{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T21:50:35Z","timestamp":1767909035808,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"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":[[2024,11,14]]},"DOI":"10.1145\/3677052.3698668","type":"proceedings-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T06:38:06Z","timestamp":1731566286000},"page":"370-378","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["EX-DRL: Hedging Against Heavy Losses with EXtreme Distributional Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2533-232X","authenticated-orcid":false,"given":"Parvin","family":"Malekzadeh","sequence":"first","affiliation":[{"name":"University of Toronto, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2427-7413","authenticated-orcid":false,"given":"Zissis","family":"Poulos","sequence":"additional","affiliation":[{"name":"York University, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8528-220X","authenticated-orcid":false,"given":"Jacky","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Toronto, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4796-7476","authenticated-orcid":false,"given":"Zeyu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Toronto, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3647-5473","authenticated-orcid":false,"given":"Konstantinos N","family":"Plataniotis","sequence":"additional","affiliation":[{"name":"University of Toronto, Canada"}]}],"member":"320","published-online":{"date-parts":[[2024,11,14]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"S Abilasha Sahely Bhadra Ahmed\u00a0Zaheer Dadarkar and P Deepak. 2022. Deep Extreme Mixture Model for Time Series Forecasting. In CIKM. 1726\u20131735.","DOI":"10.1145\/3511808.3557282"},{"key":"e_1_3_2_1_2_1","first-page":"18307","article-title":"Understanding the under-coverage bias in uncertainty estimation","volume":"34","author":"Bai Yu","year":"2021","unstructured":"Yu Bai, Song Mei, Huan Wang, and Caiming Xiong. 2021. Understanding the under-coverage bias in uncertainty estimation. Advances in Neural Information Processing Systems 34 (2021), 18307\u201318319.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","volume-title":"International conference on machine learning. PMLR, 449\u2013458","author":"Bellemare G","year":"2017","unstructured":"Marc\u00a0G Bellemare, Will Dabney, and R\u00e9mi Munos. 2017. A distributional perspective on reinforcement learning. In International conference on machine learning. PMLR, 449\u2013458."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10687-019-00364-0"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00780-014-0234-y"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1086\/260062"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2019.1571683"},{"key":"e_1_3_2_1_8_1","volume-title":"Deep bellman hedging. arXiv preprint arXiv:2207.00932","author":"Buehler Hans","year":"2022","unstructured":"Hans Buehler, Phillip Murray, and Ben Wood. 2022. Deep bellman hedging. arXiv preprint arXiv:2207.00932 (2022)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2023.1129370"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.3905\/jfds.2020.1.052"},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. PMLR, 1096\u20131105","author":"Dabney Will","year":"2018","unstructured":"Will Dabney, Georg Ostrovski, David Silver, and R\u00e9mi Munos. 2018. Implicit quantile networks for distributional reinforcement learning. In International conference on machine learning. PMLR, 1096\u20131105."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626852"},{"key":"e_1_3_2_1_14_1","volume-title":"Catastrophic-risk-aware reinforcement learning with extreme-value-theory-based policy gradients. arXiv preprint arXiv:2406.15612","author":"Davar Parisa","year":"2024","unstructured":"Parisa Davar, Fr\u00e9d\u00e9ric Godin, and Jose Garrido. 2024. Catastrophic-risk-aware reinforcement learning with extreme-value-theory-based policy gradients. arXiv preprint arXiv:2406.15612 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626913"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.3905\/jod.2020.1.108"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1080\/07350015.2021.1874390"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2957806"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.3905\/jfds.2019.1.1.159"},{"key":"e_1_3_2_1_20_1","unstructured":"Yuxi Li Csaba Szepesvari and Dale Schuurmans. 2009. Learning exercise policies for american options. In Artificial intelligence and statistics. PMLR 352\u2013359."},{"key":"e_1_3_2_1_21_1","first-page":"20218","article-title":"Uncertainty-aware reinforcement learning for risk-sensitive player evaluation in sports game","volume":"35","author":"Liu Guiliang","year":"2022","unstructured":"Guiliang Liu, Yudong Luo, Oliver Schulte, and Pascal Poupart. 2022. Uncertainty-aware reinforcement learning for risk-sensitive player evaluation in sports game. Advances in Neural Information Processing Systems 35 (2022), 20218\u201320231.