{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:42:35Z","timestamp":1773247355421,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,15]]},"DOI":"10.1145\/3768292.3770340","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:24:26Z","timestamp":1763105066000},"page":"890-897","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Regret-Optimized Portfolio Enhancement through Deep Reinforcement Learning and Future Looking Rewards"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1767-9649","authenticated-orcid":false,"given":"Daniil","family":"Karzanov","sequence":"first","affiliation":[{"name":"AXA Group Operations, Lausanne, Switzerland and EPFL, Lausanne, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5695-2495","authenticated-orcid":false,"given":"Rub\u00e9n","family":"Garz\u00f3n","sequence":"additional","affiliation":[{"name":"AXA Group Operations, Barcelona, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7403-3731","authenticated-orcid":false,"given":"Mikhail","family":"Terekhov","sequence":"additional","affiliation":[{"name":"CLAIRE, EPFL, Lausanne, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4124-1687","authenticated-orcid":false,"given":"Caglar","family":"Gulcehre","sequence":"additional","affiliation":[{"name":"CLAIRE, EPFL, Lausanne, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2338-3596","authenticated-orcid":false,"given":"Thomas","family":"Raffinot","sequence":"additional","affiliation":[{"name":"AXA Investment Managers, Paris, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5669-4871","authenticated-orcid":false,"given":"Marcin","family":"Detyniecki","sequence":"additional","affiliation":[{"name":"AXA Group Operations, Paris, France"}]}],"member":"320","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","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) 267\u2013279.","DOI":"10.1016\/j.eswa.2017.06.023"},{"key":"e_1_3_3_1_3_2","unstructured":"Henrik Andersson Henrik Scholtz and Jiakun Zheng. 2023. Measuring regret theory in the health and financial domain. (2023)."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412958"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Eric Benhamou David Saltiel Sandrine Ungari and Abhishek Mukhopadhyay. 2020. Bridging the gap between Markowitz planning and deep reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.09108 (2020).","DOI":"10.2139\/ssrn.3948307"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAIE51050.2020.9358319"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Ivo Blohm Torben Antretter Charlotta Sir\u00e9n Dietmar Grichnik and Joakim Wincent. 2020. It\u2019s a Peoples Game Isn\u2019t It?! A Comparison Between the Investment Returns of Business Angels and Machine Learning Algorithms. Entrepreneurship Theory and Practice 46 (2020) 1054 \u2013 1091. https:\/\/api.semanticscholar.org\/CorpusID:224959426","DOI":"10.1177\/1042258720945206"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Alessio Brini and Daniele Tantari. 2023. Deep reinforcement trading with predictable returns. Physica A: Statistical Mechanics and its Applications 622 (2023) 128901.","DOI":"10.1016\/j.physa.2023.128901"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Jurgita \u010cernevi\u010dien\u0117 and Audrius Kaba\u0161inskas. 2022. Review of multi-criteria decision-making methods in finance using explainable artificial intelligence. Frontiers in artificial intelligence 5 (2022) 827584.","DOI":"10.3389\/frai.2022.827584"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Alexei Chekhlov Stanislav Uryasev and Michael Zabarankin. 2005. Drawdown measure in portfolio optimization. International Journal of Theoretical and Applied Finance 8 01 (2005) 13\u201358.","DOI":"10.1142\/S0219024905002767"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Federico Cornalba Constantin Disselkamp Davide Scassola and Christopher Helf. 2024. Multi-objective reward generalization: improving performance of Deep Reinforcement Learning for applications in single-asset trading. Neural Computing and Applications 36 2 (2024) 619\u2013637.","DOI":"10.1007\/s00521-023-09033-7"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1017\/9781108883658"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220113"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Joost Driessen Pascal\u00a0J Maenhout and Grigory Vilkov. 2009. The price of correlation risk: Evidence from equity options. The Journal of Finance 64 3 (2009) 1377\u20131406.","DOI":"10.1111\/j.1540-6261.2009.01467.x"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Adam\u00a0N Elmachtoub and Paul Grigas. 2022. Smart \u201cpredict then optimize\u201d. Management Science 68 1 (2022) 9\u201326.","DOI":"10.1287\/mnsc.2020.3922"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Simon Gilchrist and Egon Zakraj\u0161ek. 2012. Credit spreads and business cycle fluctuations. American economic review 102 4 (2012) 1692\u20131720.","DOI":"10.1257\/aer.102.4.1692"},{"key":"e_1_3_3_1_18_2","unstructured":"Igor Halperin Jiayu Liu and Xiao Zhang. [n. d.]