{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T23:39:27Z","timestamp":1743032367966,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031790348"},{"type":"electronic","value":"9783031790355"}],"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\/978-3-031-79035-5_29","type":"book-chapter","created":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T22:09:48Z","timestamp":1738188588000},"page":"412-426","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RLPortfolio: Reinforcement Learning for\u00a0Financial Portfolio Optimization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7780-7009","authenticated-orcid":false,"given":"Caio de Souza Barbosa","family":"Costa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7309-4528","authenticated-orcid":false,"given":"Anna Helena Reali","family":"Costa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,30]]},"reference":[{"key":"29_CR1","unstructured":"Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, OSDI 2016, pp. 265\u2013283. USENIX Association, USA (2016)"},{"key":"29_CR2","doi-asserted-by":"publisher","unstructured":"Amrouni, S.: Selimamrouni\/Deep-Portfolio-Management-Reinforcement-Learning: V2.0. Zenodo (2022). https:\/\/doi.org\/10.5281\/zenodo.5993372","DOI":"10.5281\/zenodo.5993372"},{"key":"29_CR3","doi-asserted-by":"publisher","unstructured":"Costa, C.D.S.B., Costa, A.H.R.: POE: a general portfolio optimization environment for FinRL. In: Anais Do Brazilian Workshop on Artificial Intelligence in Finance (BWAIF), pp. 132\u2013143. SBC (2023). https:\/\/doi.org\/10.5753\/bwaif.2023.231144","DOI":"10.5753\/bwaif.2023.231144"},{"key":"29_CR4","doi-asserted-by":"publisher","unstructured":"Felizardo, L.K., Paiva, F.C.L., Costa, A.H.R., Del-Moral-Hernandez, E.: Reinforcement Learning Applied to Trading Systems: A Survey (2022). https:\/\/doi.org\/10.48550\/arXiv.2212.06064","DOI":"10.48550\/arXiv.2212.06064"},{"key":"29_CR5","unstructured":"Haghpanah, M.A.: Gym-mtsim (2021)"},{"key":"29_CR6","unstructured":"Haghpanah, M.A.: Gym-anytrading (2023)"},{"issue":"3","key":"29_CR7","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1111\/mafi.12382","volume":"33","author":"B Hambly","year":"2023","unstructured":"Hambly, B., Xu, R., Yang, H.: Recent advances in reinforcement learning in finance. Math. Financ. 33(3), 437\u2013503 (2023). https:\/\/doi.org\/10.1111\/mafi.12382","journal-title":"Math. Financ."},{"issue":"7825","key":"29_CR8","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","volume":"585","author":"CR Harris","year":"2020","unstructured":"Harris, C.R., et al.: Array programming with NumPy. Nature 585(7825), 357\u2013362 (2020). https:\/\/doi.org\/10.1038\/s41586-020-2649-2","journal-title":"Nature"},{"key":"29_CR9","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1016\/j.eswa.2019.01.012","volume":"124","author":"BM Henrique","year":"2019","unstructured":"Henrique, B.M., Sobreiro, V.A., Kimura, H.: Literature review: machine learning techniques applied to financial market prediction. Expert Syst. Appl. 124, 226\u2013251 (2019). https:\/\/doi.org\/10.1016\/j.eswa.2019.01.012","journal-title":"Expert Syst. Appl."},{"key":"29_CR10","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1016\/j.asoc.2015.07.008","volume":"36","author":"Y Hu","year":"2015","unstructured":"Hu, Y., Liu, K., Zhang, X., Su, L., Ngai, E.W.T., Liu, M.: Application of evolutionary computation for rule discovery in stock algorithmic trading: a literature review. Appl. Soft Comput. 36, 534\u2013551 (2015). https:\/\/doi.org\/10.1016\/j.asoc.2015.07.008","journal-title":"Appl. Soft Comput."