{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T18:51:32Z","timestamp":1743015092165,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031467745"},{"type":"electronic","value":"9783031467752"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-46775-2_20","type":"book-chapter","created":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T15:03:38Z","timestamp":1698332618000},"page":"224-235","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Revolutionizing SET50 Stock Portfolio Management with\u00a0Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Sukrit","family":"Thongkairat","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donlapark","family":"Ponnoprat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Phimphaka","family":"Taninpong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Woraphon","family":"Yamaka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,25]]},"reference":[{"issue":"3731","key":"20_CR1","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1126\/science.153.3731.34","volume":"153","author":"R Bellman","year":"1966","unstructured":"Bellman, R.: Dynamic programming. Science 153(3731), 34\u201337 (1966)","journal-title":"Science"},{"issue":"6","key":"20_CR2","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1016\/j.jedc.2010.01.015","volume":"34","author":"SD Bekiros","year":"2010","unstructured":"Bekiros, S.D.: Heterogeneous trading strategies with adaptive fuzzy actor-critic reinforcement learning: a behavioral approach. J. Econ. Dyn. Control 34(6), 1153\u20131170 (2010)","journal-title":"J. Econ. Dyn. Control"},{"key":"20_CR3","doi-asserted-by":"publisher","first-page":"38590","DOI":"10.1109\/ACCESS.2022.3166599","volume":"10","author":"G Borrageiro","year":"2022","unstructured":"Borrageiro, G., Firoozye, N., Barucca, P.: The recurrent reinforcement learning crypto agent. IEEE Access 10, 38590\u201338599 (2022)","journal-title":"IEEE Access"},{"key":"20_CR4","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"issue":"8","key":"20_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.: Deep hedging. Quantit. Financ. 19(8), 1271\u20131291 (2019)","journal-title":"Quantit. Financ."},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L., Gao, Q.: Application of deep reinforcement learning on automated stock trading. In: 2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS), pp. 29\u201333. IEEE (2019)","DOI":"10.1109\/ICSESS47205.2019.9040728"},{"issue":"1","key":"20_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/jrfm7010001","volume":"7","author":"TTL Chong","year":"2014","unstructured":"Chong, T.T.L., Ng, W.K., Liew, V.K.S.: Revisiting the performance of MACD and RSI oscillators. J. Risk Financ. Manag. 7(1), 1\u201312 (2014)","journal-title":"J. Risk Financ. Manag."},{"key":"20_CR8","doi-asserted-by":"publisher","unstructured":"Dang, Q.-V.: Reinforcement learning in stock trading. In: Le Thi, H.A., Le, H.M., Pham Dinh, T., Nguyen, N.T. (eds.) ICCSAMA 2019. AISC, vol. 1121, pp. 311\u2013322. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-38364-0_28","DOI":"10.1007\/978-3-030-38364-0_28"},{"issue":"3","key":"20_CR9","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1109\/TNNLS.2016.2522401","volume":"28","author":"Y Deng","year":"2016","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 (2016)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"20_CR10","unstructured":"Dhariwal, P., et al.: Openai baselines (2017). https:\/\/github.com\/openai\/baselines"},{"key":"20_CR11","unstructured":"Fischer, T.G.: Reinforcement learning in financial markets-a survey (No. 12\/2018). FAU Discussion Papers in Economics (2018)"},{"key":"20_CR12","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1587\u20131596 (2018)"},{"issue":"3","key":"20_CR13","doi-asserted-by":"publisher","first-page":"58","DOI":"10.21511\/bbs.13(3).2018.06","volume":"13","author":"I Gurrib","year":"2018","unstructured":"Gurrib, I.: Performance of the average directional Index as a market timing tool for the most actively traded USD based currency pairs. Banks Bank Syst. 13(3), 58\u201370 (2018)","journal-title":"Banks Bank Syst."},{"key":"20_CR14","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870 (2018)"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Hirsa, A., Osterrieder, J., Hadji-Misheva, B., Posth, J.A.: Deep reinforcement learning on a multi-asset environment for trading. arXiv preprint arXiv:2106.08437 (2021)","DOI":"10.2139\/ssrn.3867800"},{"key":"20_CR16","unstructured":"Jagtap, R.: Understanding Markov Decision Process (MDP). Towards data science (2020). https:\/\/towardsdatascience.com\/understanding-the-markov-decision-process-mdp-8f838510f150"},{"key":"20_CR17","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.eswa.2018.09.036","volume":"117","author":"G Jeong","year":"2019","unstructured":"Jeong, G., Kim, H.Y.: Improving financial trading decisions using deep Q-learning: predicting the number of shares, action strategies, and transfer learning. Expert Syst. Appl. 117, 125\u2013138 (2019)","journal-title":"Expert Syst. Appl."