{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:43:01Z","timestamp":1771612981723,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T00:00:00Z","timestamp":1700870400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,27]]},"DOI":"10.1145\/3604237.3626906","type":"proceedings-article","created":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T18:09:47Z","timestamp":1700935787000},"page":"610-618","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Margin Trader: A Reinforcement Learning Framework for Portfolio Management with Margin and Constraints"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8010-8326","authenticated-orcid":false,"given":"Jingyi","family":"Gu","sequence":"first","affiliation":[{"name":"New Jersey Institute of Technology, US"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4925-0468","authenticated-orcid":false,"given":"Wenlu","family":"Du","sequence":"additional","affiliation":[{"name":"New Jersey Institute of Technology, US"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8527-8948","authenticated-orcid":false,"given":"A M Muntasir","family":"Rahman","sequence":"additional","affiliation":[{"name":"New Jersey Institute of Technology, US"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1880-4763","authenticated-orcid":false,"given":"Guiling","family":"Wang","sequence":"additional","affiliation":[{"name":"New Jersey Institute of Technology, US"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,11,25]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"An adaptive portfolio trading system: A risk-return portfolio optimization using recurrent reinforcement learning with expected maximum drawdown. Expert Systems with Applications 87","author":"Almahdi Saud","year":"2017","unstructured":"Saud Almahdi and Steve\u00a0Y Yang. 2017. An adaptive portfolio trading system: A risk-return portfolio optimization using recurrent reinforcement learning with expected maximum drawdown. Expert Systems with Applications 87 (2017)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422559"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Qianggang Ding Sifan Wu Hao Sun Jiadong Guo and Jian Guo. 2020. Hierarchical Multi-Scale Gaussian Transformer for Stock Movement Prediction.. In IJCAI. 4640\u20134646.","DOI":"10.24963\/ijcai.2020\/640"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20369"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0022109011000342"},{"key":"e_1_3_2_1_6_1","volume-title":"Margin requirements, margin loans, and margin rates: Practice and principles. New England Economic Review","author":"Peter Fortune","year":"2000","unstructured":"Peter Fortune 2000. Margin requirements, margin loans, and margin rates: Practice and principles. New England Economic Review (2000), 19\u201344."},{"key":"e_1_3_2_1_7_1","volume-title":"Stock broad-index trend patterns learning via domain knowledge informed generative network. arXiv preprint arXiv:2302.14164","author":"Gu Jingyi","year":"2023","unstructured":"Jingyi Gu, Fadi\u00a0P Deek, and Guiling Wang. 2023. Stock broad-index trend patterns learning via domain knowledge informed generative network. arXiv preprint arXiv:2302.14164 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"International conference on machine learning. PMLR.","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning. PMLR."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/mafi.12382"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.09.036"},{"key":"e_1_3_2_1_11_1","volume-title":"A deep reinforcement learning framework for the financial portfolio management problem. arXiv preprint arXiv:1706.10059","author":"Jiang Zhengyao","year":"2017","unstructured":"Zhengyao Jiang, Dixing Xu, and Jinjun Liang. 2017. A deep reinforcement learning framework for the financial portfolio management problem. arXiv preprint arXiv:1706.10059 (2017)."},{"key":"e_1_3_2_1_12_1","volume-title":"Application of deep reinforcement learning in stock trading strategies and stock forecasting. Computing","author":"Li Yuming","year":"2020","unstructured":"Yuming Li, Pin Ni, and Victor Chang. 2020. Application of deep reinforcement learning in stock trading strategies and stock forecasting. Computing (2020)."},{"key":"e_1_3_2_1_13_1","volume-title":"Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971","author":"Lillicrap P","year":"2015","unstructured":"Timothy\u00a0P Lillicrap, Jonathan\u00a0J Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. 2015. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)."},{"key":"e_1_3_2_1_14_1","first-page":"1835","article-title":"FinRL-Meta: Market environments and benchmarks for data-driven financial reinforcement learning","volume":"35","author":"Liu Xiao-Yang","year":"2022","unstructured":"Xiao-Yang Liu, Ziyi Xia, Jingyang Rui, Jiechao Gao, Hongyang Yang, Ming Zhu, Christina Wang, Zhaoran Wang, and Jian Guo. 2022. FinRL-Meta: Market environments and benchmarks for data-driven financial reinforcement learning. Advances in Neural Information Processing Systems 35 (2022), 1835\u20131849.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490354.3494366"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5587"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10614-020-10038-w"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3390\/data6110119"},{"key":"e_1_3_2_1_19_1","volume-title":"International conference on machine learning. PMLR","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih, Adria\u00a0Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous methods for deep reinforcement learning. In International conference on machine learning. PMLR, 1928\u20131937."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557363"},{"key":"e_1_3_2_1_21_1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin Antonin","year":"2021","unstructured":"Antonin Raffin, Ashley Hill, Adam Gleave, Anssi Kanervisto, Maximilian Ernestus, and Noah Dormann. 2021. Stable-baselines3: Reliable reinforcement learning implementations. The Journal of Machine Learning Research 22, 1 (2021).","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_2_1_22_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_23_1","volume-title":"The sharpe ratio. Streetwise\u2013the Best of the Journal of Portfolio Management 3","author":"Sharpe F","year":"1998","unstructured":"William\u00a0F Sharpe. 1998. The sharpe ratio. Streetwise\u2013the Best of the Journal of Portfolio Management 3 (1998), 169\u201385."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3625234"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557283"},{"key":"e_1_3_2_1_26_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton S","unstructured":"Richard\u00a0S Sutton and Andrew\u00a0G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422532"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330647"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16142"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16144"},{"key":"e_1_3_2_1_31_1","volume-title":"Practical Deep Reinforcement Learning Approach for Stock Trading","author":"Xiong Zhuoran","year":"2023","unstructured":"Zhuoran Xiong, Xiao-Yang Liu, Shan Zhong, Hongyang\u00a0Bruce Yang, and Anwar Walid. 2018. Practical Deep Reinforcement Learning Approach for Stock Trading (2023). (2018)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/3491440.3492081"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422540"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/557"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5462"},{"key":"e_1_3_2_1_36_1","first-page":"236","article-title":"Cost-sensitive portfolio selection via deep reinforcement learning","volume":"34","author":"Zhang Yifan","year":"2020","unstructured":"Yifan Zhang, Peilin Zhao, Qingyao Wu, Bin Li, Junzhou Huang, and Mingkui Tan. 2020. Cost-sensitive portfolio selection via deep reinforcement learning. IEEE Transactions on Knowledge and Data Engineering 34, 1 (2020), 236\u2013248.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"}],"event":{"name":"ICAIF '23: 4th ACM International Conference on AI in Finance","location":"Brooklyn NY USA","acronym":"ICAIF '23"},"container-title":["4th ACM International Conference on AI in Finance"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604237.3626906","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3604237.3626906","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:39:18Z","timestamp":1755884358000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604237.3626906"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,25]]},"references-count":36,"alternative-id":["10.1145\/3604237.3626906","10.1145\/3604237"],"URL":"https:\/\/doi.org\/10.1145\/3604237.3626906","relation":{},"subject":[],"published":{"date-parts":[[2023,11,25]]},"assertion":[{"value":"2023-11-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}