{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T18:46:57Z","timestamp":1774550817726,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:00:00Z","timestamp":1705017600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1,12]]},"DOI":"10.1145\/3647782.3647801","type":"proceedings-article","created":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T00:05:11Z","timestamp":1715040311000},"page":"119-125","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A General Framework on Enhancing Portfolio Management with Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7740-2484","authenticated-orcid":false,"given":"Yinheng","family":"Li","sequence":"first","affiliation":[{"name":"Columbia University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3049-6698","authenticated-orcid":false,"given":"Junhao","family":"Wang","sequence":"additional","affiliation":[{"name":"Columbia University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9879-7876","authenticated-orcid":false,"given":"Yijie","family":"Cao","sequence":"additional","affiliation":[{"name":"Columbia University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,6]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"e_1_3_2_1_2_1","unstructured":"Jos\u00e9\u00a0E. Figueroa-L\u00f3pez. 2005. A selected survey of portfolio optimization problems."},{"key":"e_1_3_2_1_3_1","unstructured":"Thomas\u00a0G. Fischer. 2018. Reinforcement learning in financial markets - a survey."},{"key":"e_1_3_2_1_4_1","volume-title":"Robust Log-Optimal Strategy with Reinforcement Learning. arXiv: Portfolio Management","author":"Guo YiFeng","year":"2018","unstructured":"YiFeng Guo, XingYu Fu, Yuyan Shi, and MingWen Liu. 2018. Robust Log-Optimal Strategy with Reinforcement Learning. arXiv: Portfolio Management (2018)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","unstructured":"Zhengyao Jiang Dixing Xu and Jinjun Liang. 2017. A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem. https:\/\/doi.org\/10.48550\/ARXIV.1706.10059","DOI":"10.48550\/ARXIV.1706.10059"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Jerzy\u00a0J. Korczak Piotr Lipi\u0144ski and Patrick Roger. 2001. Evolution Strategy in Portfolio Optimization. In Artificial Evolution.","DOI":"10.1007\/3-540-46033-0_13"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.2129"},{"key":"e_1_3_2_1_8_1","volume-title":"Asynchronous Methods for Deep Reinforcement Learning. CoRR abs\/1602.01783","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih, Adri\u00e0\u00a0Puigdom\u00e8nech Badia, Mehdi Mirza, Alex Graves, Timothy\u00a0P. Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous Methods for Deep Reinforcement Learning. CoRR abs\/1602.01783 (2016). arXiv:1602.01783http:\/\/arxiv.org\/abs\/1602.01783"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Ahmet\u00a0Murat Ozbayoglu Mehmet\u00a0Ugur Gudelek and Omer\u00a0Berat Sezer. 2020. Deep Learning for Financial Applications : A Survey. https:\/\/doi.org\/10.48550\/ARXIV.2002.05786","DOI":"10.48550\/ARXIV.2002.05786"},{"key":"e_1_3_2_1_10_1","volume-title":"Simulationsmethoden in der Medizin und Biologie","author":"Rechenberg I.","unstructured":"I. Rechenberg. 1978. Evolutionsstrategien. In Simulationsmethoden in der Medizin und Biologie, Berthold Schneider and Ulrich Ranft (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 83\u2013114."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","unstructured":"Tim Salimans Jonathan Ho Xi Chen Szymon Sidor and Ilya Sutskever. 2017. Evolution Strategies as a Scalable Alternative to Reinforcement Learning. https:\/\/doi.org\/10.48550\/ARXIV.1703.03864","DOI":"10.48550\/ARXIV.1703.03864"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"John Schulman Sergey Levine Philipp Moritz Michael\u00a0I. Jordan and Pieter Abbeel. 2015. Trust Region Policy Optimization. https:\/\/doi.org\/10.48550\/ARXIV.1502.05477","DOI":"10.48550\/ARXIV.1502.05477"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. https:\/\/doi.org\/10.48550\/ARXIV.1707.06347","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.3905\/jpm.1994.409501"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Charalampos Stasinakis and Georgios Sermpinis. 2014. Financial Forecasting and Trading Strategies: A Survey. 22\u201339. https:\/\/doi.org\/10.4324\/9780203084984","DOI":"10.4324\/9780203084984"},{"key":"e_1_3_2_1_16_1","first-page":"253","article-title":"Portfolio Selection: Efficient Diversification of Investments","volume":"10","author":"Stuart L.","year":"1959","unstructured":"Alan\u00a0L. Stuart and Harry\u00a0M. Markowitz. 1959. Portfolio Selection: Efficient Diversification of Investments. A Quarterly Journal of Operations Research 10 (1959), 253.","journal-title":"A Quarterly Journal of Operations Research"},{"key":"e_1_3_2_1_17_1","volume-title":"Advances in Neural Information Processing Systems, S.\u00a0Solla, T.\u00a0Leen, and K.\u00a0M\u00fcller (Eds.). Vol.\u00a012","author":"Sutton S","year":"1999","unstructured":"Richard\u00a0S Sutton, David McAllester, Satinder Singh, and Yishay Mansour. 1999. Policy Gradient Methods for Reinforcement Learning with Function Approximation. In Advances in Neural Information Processing Systems, S.\u00a0Solla, T.\u00a0Leen, and K.\u00a0M\u00fcller (Eds.). Vol.\u00a012. MIT Press. https:\/\/proceedings.neurips.cc\/paper\/1999\/file\/464d828b85b0bed98e80ade0a5c43b0f-Paper.pdf"},{"key":"e_1_3_2_1_18_1","unstructured":"Kamran Usmani. 2015. An Investigation into the Use of Reinforcement Learning Techniques within the Algorithmic Trading Domain."},{"key":"e_1_3_2_1_19_1","volume-title":"Characterizing the Gap Between Actor-Critic and Policy Gradient. In International Conference on Machine Learning.","author":"Wen Junfeng","year":"2021","unstructured":"Junfeng Wen, Saurabh Kumar, Ramki Gummadi, and Dale Schuurmans. 2021. Characterizing the Gap Between Actor-Critic and Policy Gradient. In International Conference on Machine Learning."}],"event":{"name":"ICCMB 2024: 2024 7th International Conference on Computers in Management and Business","location":"Singapore Singapore","acronym":"ICCMB 2024"},"container-title":["Proceedings of the 2024 7th International Conference on Computers in Management and Business"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3647782.3647801","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3647782.3647801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:24:28Z","timestamp":1755912268000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3647782.3647801"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,12]]},"references-count":19,"alternative-id":["10.1145\/3647782.3647801","10.1145\/3647782"],"URL":"https:\/\/doi.org\/10.1145\/3647782.3647801","relation":{},"subject":[],"published":{"date-parts":[[2024,1,12]]},"assertion":[{"value":"2024-05-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}