{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:37:31Z","timestamp":1742913451071,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030968953"},{"type":"electronic","value":"9783030968960"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-96896-0_21","type":"book-chapter","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T12:16:52Z","timestamp":1657196212000},"page":"467-482","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Federated Reinforcement Learning for Portfolio Management"],"prefix":"10.1007","author":[{"given":"Pengqian","family":"Yu","sequence":"first","affiliation":[]},{"given":"Laura","family":"Wynter","sequence":"additional","affiliation":[]},{"given":"Shiau Hong","family":"Lim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,8]]},"reference":[{"key":"21_CR1","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":"21_CR2","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1613\/jair.1491","volume":"22","author":"R Begleiter","year":"2004","unstructured":"Begleiter R, El-Yaniv R, Yona G (2004) On prediction using variable order Markov models. J Artif Intell Res 22:385\u2013421","journal-title":"J Artif Intell Res"},{"key":"21_CR3","first-page":"359","volume":"10","author":"DJ Berndt","year":"1994","unstructured":"Berndt DJ, Clifford J (1994) Using dynamic time warping to find patterns in time series. In: KDD workshop, Seattle, vol 10, pp 359\u2013370","journal-title":"KDD workshop, Seattle, vol"},{"issue":"3","key":"21_CR4","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1086\/260062","volume":"81","author":"F Black","year":"1973","unstructured":"Black F, Scholes M (1973) The pricing of options and corporate liabilities. J Polit Econ 81(3):637\u2013654","journal-title":"J Polit Econ"},{"issue":"8","key":"21_CR5","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 (2019) Deep hedging. Quant Financ 19(8):1271\u20131291","journal-title":"Quant Financ"},{"key":"21_CR6","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, pp 2672\u20132680"},{"key":"21_CR7","unstructured":"Haugen RA, Haugen RA (2001) Modern investment theory, vol 5. Prentice Hall, Upper Saddle River"},{"key":"21_CR8","unstructured":"Jiang Z, Xu D, Liang J (2017) A deep reinforcement learning framework for the financial portfolio management problem. arXiv preprint arXiv:170610059"},{"key":"21_CR9","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/978-1-4419-9230-7_2","volume-title":"Asset pricing","author":"T Kariya","year":"2003","unstructured":"Kariya T, Liu RY (2003) Options, futures and other derivatives. In: Asset pricing. Springer, Boston, MA, pp 9\u201326"},{"key":"21_CR10","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"key":"21_CR11","first-page":"429","volume":"2","author":"T Li","year":"2020","unstructured":"Li T, Sahu AK, Zaheer M, Sanjabi M, Talwalkar A, Smith V (2020) Federated optimization in heterogeneous networks. Proc Mach Learn Syst 2:429\u2013450","journal-title":"Proc Mach Learn Syst"},{"key":"21_CR12","volume-title":"Portfolio selection: efficient diversification of investments","author":"H Markowitz","year":"1959","unstructured":"Markowitz H (1959) Portfolio selection: efficient diversification of investments, vol 16. Wiley, New York"},{"key":"21_CR13","unstructured":"McMahan B, Moore E, Ramage D, Hampson S, y Arcas BA (2017) Communication-efficient learning of deep networks from decentralized data. In: Artificial intelligence and statistics. PMLR, pp 1273\u20131282"},{"key":"21_CR14","unstructured":"Pillutla K, Kakade SM, Harchaoui Z (2019) Robust aggregation for federated learning. arXiv preprint arXiv:191213445"},{"issue":"1","key":"21_CR15","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1086\/294846","volume":"39","author":"WF Sharpe","year":"1966","unstructured":"Sharpe WF (1966) Mutual fund performance. J Bus 39(1):119\u2013138","journal-title":"J Bus"},{"key":"21_CR16","unstructured":"Silver D, Lever G, Heess N, Degris T, Wierstra D, Riedmiller M (2014) Deterministic policy gradient algorithms. In: Proceedings of the 31st international conference on international conference on machine learning \u2013 JMLR.org, ICML\u201914, vol 32, pp I\u2013387\u2013I\u2013395"},{"key":"21_CR17","unstructured":"Sutton RS, McAllester DA, Singh SP, Mansour Y (2000) Policy gradient methods for reinforcement learning with function approximation. In: Advances in neural information processing systems, pp 1057\u20131063"},{"key":"21_CR18","doi-asserted-by":"publisher","first-page":"1112","DOI":"10.1609\/aaai.v34i01.5462","volume":"34","author":"Y Ye","year":"2020","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, pp 1112\u20131119","journal-title":"Proceedings of the AAAI conference on artificial intelligence, vol"},{"key":"21_CR19","unstructured":"Yin D, Chen Y, Kannan R, Bartlett P (2018) Byzantine-robust distributed learning: towards optimal statistical rates. PMLR, Stockholmsm\u00e4ssan, Stockholm, vol 80. Proceedings of Machine Learning Research, pp 5650\u20135659. http:\/\/proceedings.mlr.press\/v80\/yin18a.html"}],"container-title":["Federated Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-96896-0_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T12:30:19Z","timestamp":1657197019000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-96896-0_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030968953","9783030968960"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-96896-0_21","relation":{},"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"8 February 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}