{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T01:09:06Z","timestamp":1768525746842,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1145\/3695719.3695720","type":"proceedings-article","created":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T21:57:15Z","timestamp":1731535035000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A Deep Reinforcement Learning Model for Portfolio Management Incorporating Historical Stock Prices and Risk Information"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9645-0300","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Control Science and Engineering, Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8164-8811","authenticated-orcid":false,"given":"Yan","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8652-9818","authenticated-orcid":false,"given":"XiaoDong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Dalian University of Technology, Dalian, Liaoning, China and Dalian Dongteng Data Technology Co.,LTD, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,13]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Kun Gao. Quantitative trading in equities. In Financial Engineering: The Evolution of a Profession pages 323\u2013336. 2011.","DOI":"10.1002\/9781118266854.ch15"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Xu\u00a0Jungang Li\u00a0Pengfei and Lai Xinhua. Lstm neural network with attention mechanism for stock timing in quantitative trading field. In 2022 2nd International Conference on Intelligent Technologies (CONIT) pages 1\u20137. IEEE 2022.","DOI":"10.1109\/CONIT55038.2022.9848232"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Paolo Tenti. Forecasting foreign exchange rates using recurrent neural networks. Applied Artificial Intelligence 10(6):567\u2013582 1996.","DOI":"10.1080\/088395196118434"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. Long short-term memory. Neural computation 9(8):1735\u20131780 1997.","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_3_1_6_2","unstructured":"Jake Bouvrie. Notes on convolutional neural networks. 2006."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Chen Li Xu\u00a0Zhang Mahboob Qaosar Saleh Ahmed Kazi Md\u00a0Rokibul Alam and Yasuhiko Morimoto. Multi-factor based stock price prediction using hybrid neural networks with attention mechanism. In 2019 ieee intl conf on dependable autonomic and secure computing intl conf on pervasive intelligence and computing intl conf on cloud and big data computing intl conf on cyber science and technology congress (dasc\/picom\/cbdcom\/cyberscitech) pages 961\u2013966. IEEE 2019.","DOI":"10.1109\/DASC\/PiCom\/CBDCom\/CyberSciTech.2019.00176"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Jo\u00e3o Carapu\u00e7o Rui Neves and Nuno Horta. Reinforcement learning applied to forex trading. Applied Soft Computing 73:783\u2013794 2018.","DOI":"10.1016\/j.asoc.2018.09.017"},{"key":"e_1_3_3_1_9_2","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. Playing atari with deep reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1312.5602 2013."},{"key":"e_1_3_3_1_10_2","unstructured":"Timothy\u00a0P Lillicrap Jonathan\u00a0J Hunt Alexander Pritzel Nicolas Heess Tom Erez Yuval Tassa David Silver and Daan Wierstra. Continuous control with deep reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1509.02971 2015."},{"key":"e_1_3_3_1_11_2","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. Proximal policy optimization algorithms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1707.06347 2017."},{"key":"e_1_3_3_1_12_2","unstructured":"Scott Fujimoto Herke Hoof and David Meger. Addressing function approximation error in actor-critic methods. In International conference on machine learning pages 1587\u20131596. PMLR 2018."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Lingheng Meng Rob Gorbet and Dana Kuli\u0107. Memory-based deep reinforcement learning for pomdps. In 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) pages 5619\u20135626. IEEE 2021.","DOI":"10.1109\/IROS51168.2021.9636140"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Frank\u00a0J Fabozzi Harry\u00a0M Markowitz and Francis Gupta. Portfolio selection. Handbook of finance 2 2008.","DOI":"10.1002\/9780470404324.hof002001"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Robert\u00a0C Merton. An intertemporal capital asset pricing model. Econometrica: Journal of the Econometric Society pages 867\u2013887 1973.","DOI":"10.2307\/1913811"},{"key":"e_1_3_3_1_16_2","unstructured":"Zhengyao Jiang Dixing Xu and Jinjun Liang. A deep reinforcement learning framework for the financial portfolio management problem. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1706.10059 2017."},{"key":"e_1_3_3_1_17_2","unstructured":"David Silver Guy Lever Nicolas Heess Thomas Degris Daan Wierstra and Martin Riedmiller. Deterministic policy gradient algorithms. In International conference on machine learning pages 387\u2013395. Pmlr 2014."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Jingyuan Wang Yang Zhang Ke\u00a0Tang Junjie Wu and Zhang Xiong. Alphastock: A buying-winners-and-selling-losers investment strategy using interpretable deep reinforcement attention networks. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining pages 1900\u20131908 2019.","DOI":"10.1145\/3292500.3330647"},{"key":"e_1_3_3_1_19_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems 30 2017."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Zhicheng Wang Biwei Huang Shikui Tu Kun Zhang and Lei Xu. Deeptrader: a deep reinforcement learning approach for risk-return balanced portfolio management with market conditions embedding. In Proceedings of the AAAI conference on artificial intelligence volume\u00a035 pages 643\u2013650 2021.","DOI":"10.1609\/aaai.v35i1.16144"},{"key":"e_1_3_3_1_21_2","unstructured":"Thomas\u00a0N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1609.02907 2016."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Adil Moghar and Mhamed Hamiche. Stock market prediction using lstm recurrent neural network. Procedia Computer Science 170:1168\u20131173 2020.","DOI":"10.1016\/j.procs.2020.03.049"},{"key":"e_1_3_3_1_23_2","unstructured":"Huaxiu Yao Xianfeng Tang Hua Wei Guanjie Zheng Yanwei Yu and Zhenhui Li. Modeling spatial-temporal dynamics for traffic prediction. arxiv 2018. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1803.01254."},{"key":"e_1_3_3_1_24_2","unstructured":"David Silver. Lecture 2: Markov decision processes. UCL. Retrieved from www0. cs. ucl. ac. uk\/staff\/d. silver\/web\/Teaching files\/MDP. pdf 2015."},{"key":"e_1_3_3_1_25_2","unstructured":"Yang Yue Bingyi Kang Xiao Ma Gao Huang Shiji Song and Shuicheng Yan. Offline prioritized experience replay. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.05412 2023."}],"event":{"name":"ICDLT 2024: 2024 8th International Conference on Deep Learning Technologies (ICDLT)","location":"Suzhou China","acronym":"ICDLT 2024"},"container-title":["Proceedings of the 2024 8th International Conference on Deep Learning Technologies"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695719.3695720","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695719.3695720","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:06Z","timestamp":1750295406000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695719.3695720"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":24,"alternative-id":["10.1145\/3695719.3695720","10.1145\/3695719"],"URL":"https:\/\/doi.org\/10.1145\/3695719.3695720","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]},"assertion":[{"value":"2024-11-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}