{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T13:01:26Z","timestamp":1785502886712,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","funder":[{"name":"NTU-WeBank Research Centre on Fintech, Nanyang Technological University, Singapore.","award":["None"],"award-info":[{"award-number":["None"]}]},{"name":"Singapore Ministry of Educa tion (MOE) Academic Research Fund (AcRF) Tier 1 grant.","award":["23-SIS-SMU-037"],"award-info":[{"award-number":["23-SIS-SMU-037"]}]},{"name":"Guangzhou-HKUST(GZ) Joint Funding Program","award":["No. 2024A03J0630"],"award-info":[{"award-number":["No. 2024A03J0630"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3780187","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"1194-1203","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FineFT: Efficient and Risk-Aware Ensemble Reinforcement Learning for Futures Trading"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0431-7940","authenticated-orcid":false,"given":"Molei","family":"Qin","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8274-0595","authenticated-orcid":false,"given":"Xinyu","family":"Cai","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0073-123X","authenticated-orcid":false,"given":"Yewen","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2947-5947","authenticated-orcid":false,"given":"Haochong","family":"Xia","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0107-4211","authenticated-orcid":false,"given":"Chuqiao","family":"Zong","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7153-1878","authenticated-orcid":false,"given":"Shuo","family":"Sun","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3369-219X","authenticated-orcid":false,"given":"Xinrun","family":"Wang","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7064-7438","authenticated-orcid":false,"given":"Bo","family":"An","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1002\/fut.22163"},{"key":"e_1_3_2_2_2_1","volume-title":"International Conference on Machine Learning. PMLR, 176-185","author":"Anschel Oron","year":"2017","unstructured":"Oron Anschel, Nir Baram, and Nahum Shimkin. 2017. Averaged-DQN: Variance reduction and stabilization for deep reinforcement learning. In International Conference on Machine Learning. PMLR, 176-185."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8813791"},{"key":"e_1_3_2_2_4_1","volume-title":"Deep reinforcement learning for active high frequency trading. arXiv preprint arXiv:2101.07107","author":"Briola Antonio","year":"2021","unstructured":"Antonio Briola, Jeremy Turiel, Riccardo Marcaccioli, and Tomaso Aste. 2021. Deep reinforcement learning for active high frequency trading. arXiv preprint arXiv:2101.07107 (2021)."},{"key":"e_1_3_2_2_5_1","volume-title":"Diego Reforgiato Recupero, and Antonio Sanna.","author":"Carta Salvatore","year":"2021","unstructured":"Salvatore Carta, Anselmo Ferreira, Alessandro Sebastian Podda, Diego Reforgiato Recupero, and Antonio Sanna. 2021. Multi-DQN: An ensemble of Deep Q-learning Agents for Stock Market Forecasting. Expert Systems with pplications, Vol. 164 (2021), 113820."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-405X(02)00136-8"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.4324\/9781315115719"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"e_1_3_2_2_10_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15559-8_29"},{"key":"e_1_3_2_2_12_1","volume-title":"On the generalization of representations in reinforcement learning. arXiv preprint arXiv:2203.00543","author":"Lan Charline Le","year":"2022","unstructured":"Charline Le Lan, Stephen Tu, Adam Oberman, Rishabh Agarwal, and Marc G Bellemare. 2022. On the generalization of representations in reinforcement learning. arXiv preprint arXiv:2203.00543 (2022)."},{"key":"e_1_3_2_2_13_1","volume-title":"International Conference on Machine Learning. 6131-6141","author":"Lee Kimin","year":"2021","unstructured":"Kimin Lee, Michael Laskin, Aravind Srinivas, and Pieter Abbeel. 2021. Sunrise: A simple unified framework for ensemble learning in deep reinforcement learning. In International Conference on Machine Learning. 6131-6141."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5587"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1386-4181(00)00007-0"},{"key":"e_1_3_2_2_16_1","first-page":"529","volume-title":"Nature","volume":"518","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et al., 2015. Human-level control through deep reinforcement learning. Nature, Vol. 518, 7540 (2015), 529-533."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29384"},{"key":"e_1_3_2_2_18_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_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2012.2205924"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Shuo Sun Molei Qin Wentao Zhang Haochong Xia Chuqiao Zong Jie Ying Yonggang Xie Lingxuan Zhao Xinrun Wang and Bo An. 2024. TradeMaster: A holistic quantitative trading platform empowered by reinforcement learning. In Advances in Neural Information Processing Systems.","DOI":"10.52202\/075280-2576"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599424"},{"key":"e_1_3_2_2_22_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research, Vol. 9, 11 (2008).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29531"},{"key":"e_1_3_2_2_24_1","volume-title":"Deep reinforcement learning amidst lifelong non-stationarity. arXiv preprint arXiv:2006.10701","author":"Xie Annie","year":"2020","unstructured":"Annie Xie. 2020. Deep reinforcement learning amidst lifelong non-stationarity. arXiv preprint arXiv:2006.10701 (2020)."},{"key":"e_1_3_2_2_25_1","volume-title":"Advances in Neural Information Processing Systems","volume":"13","author":"Zhang Tong","year":"2000","unstructured":"Tong Zhang. 2000. Regularized winnow methods. Advances in Neural Information Processing Systems, Vol. 13 (2000)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Wentao Zhang Lingxuan Zhao Haochong Xia Shuo Sun Jiaze Sun Molei Qin Xinyi Li Yuqing Zhao Yilei Zhao Xinyu Cai et al. 2024b. FinAgent: A multimodal foundation agent for financial trading: Tool-augmented diversified and generalist. arXiv preprint arXiv:2402.18485 (2024).","DOI":"10.1145\/3637528.3671801"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645615"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.3390\/stats5020033"},{"key":"e_1_3_2_2_29_1","volume-title":"MacroHFT: Memory augmented context-aware reinforcement learning on high frequency trading. arXiv preprint arXiv:2406.14537","author":"Zong Chuqiao","year":"2024","unstructured":"Chuqiao Zong, Chaojie Wang, Molei Qin, Lei Feng, Xinrun Wang, and Bo An. 2024. MacroHFT: Memory augmented context-aware reinforcement learning on high frequency trading. arXiv preprint arXiv:2406.14537 (2024)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3780187","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:10:45Z","timestamp":1785499845000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3780187"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":29,"alternative-id":["10.1145\/3770854.3780187","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3780187","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}