},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Liang, J.: Cryptocurrency portfolio management with deep reinforcement learning. In: 2017 Intelligent Systems Conference (IntelliSys), pp. 905\u201391. IEEE (2017)","DOI":"10.1109\/IntelliSys.2017.8324237"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Li, J., Rao, R., Shi, J.: Learning to trade with deep actor critic methods. In: 2018 11th International Symposium on Computational Intelligence and Design (ISCID), vol. 2, pp. 66\u201371. IEEE (2018)","DOI":"10.1109\/ISCID.2018.10116"},{"issue":"6","key":"20_CR20","doi-asserted-by":"publisher","first-page":"1305","DOI":"10.1007\/s00607-019-00773-w","volume":"102","author":"Y Li","year":"2020","unstructured":"Li, Y., Ni, P., Chang, V.: Application of deep reinforcement learning in stock trading strategies and stock forecasting. Computing 102(6), 1305\u20131322 (2020)","journal-title":"Computing"},{"key":"20_CR21","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"issue":"1","key":"20_CR22","first-page":"176","volume":"6","author":"M Maitah","year":"2016","unstructured":"Maitah, M., Prochazka, P., Cermak, M., \u0160r\u00e9dl, K.: Commodity channel index: evaluation of trading rule of agricultural commodities. Int. J. Econ. Financ. Issues 6(1), 176\u2013178 (2016)","journal-title":"Int. J. Econ. Financ. Issues"},{"key":"20_CR23","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"issue":"7540","key":"20_CR24","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"20_CR25","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937. PMLR (2016)"},{"issue":"4","key":"20_CR26","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":"7","key":"20_CR27","first-page":"1136","volume":"14","author":"K Moriyama","year":"2008","unstructured":"Moriyama, K., Matsumoto, M., Fukui, K.I., Kurihara, S., Numao, M.: Reinforcement learning on a futures market simulator. J. Univers. Comput. Sci. 14(7), 1136\u20131153 (2008)","journal-title":"J. Univers. Comput. Sci."},{"key":"20_CR28","unstructured":"Raffin, A., Hill, A., Ernestus, M., Gleave, A., Kanervisto, A., Dormann, N.: Stable baselines3 (2019)"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Riedmiller, M.: Neural reinforcement learning to swing-up and balance a real pole. In: 2005 IEEE International Conference on Systems, Man and Cybernetics, vol. 4, pp. 3191\u20133196. IEEE (2005)","DOI":"10.1109\/ICSMC.2005.1571637"},{"key":"20_CR30","unstructured":"Sadighian, J.: Deep reinforcement learning in cryptocurrency market making. arXiv preprint arXiv:1911.08647 (2019)"},{"key":"20_CR31","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897. PMLR (2015)"},{"key":"20_CR32","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"20_CR33","doi-asserted-by":"publisher","first-page":"162651","DOI":"10.1109\/ACCESS.2021.3133937","volume":"9","author":"Z Shahbazi","year":"2021","unstructured":"Shahbazi, Z., Byun, Y.C.: Improving the cryptocurrency price prediction performance based on reinforcement learning. IEEE Access 9, 162651\u2013162659 (2021)","journal-title":"IEEE Access"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Si, W., Li, J., Ding, P., Rao, R.: A multi-objective deep reinforcement learning approach for stock index future\u2019s intraday trading. In: 2017 10th International Symposium on Computational Intelligence and Design (ISCID), vol. 2, pp. 431\u2013436. IEEE (2017)","DOI":"10.1109\/ISCID.2017.210"},{"issue":"1","key":"20_CR35","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1162\/089892999563184","volume":"11","author":"RS Sutton","year":"1999","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning. J. Cogn. Neurosci. 11(1), 126\u2013134 (1999)","journal-title":"J. Cogn. Neurosci."},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30, no. 1 (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"20_CR37","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.ins.2020.05.066","volume":"538","author":"X Wu","year":"2020","unstructured":"Wu, X., Chen, H., Wang, J., Troiano, L., Loia, V., Fujita, H.: Adaptive stock trading strategies with deep reinforcement learning methods. Inf. Sci. 538, 142\u2013158 (2020)","journal-title":"Inf. Sci."},{"key":"20_CR38","unstructured":"Wu, Y., Tian, Y.: Training agent for first-person shooter game with actor-critic curriculum learning (2016)"},{"key":"20_CR39","unstructured":"Xiong, Z., Liu, X.Y., Zhong, S., Yang, H., Walid, A.: Practical deep reinforcement learning approach for stock trading. arXiv preprint arXiv:1811.07522 (2018)"},{"key":"20_CR40","doi-asserted-by":"crossref","unstructured":"Yang, H., Liu, X.Y., Wu, Q.: A practical machine learning approach for dynamic stock recommendation. In: 2018 17th IEEE International Conference on Trust, Security and Privacy in Computing and Communications\/12th IEEE International Conference on Big Data Science and Engineering (TrustCom\/BigDataSE), pp. 1693\u20131697. IEEE (2018)","DOI":"10.1109\/TrustCom\/BigDataSE.2018.00253"},{"issue":"2","key":"20_CR41","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.: Deep reinforcement learning for trading. J. Financ. Data Sci. 2(2), 25\u201340 (2020)","journal-title":"J. Financ. Data Sci."}],"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\/978-3-031-46775-2_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T22:00:01Z","timestamp":1730412001000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46775-2_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031467745","9783031467752"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46775-2_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"25 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Kanazawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iukm2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.jaist.ac.jp\/IUKM\/IUKM2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}