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_22_1","first-page":"60922","article-title":"An alternative to variance: Gini deviation for risk-averse policy gradient","volume":"36","author":"Luo Yudong","year":"2023","unstructured":"Yudong Luo, Guiliang Liu, Pascal Poupart, and Yangchen Pan. 2023. An alternative to variance: Gini deviation for risk-averse policy gradient. Advances in Neural Information Processing Systems 36 (2023), 60922\u201360946.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","volume-title":"Conservative offline distributional reinforcement learning. Advances in neural information processing systems 34","author":"Ma Yecheng","year":"2021","unstructured":"Yecheng Ma, Dinesh Jayaraman, and Osbert Bastani. 2021. Conservative offline distributional reinforcement learning. Advances in neural information processing systems 34 (2021), 19235\u201319247."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095594"},{"key":"e_1_3_2_1_25_1","volume-title":"Active Inference and Reinforcement Learning: A Unified Inference on Continuous State and Action Spaces under Partial Observability. Neural Computation","author":"Malekzadeh Parvin","year":"2024","unstructured":"Parvin Malekzadeh and Konstantinos\u00a0N Plataniotis. 2024. Active Inference and Reinforcement Learning: A Unified Inference on Continuous State and Action Spaces under Partial Observability. Neural Computation (2024), 1\u201364."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447501"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3007951"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2021.1993614"},{"key":"e_1_3_2_1_29_1","volume-title":"Theory of rational option pricing. The Bell Journal of economics and management science","author":"Merton C","year":"1973","unstructured":"Robert\u00a0C Merton. 1973. Theory of rational option pricing. The Bell Journal of economics and management science (1973), 141\u2013183."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533271.3561731"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2020.2980448"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1093\/jjfinec\/nbaa022"},{"key":"e_1_3_2_1_33_1","volume-title":"Statistical inference using extreme order statistics. the Annals of Statistics","author":"James","year":"1975","unstructured":"James Pickands\u00a0III. 1975. Statistical inference using extreme order statistics. the Annals of Statistics (1975), 119\u2013131."},{"key":"e_1_3_2_1_34_1","volume-title":"Hedging Beyond the Mean: A Distributional Reinforcement Learning Perspective for Hedging Portfolios with Structured Products. arXiv preprint arXiv:2407.10903","author":"Sharma Anil","year":"2024","unstructured":"Anil Sharma, Freeman Chen, Jaesun Noh, Julio DeJesus, and Mario Schlener. 2024. Hedging Beyond the Mean: A Distributional Reinforcement Learning Perspective for Hedging Portfolios with Structured Products. arXiv preprint arXiv:2407.10903 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Extreme market risk and extreme value theory. Mathematics and computers in simulation 94","author":"Singh K","year":"2013","unstructured":"Abhay\u00a0K Singh, David\u00a0E Allen, and Powell\u00a0J Robert. 2013. Extreme market risk and extreme value theory. Mathematics and computers in simulation 94 (2013), 310\u2013328."},{"key":"e_1_3_2_1_36_1","volume-title":"Uncertainty in Artificial Intelligence. PMLR","author":"Troop Dylan","year":"2021","unstructured":"Dylan Troop, Fr\u00e9d\u00e9ric Godin, and Jia\u00a0Yuan Yu. 2021. Bias-corrected peaks-over-threshold estimation of the cvar. In Uncertainty in Artificial Intelligence. PMLR, 1809\u20131818."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422532"},{"key":"e_1_3_2_1_38_1","first-page":"893","article-title":"Extreme quantile estimation based on the tail single-index model","volume":"32","author":"Xu Wen","year":"2022","unstructured":"Wen Xu, Huixia\u00a0Judy Wang, and Deyuan Li. 2022. Extreme quantile estimation based on the tail single-index model. Statistica Sinica 32, 2 (2022), 893\u2013914.","journal-title":"Statistica Sinica"}],"event":{"name":"ICAIF '24: 5th ACM International Conference on AI in Finance","location":"Brooklyn NY USA","acronym":"ICAIF '24"},"container-title":["Proceedings of the 5th ACM International Conference on AI in Finance"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677052.3698668","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3677052.3698668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:13:53Z","timestamp":1755882833000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677052.3698668"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,14]]},"references-count":38,"alternative-id":["10.1145\/3677052.3698668","10.1145\/3677052"],"URL":"https:\/\/doi.org\/10.1145\/3677052.3698668","relation":{},"subject":[],"published":{"date-parts":[[2024,11,14]]},"assertion":[{"value":"2024-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}