{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:24:54Z","timestamp":1775503494571,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T00:00:00Z","timestamp":1745539200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T00:00:00Z","timestamp":1745539200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s10489-025-06423-3","type":"journal-article","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T00:08:50Z","timestamp":1745539730000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An adaptive quantitative trading strategy optimization framework based on meta reinforcement learning and cognitive game theory"],"prefix":"10.1007","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5500-3311","authenticated-orcid":false,"given":"Zhiheng","family":"Shen","sequence":"first","affiliation":[]},{"given":"Hanchi","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"key":"6423_CR1","doi-asserted-by":"crossref","unstructured":"Nevmyvaka Y, Feng Y, Kearns M (2006) Reinforcement learning for optimized trade execution. In: Proceedings of the 23rd international conference on machine learning, pp 673\u2013680","DOI":"10.1145\/1143844.1143929"},{"key":"6423_CR2","doi-asserted-by":"crossref","unstructured":"Hendricks D, Wilcox D (2014) A reinforcement learning extension to the Almgren-Chriss framework for optimal trade execution. In: Proceedings of the 2014 IEEE conference on computational intelligence for financial engineering & economics, IEEE, pp 457\u2013464","DOI":"10.1109\/CIFEr.2014.6924109"},{"key":"6423_CR3","unstructured":"Bacoyannis V, Glukhov V, Jin T, Kochems J, Song DR (2018) Idiosyncrasies and challenges of data driven learning in electronic trading. In: IEEE International Conference on Data Mining Workshops (ICDMW), IEEE, pp 147\u2013154"},{"key":"6423_CR4","unstructured":"Wei J, Wang J, Yuan Y (2019) Robust deep reinforcement learning for optimal order execution. arXiv:1912.08394"},{"key":"6423_CR5","unstructured":"Ning B, Lin FHT, Jaimungal S (2018) Double deep Q-learning for optimal execution. arXiv:1812.06600"},{"key":"6423_CR6","doi-asserted-by":"crossref","unstructured":"Liu X, Liang Y, Wang H, Yang Z, Liu W (2020) Adaptive quantitative trading: An imitative deep reinforcement learning approach. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, no 02, pp 2128\u20132135","DOI":"10.1609\/aaai.v34i02.5587"},{"issue":"1","key":"6423_CR7","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1007\/s00191-015-0418-4","volume":"26","author":"SJ Leal","year":"2016","unstructured":"Leal SJ, Napoletano M, Roventini A, Fagiolo G (2016) Rock around the clock: An agent-based model of low-and high-frequency trading. J Evol Econ 26(1):49\u201376","journal-title":"J Evol Econ"},{"key":"6423_CR8","doi-asserted-by":"crossref","unstructured":"Vyetrenko S, Xu S, Likhomanenko T, Keenan G, Begoli E (2020) Get real: Realism metrics for robust limit order book market simulations. arXiv:2002.02013","DOI":"10.1145\/3383455.3422561"},{"key":"6423_CR9","unstructured":"Vyetrenko S, Byrd D, Petosa N, Mahfouz M, Dervovic D, Veloso M, Balch TH (2019) Adversarial deep reinforcement learning in portfolio management. arXiv:1907.02046"},{"key":"6423_CR10","doi-asserted-by":"crossref","first-page":"1288","DOI":"10.1016\/j.procs.2020.04.034","volume":"171","author":"A Shrivastava","year":"2020","unstructured":"Shrivastava A, Xu Y, Jiang Z, Li P, Xu H (2020) An intelligent trading algorithm based on deep reinforcement learning. Procedia Comput Sci 171:1288\u20131299","journal-title":"Procedia Comput Sci"},{"key":"6423_CR11","unstructured":"Karpe A, Kalghatgi S, Jain R, Gujar S (2020) Fast and sample-efficient learning in continuous games with self-play. arXiv:2002.08876"},{"key":"6423_CR12","unstructured":"Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Amodei D (2020) Language models are few-shot learners. arXiv:2005.14165"},{"issue":"10","key":"6423_CR13","doi-asserted-by":"publisher","first-page":"1640","DOI":"10.3390\/math8101640","volume":"8","author":"A