"Neural Comput Appl"},{"key":"8011_CR30","doi-asserted-by":"crossref","unstructured":"Bansal G, Nushi B, Kamar E, Lasecki WS, Weld DS, Horvitz E (2019) Beyond accuracy: the role of mental models in human-AI team performance. In: Proceedings of the AAAI conference on human computation and crowdsourcing, vol 7, pp 2\u201311","DOI":"10.1609\/hcomp.v7i1.5285"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-08011-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-08011-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-08011-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T20:29:19Z","timestamp":1677616159000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-08011-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,24]]},"references-count":30,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["8011"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-08011-9","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,24]]},"assertion":[{"value":"11 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 October 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2022","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 authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human or animal participants"}}]}}