},{"key":"29_CR11","unstructured":"Jiang, Z.: ZhengyaoJiang\/PGPortfolio (2024)"},{"key":"29_CR12","doi-asserted-by":"publisher","unstructured":"Jiang, Z., Xu, D., Liang, J.: A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem (2017). https:\/\/doi.org\/10.48550\/arXiv.1706.10059","DOI":"10.48550\/arXiv.1706.10059"},{"key":"29_CR13","doi-asserted-by":"publisher","unstructured":"Khadjeh\u00a0Nassirtoussi, A., Aghabozorgi, S., Ying\u00a0Wah, T., Ngo, D.C.L.: Text mining for market prediction: a systematic review. Expert Syst. Appl. 41(16), 7653\u20137670 (2014). https:\/\/doi.org\/10.1016\/j.eswa.2014.06.009","DOI":"10.1016\/j.eswa.2014.06.009"},{"key":"29_CR14","unstructured":"Le, F.D.: Global Market Portfolio 2023 (2023). https:\/\/www.ssga.com\/international\/en\/institutional\/ic\/insights\/global-market-portfolio-2023"},{"issue":"3","key":"29_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103247","volume":"60","author":"J Li","year":"2023","unstructured":"Li, J., Zhang, Y., Yang, X., Chen, L.: Online portfolio management via deep reinforcement learning with high-frequency data. Inf. Process. Manag. 60(3), 103247 (2023). https:\/\/doi.org\/10.1016\/j.ipm.2022.103247","journal-title":"Inf. Process. Manag."},{"key":"29_CR16","doi-asserted-by":"publisher","unstructured":"Li, Y.: Deep Reinforcement Learning (2018). https:\/\/doi.org\/10.48550\/arXiv.1810.06339","DOI":"10.48550\/arXiv.1810.06339"},{"key":"29_CR17","doi-asserted-by":"publisher","unstructured":"Liang, Z., Chen, H., Zhu, J., Jiang, K., Li, Y.: Adversarial Deep Reinforcement Learning in Portfolio Management (2018). https:\/\/doi.org\/10.48550\/arXiv.1808.09940","DOI":"10.48550\/arXiv.1808.09940"},{"key":"29_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.108894","volume":"123","author":"YC Lin","year":"2022","unstructured":"Lin, Y.C., Chen, C.T., Sang, C.Y., Huang, S.H.: Multiagent-based deep reinforcement learning for risk-shifting portfolio management. Appl. Soft Comput. 123, 108894 (2022). https:\/\/doi.org\/10.1016\/j.asoc.2022.108894","journal-title":"Appl. Soft Comput."},{"key":"29_CR19","doi-asserted-by":"publisher","unstructured":"Liu, X.Y., et al.: ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement Learning (2022). https:\/\/doi.org\/10.48550\/arXiv.2112.05923","DOI":"10.48550\/arXiv.2112.05923"},{"key":"29_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-08011-9","author":"C Ma","year":"2022","unstructured":"Ma, C., Zhang, J., Li, Z., Xu, S.: Multi-agent deep reinforcement learning algorithm with trend consistency regularization for portfolio management. Neural Comput. Appl. (2022). https:\/\/doi.org\/10.1007\/s00521-022-08011-9","journal-title":"Neural Comput. Appl."},{"issue":"1","key":"29_CR21","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1239\/jap\/1077134674","volume":"41","author":"M Magdon-Ismail","year":"2004","unstructured":"Magdon-Ismail, M., Atiya, A.F., Pratap, A., Abu-Mostafa, Y.S.: On the maximum drawdown of a Brownian motion. J. Appl. Probab. 41(1), 147\u2013161 (2004). https:\/\/doi.org\/10.1239\/jap\/1077134674","journal-title":"J. Appl. Probab."},{"key":"29_CR22","doi-asserted-by":"publisher","unstructured":"Paszke, A., et al.: PyTorch: An Imperative Style, High-Performance Deep Learning Library (2019). https:\/\/doi.org\/10.48550\/arXiv.1912.01703","DOI":"10.48550\/arXiv.1912.01703"},{"issue":"268","key":"29_CR23","first-page":"1","volume":"22","author":"A Raffin","year":"2021","unstructured":"Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(268), 1\u20138 (2021)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"29_CR24","doi-asserted-by":"publisher","first-page":"49","DOI":"10.3905\/jpm.1994.409501","volume":"21","author":"WF Sharpe","year":"1994","unstructured":"Sharpe, W.F.: The sharpe ratio. J. Portfolio Manag. 21(1), 49\u201358 (1994). https:\/\/doi.org\/10.3905\/jpm.1994.409501","journal-title":"J. Portfolio Manag."},{"key":"29_CR25","doi-asserted-by":"publisher","unstructured":"Shi, S., Li, J., Li, G., Pan, P.: 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, Beijing, China, pp. 1613\u20131622. ACM (2019). https:\/\/doi.org\/10.1145\/3357384.3357961","DOI":"10.1145\/3357384.3357961"},{"key":"29_CR26","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.neucom.2022.04.105","volume":"498","author":"S Shi","year":"2022","unstructured":"Shi, S., Li, J., Li, G., Pan, P., Chen, Q., Sun, Q.: GPM: a graph convolutional network based reinforcement learning framework for portfolio management. Neurocomputing 498, 14\u201327 (2022). https:\/\/doi.org\/10.1016\/j.neucom.2022.04.105","journal-title":"Neurocomputing"},{"issue":"7676","key":"29_CR27","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of Go without human knowledge. Nature 550(7676), 354\u2013359 (2017). https:\/\/doi.org\/10.1038\/nature24270","journal-title":"Nature"},{"key":"29_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113456","volume":"156","author":"F Soleymani","year":"2020","unstructured":"Soleymani, F., Paquet, E.: Financial portfolio optimization with online deep reinforcement learning and restricted stacked autoencoder\u2013DeepBreath. Expert Syst. Appl. 156, 113456 (2020). https:\/\/doi.org\/10.1016\/j.eswa.2020.113456","journal-title":"Expert Syst. Appl."