Mosavi","year":"2020","unstructured":"Mosavi A, Faghan Y, Ghamisi P, Duan P, Ardabili SF, Salwana E, Shamshirband S (2020) Comprehensive review of deep reinforcement learning methods and applications in economics. Mathematics 8(10):1640","journal-title":"Mathematics"},{"key":"6423_CR14","doi-asserted-by":"crossref","unstructured":"Charpentier A, Elie R, Remlinger C (2021) Reinforcement learning in economics and finance. Comput Econ:1\u201338","DOI":"10.1007\/s10614-021-10119-4"},{"key":"6423_CR15","unstructured":"Ganesh S, Vadori N, Xu M, Zheng H, Reddy P, Veloso M (2019) Reinforcement learning for market making in a multi-agent dealer market. arXiv:1911.05892"},{"key":"6423_CR16","doi-asserted-by":"crossref","unstructured":"Yu T, Quillen D, He Z, Julian R, Hausman K, Finn C, Levine S (2018) One-shot imitation from observing humans via domain-adaptive meta-learning. arXiv:1802.01557","DOI":"10.15607\/RSS.2018.XIV.002"},{"key":"6423_CR17","unstructured":"Cai X, Hu Z, Zhou Q, Pan G (2019) An effective multi-agent meta-reinforcement learning framework for robust trading strategy adaptation. arXiv:1911.03916"},{"key":"6423_CR18","unstructured":"Charpentier A, Elie R, Remlinger C (2021) Multi-task and multi-agent meta reinforcement learning for a trading model. arXiv:2102.08791"},{"key":"6423_CR19","unstructured":"Wang JX, Kurth-Nelson Z, Tirumala D, Soyer H, Leibo JZ, Munos R, Botvinick M (2016) Learning to reinforcement learn. arXiv:1611.05763"},{"key":"6423_CR20","unstructured":"Duan Y, Schulman J, Chen X, Bartlett PL, Sutskever I, Abbeel P (2016) RL$$^2$$: Fast reinforcement learning via slow reinforcement learning. arXiv:1611.02779"},{"key":"6423_CR21","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the 34th international conference on machine learning, PMLR, pp 1126-1135"},{"key":"6423_CR22","unstructured":"Nichol A, Achiam J, Schulman J (2018) On first-order meta-learning algorithms. arXiv:1803.02999"},{"key":"6423_CR23","unstructured":"Li Z, Zhou F, Chen F, Li H (2017) Meta-SGD: learning to learn quickly for few-shot learning. arXiv:1707.09835"},{"key":"6423_CR24","unstructured":"Lanctot M, Zambaldi V, Gruslys A, Lazaridou A, Perolat J, Silver D, Graepel T (2017) A unified game-theoretic approach to multiagent reinforcement learning. In: Advances in neural information processing systems, pp 4190\u20134203"},{"key":"6423_CR25","unstructured":"Shen Y, Li Y, Zhang T, Zheng G, Gong Y, Zhang W (2020) Go-explore: a simple and effective approach for discovering diverse and high-performing strategies in reinforcement learning. arXiv:2006.10720"},{"key":"6423_CR26","unstructured":"Srinivasan S, Lanctot M, Zambaldi V, P\u00e9rolat J, Tuyls K, Munos R, Bowling M (2018) Actor-critic policy optimization in partially observable multiagent environments. In: Advances in neural information processing systems, pp 3422\u20133435"},{"key":"6423_CR27","unstructured":"Chen G, Peng P, Zhang G, Ye J (2020) Learning to identify high-quality advice for multi-agent reinforcement learning. arXiv:2005.07862"},{"key":"6423_CR28","doi-asserted-by":"crossref","unstructured":"Zheng G, Zhang F, Zheng Z, Xiang Y, Yuan NJ, Xie X, Li Z (2018) DRN: a deep reinforcement learning framework for news recommendation. In: Proceedings of the 2018 world wide web conference, pp 167\u2013176","DOI":"10.1145\/3178876.3185994"},{"issue":"1","key":"6423_CR29","doi-asserted-by":"publisher","first-page":"9","DOI":"10.3390\/asi4010009","volume":"4","author":"Z Hu","year":"2020","unstructured":"Hu Z, Zhao Y, Khushi M (2020) A survey of forex and stock price prediction using deep learning. Appl Syst Innovation 4(1):9","journal-title":"Appl Syst Innovation"},{"key":"6423_CR30","unstructured":"Yang S, Yu Y, Zhou Z (2019) Evolving trading rules using genetic programming for portfolio optimization. Comput Econ:1\u201319"},{"key":"6423_CR31","unstructured":"Colby MK, Kharaghani S, HajiGhassemi O, Tumer K (2021) Generating diverse strategies for portfolio optimization: reinforcement learning with ensemble sampling. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, no 1, pp 34\u201341"},{"key":"6423_CR32","doi-asserted-by":"crossref","unstructured":"Ye Y, Pei H, Wang B, Chen PY, Zhu Y, Xiao J, Li B (2020) Reinforcement-learning based portfolio management with augmented asset movement prediction states. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, no 01, pp 1112\u20131119","DOI":"10.1609\/aaai.v34i01.5462"},{"key":"6423_CR33","unstructured":"Xiong Z, Liu XY, Zhong S, Yang H, Walid A (2018) Practical deep reinforcement learning approach for stock trading. arXiv:1811.07522"},{"key":"6423_CR34","doi-asserted-by":"publisher","first-page":"112891","DOI":"10.1016\/j.eswa.2019.112891","volume":"140","author":"AM Aboussalah","year":"2020","unstructured":"Aboussalah AM, Lee CG (2020) Continuous control with stacked deep dynamic recurrent reinforcement learning for portfolio optimization. Expert Syst Appl 140:112891","journal-title":"Expert Syst Appl"},{"key":"6423_CR35","unstructured":"Jian P, Zhang S, Zhou X (2020) Multi-agent reinforcement learning for portfolio management with liquidity risk. In: Proceedings of the first ACM international conference on AI in finance, pp 1\u20139"},{"key":"6423_CR36","unstructured":"Jiang Z, Xu D, Liang J (2017) A deep reinforcement learning framework for the financial portfolio management problem. arXiv:1706.10059"},{"key":"6423_CR37","unstructured":"Huang CY (2020) A deep reinforcement learning approach for stock selection. arXiv:2010.12950"},{"issue":"1","key":"6423_CR38","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1006\/game.1995.1023","volume":"10","author":"RD McKelvey","year":"1995","unstructured":"McKelvey RD, Palfrey TR (1995) Quantal response equilibria for normal form games. Games Econom Behav 10(1):6\u201338","journal-title":"Games Econom Behav"},{"key":"6423_CR39","unstructured":"Sokolov A, Hillebrand M (2021) Automating market making using deep reinforcement learning with real market data. arXiv:2102.06988"},{"issue":"2","key":"6423_CR40","doi-asserted-by":"publisher","first-page":"25","DOI":"10.3905\/jfds.2020.1.030","volume":"2","author":"Z Zhang","year":"2020","unstructured":"Zhang Z, Zohren S, Roberts S (2020) Deep reinforcement learning for trading. J Financial Data Sci 2(2):25\u201340","journal-title":"J Financial Data Sci"},{"issue":"3","key":"6423_CR41","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/s11002-014-9316-z","volume":"25","author":"A De Palma","year":"2014","unstructured":"De Palma A, Abdellaoui M, Attanasi G, Ben-Akiva M, Erev I, Fehr-Duda H, Walker J (2014) Beware of black swans: Taking stock of the description-experience gap in decision under uncertainty. Mark Lett 25(3):269\u2013280","journal-title":"Mark Lett"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06423-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06423-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06423-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T13:57:38Z","timestamp":1758290258000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06423-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,25]]},"references-count":41,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["6423"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06423-3","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,25]]},"assertion":[{"value":"2 March 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2025","order":2,"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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}},{"value":"The data used in this study is from a publicly available dataset that requires a fee for access. The authors have obtained the necessary permissions and licenses to use the data for research purposes. No additional ethical approval or informed consent was required.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and Informed Consent for Data Used"}}],"article-number":"689"}}