. Combining Reinforcement Learning and Inverse Reinforcement Learning for Asset Allocation Recommendations. arxiv:https:\/\/arXiv.org\/abs\/2201.01874 [cs q-fin]http:\/\/arxiv.org\/abs\/2201.01874"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Ben Hambly Renyuan Xu and Huining Yang. 2023. Recent advances in reinforcement learning in finance. Mathematical Finance 33 3 (2023) 437\u2013503.","DOI":"10.1111\/mafi.12382"},{"key":"e_1_3_3_1_20_2","unstructured":"Zhengyao Jiang Dixing Xu and Jinjun Liang. 2017. 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_21_2","unstructured":"Daniil Karzanov. 2023. Headline-Driven Classification and Local Interpretation for Market Outperformance and Low-Risk Stock Prediction. Computational Economics (2023) 1\u201320."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Vasileios Kochliaridis Eleftherios Kouloumpris and Ioannis Vlahavas. 2023. Combining deep reinforcement learning with technical analysis and trend monitoring on cryptocurrency markets. Neural Computing and Applications 35 29 (2023) 21445\u201321462.","DOI":"10.1007\/s00521-023-08516-x"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37720-5_2"},{"key":"e_1_3_3_1_24_2","unstructured":"Chung\u00a0I Lu. 2023. Evaluation of Deep Reinforcement Learning Algorithms for Portfolio Optimisation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.07694 (2023)."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-19823-7_20"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Giorgio Lucarelli and Matteo Borrotti. 2020. A deep Q-learning portfolio management framework for the cryptocurrency market. Neural Computing and Applications 32 (2020) 17229\u201317244.","DOI":"10.1007\/s00521-020-05359-8"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5521"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Harry Markowitz. 1952. Portfolio Selection. The Journal of Finance 7 1 (1952) 77\u201391. http:\/\/www.jstor.org\/stable\/2975974","DOI":"10.1111\/j.1540-6261.1952.tb01525.x"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei\u00a0A Rusu Joel Veness Marc\u00a0G Bellemare Alex Graves Martin Riedmiller Andreas\u00a0K Fidjeland Georg Ostrovski et\u00a0al. 2015. Human-level control through deep reinforcement learning. nature 518 7540 (2015) 529\u2013533.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Bernardo\u00a0K Pagnoncelli Domingo Ram\u00edrez Hamed Rahimian and Arturo Cifuentes. 2023. A synthetic data-plus-features driven approach for portfolio optimization. Computational Economics 62 1 (2023) 187\u2013204.","DOI":"10.1007\/s10614-022-10274-2"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Jos\u00e9-Manuel Pe\u00f1a Fernando Su\u00e1rez Omar Larr\u00e9 Domingo Ram\u00edrez and Arturo Cifuentes. 2024. A modified CTGAN-plus-features-based method for optimal asset allocation. Quantitative Finance 24 3-4 (2024) 465\u2013479.","DOI":"10.1080\/14697688.2024.2329194"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CIFEr52523.2022.9776121"},{"key":"e_1_3_3_1_33_2","unstructured":"M\u00e9lanie Rey. 2015. Copula models in machine learning. Ph.\u00a0D. Dissertation. University_of_Basel."},{"key":"e_1_3_3_1_34_2","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1707.06347 (2017)."},{"key":"e_1_3_3_1_35_2","unstructured":"Kevin Sheppard. 2023. ARCH: Autoregressive Conditional Heteroskedasticity models in Python. https:\/\/github.com\/bashtage\/arch Version 5.3.1."},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"David Silver Aja Huang Chris\u00a0J Maddison Arthur Guez Laurent Sifre George Van Den\u00a0Driessche Julian Schrittwieser Ioannis Antonoglou Veda Panneershelvam Marc Lanctot et\u00a0al. 2016. Mastering the game of Go with deep neural networks and tree search. nature 529 7587 (2016) 484\u2013489.","DOI":"10.1038\/nature16961"},{"key":"e_1_3_3_1_37_2","unstructured":"Srijan Sood Kassiani Papasotiriou Marius Vaiciulis and Tucker Balch. 2023. Deep Reinforcement Learning for Optimal Portfolio Allocation: A Comparative Study with Mean-Variance Optimization. FinPlan 2023 2023 (2023) 21."},{"key":"e_1_3_3_1_38_2","unstructured":"Sonam Srivastava et\u00a0al. 2020. Deep reinforcement learning for asset allocation in us equities. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.04404 (2020)."},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Robert\u00a0E Whaley. 2000. The investor fear gauge. Journal of portfolio management 26 3 (2000) 12.","DOI":"10.3905\/jpm.2000.319728"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Jimmy Ming-Tai Wu Sheng-Hao Lin Jia-Hao Syu and Mu-En Wu. 2022. Embedded draw-down constraint reward function for deep reinforcement learning. Applied Soft Computing 125 (2022) 109150.","DOI":"10.1016\/j.asoc.2022.109150"}],"event":{"name":"ICAIF '25: 6th ACM International Conference on AI in Finance","location":"Singapore Singapore","acronym":"ICAIF '25"},"container-title":["Proceedings of the 6th ACM International Conference on AI in Finance"],"original-title":[],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:29:03Z","timestamp":1763105343000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3768292.3770340"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":39,"alternative-id":["10.1145\/3768292.3770340","10.1145\/3768292"],"URL":"https:\/\/doi.org\/10.1145\/3768292.3770340","relation":{},"subject":[],"published":{"date-parts":[[2025,11,14]]},"assertion":[{"value":"2025-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}