},{"key":"29_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115127","volume":"182","author":"F Soleymani","year":"2021","unstructured":"Soleymani, F., Paquet, E.: Deep graph convolutional reinforcement learning for financial portfolio management - DeepPocket. Expert Syst. Appl. 182, 115127 (2021). https:\/\/doi.org\/10.1016\/j.eswa.2021.115127","journal-title":"Expert Syst. Appl."},{"key":"29_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122027","volume":"238","author":"Q Sun","year":"2024","unstructured":"Sun, Q., Wei, X., Yang, X.: GraphSAGE with deep reinforcement learning for financial portfolio optimization. Expert Syst. Appl. 238, 122027 (2024). https:\/\/doi.org\/10.1016\/j.eswa.2023.122027","journal-title":"Expert Syst. Appl."},{"key":"29_CR31","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book, Cambridge (2018)"},{"key":"29_CR32","doi-asserted-by":"publisher","unstructured":"The pandas development team: Pandas-dev\/pandas: Pandas. Zenodo (2023). https:\/\/doi.org\/10.5281\/ZENODO.3509134","DOI":"10.5281\/ZENODO.3509134"},{"key":"29_CR33","doi-asserted-by":"publisher","unstructured":"Towers, M., et al.: Gymnasium. Zenodo (2023). https:\/\/doi.org\/10.5281\/zenodo.8127026","DOI":"10.5281\/zenodo.8127026"},{"key":"29_CR34","doi-asserted-by":"publisher","unstructured":"Weng, J., et al.: Tianshou: A Highly Modularized Deep Reinforcement Learning Library (2022). https:\/\/doi.org\/10.48550\/arXiv.2107.14171","DOI":"10.48550\/arXiv.2107.14171"},{"key":"29_CR35","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.neucom.2020.04.004","volume":"402","author":"L Weng","year":"2020","unstructured":"Weng, L., Sun, X., Xia, M., Liu, J., Xu, Y.: Portfolio trading system of digital currencies: a deep reinforcement learning with multidimensional attention gating mechanism. Neurocomputing 402, 171\u2013182 (2020). https:\/\/doi.org\/10.1016\/j.neucom.2020.04.004","journal-title":"Neurocomputing"},{"issue":"1","key":"29_CR36","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","volume":"32","author":"Z Wu","year":"2021","unstructured":"Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Yu, P.S.: A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32(1), 4\u201324 (2021). https:\/\/doi.org\/10.1109\/TNNLS.2020.2978386","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"29_CR37","doi-asserted-by":"publisher","unstructured":"Xu, K., Zhang, Y., Ye, D., Zhao, P., Tan, M.: Relation-aware transformer for portfolio policy learning. In: Twenty-Ninth International Joint Conference on Artificial Intelligence, vol.\u00a05, pp. 4647\u20134653 (2020). https:\/\/doi.org\/10.24963\/ijcai.2020\/641","DOI":"10.24963\/ijcai.2020\/641"},{"key":"29_CR38","doi-asserted-by":"publisher","unstructured":"Yang, X., Liu, W., Zhou, D., Bian, J., Liu, T.Y.: Qlib: An AI-oriented Quantitative Investment Platform (2020). https:\/\/doi.org\/10.48550\/arXiv.2009.11189","DOI":"10.48550\/arXiv.2009.11189"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-79035-5_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T22:09:54Z","timestamp":1738188594000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-79035-5_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031790348","9783031790355"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-79035-5_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"30 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BRACIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazilian Conference on Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bel\u00e9m do Par\u00e1","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}