{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T03:40:18Z","timestamp":1743565218863,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":17,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819646029","type":"print"},{"value":"9789819646036","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-4603-6_11","type":"book-chapter","created":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T03:18:14Z","timestamp":1743563894000},"page":"125-136","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Twin-Based Reinforcement Learning for\u00a0Solving Multi-period Portfolio Optimization Problem"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0402-2432","authenticated-orcid":false,"given":"Phuc Tan","family":"Huynh","sequence":"first","affiliation":[]},{"given":"Trang Hong","family":"Son","sequence":"additional","affiliation":[]},{"given":"Khoa D.","family":"Vo","sequence":"additional","affiliation":[]},{"given":"Nguyen","family":"Huynh-Tuong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,24]]},"reference":[{"issue":"1","key":"11_CR1","first-page":"77","volume":"7","author":"H Markowitz","year":"1952","unstructured":"Markowitz, H.: Portfolio selection. J. Finan. 7(1), 77\u201391 (1952)","journal-title":"J. Finan."},{"issue":"5","key":"11_CR2","doi-asserted-by":"publisher","first-page":"28","DOI":"10.2469\/faj.v48.n5.28","volume":"48","author":"F Black","year":"1992","unstructured":"Black, F., Litterman, R.: Global portfolio optimization. Finan. Anal. J. 48(5), 28\u201343 (1992)","journal-title":"Finan. Anal. J."},{"issue":"3","key":"11_CR3","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1111\/1467-9965.00100","volume":"10","author":"D Li","year":"2000","unstructured":"Li, D., Ng, W.-L.: Optimal dynamic portfolio selection: multiperiod mean- variance formulation. Math. Finan. 10(3), 387\u2013406 (2000)","journal-title":"Math. Finan."},{"issue":"2","key":"11_CR4","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1016\/j.ejor.2016.10.031","volume":"259","author":"C Krauss","year":"2017","unstructured":"Krauss, C., Do, X.A., Huck, N.: Deep neural networks, gradient-boosted trees, random forests: statistical arbitrage on the s &p 500. Eur. J. Oper. Res. 259(2), 689\u2013702 (2017)","journal-title":"Eur. J. Oper. Res."},{"issue":"4","key":"11_CR5","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1109\/72.935097","volume":"12","author":"J Moody","year":"2001","unstructured":"Moody, J., Saffell, M.: Learning to trade via direct reinforcement. IEEE Trans. Neural Netw. 12(4), 875\u2013889 (2001)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"3","key":"11_CR6","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1109\/TNNLS.2016.2522401","volume":"28","author":"Y Deng","year":"2017","unstructured":"Deng, Y., Bao, F., Kong, Y., Ren, Z., Dai, Q.: Deep direct reinforcement learning for financial signal representation and trading. IEEE Trans. Neural Netw. Learn. Syst. 28(3), 653\u2013664 (2017)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"11_CR7","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, S.Y.: An adaptive portfolio trading system: a risk-return portfolio optimization using recurrent reinforcement learning with expected maximum drawdown. Expert Syst. Appl. 87, 267\u2013279 (2017)","journal-title":"Expert Syst. Appl."},{"key":"11_CR8","unstructured":"Jiang, Z., Xu, D., Liang, J.: A deep reinforcement learning framework for the financial portfolio management problem (2017). https:\/\/arxiv.org\/abs\/1706.10059"},{"key":"11_CR9","first-page":"138223","volume":"8","author":"Y Ye","year":"2020","unstructured":"Ye, Y., Shen, Y., Xu, D.: A proximal policy optimization approach for deep reinforcement learning in financial portfolio management. IEEE Access 8, 138223\u2013138234 (2020)","journal-title":"IEEE Access"},{"key":"11_CR10","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. CoRR arxiv:1707.06347 (2017)"},{"key":"11_CR11","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of the 33rd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 48, pp. 1928\u20131937. PMLR, New York (2016). https:\/\/proceedings.mlr.press\/v48\/mniha16.html"},{"key":"11_CR12","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. CoRR arxiv:1801.01290 (2018)"},{"key":"11_CR13","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. CoRR arxiv:1802.09477 (2018)"},{"key":"11_CR14","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. MIT Press, Cambridge (2018)","edition":"2"},{"issue":"8","key":"11_CR15","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1073\/pnas.38.8.716","volume":"38","author":"R Bellman","year":"1952","unstructured":"Bellman, R.: On the theory of dynamic programming. Proc. Natl. Acad. Sci. USA 38(8), 716\u2013719 (1952)","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"11_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111233","volume":"152","author":"NHL Kan","year":"2024","unstructured":"Kan, N.H.L., Cao, Q., Quek, C.: Learning and processing framework using fuzzy deep neural network for trading and portfolio rebalancing. Appl. Soft Comput. 152, 111233 (2024)","journal-title":"Appl. Soft Comput."},{"issue":"3","key":"11_CR17","doi-asserted-by":"publisher","first-page":"59","DOI":"10.3905\/joi.3.3.59","volume":"3","author":"FA Sortino","year":"1994","unstructured":"Sortino, F.A., Price, L.N.: Performance measurement in a downside risk framework. J. Invest. 3(3), 59\u201364 (1994)","journal-title":"J. Invest."}],"container-title":["Lecture Notes in Computer Science","Integrated Uncertainty in Knowledge Modelling and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-4603-6_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T03:18:33Z","timestamp":1743563913000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-4603-6_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819646029","9789819646036"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-4603-6_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"\u2013 Conflict of interest\/competing interests: none.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"IUKM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ho Chi Minh City","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 March 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 March 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iukm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.jaist.ac.jp\/IUKM\/IUKM2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}