{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:23:53Z","timestamp":1763191433708,"version":"3.45.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228590","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning for Option Hedging Using Quantile Regression and Curriculum Learning with Historical Data Fusion"],"prefix":"10.1109","author":[{"given":"Qiao","family":"Pan","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Donghua University,Shanghai,China"}]},{"given":"Long","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Donghua University,Shanghai,China"}]},{"given":"Zhaoju","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Donghua University,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW53433.2021.00145"},{"article-title":"Reinforcement Learning for Credit Index Option Hedging","year":"2023","author":"Mandelli","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1086\/260062"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.1985.tb02383.x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1111\/mafi.12382"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3905\/jod.2020.1.108"},{"article-title":"Learning from delayed rewards","year":"1989","author":"Watkins","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3905\/jfds.2019.1.1.159"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3905\/jfds.2020.1.045"},{"key":"ref11","article-title":"Playing Atari with Deep Reinforcement Learning","author":"Mnih","year":"2013","journal-title":"Computing Research Repository abs\/1312.5602"},{"key":"ref12","article-title":"Proximal Policy Optimization Algorithms","author":"Schulman","year":"2017","journal-title":"Computing Research Repository abs\/1707.06347"},{"key":"ref13","article-title":"Deep Hedging of Derivatives Using Reinforcement Learning","author":"Jay","year":"2021","journal-title":"RePEc Research Papers in Economics"},{"article-title":"Continuous Control with Deep Reinforcement Learning","volume-title":"International Conference on Learning Representations","author":"Lillicrap","key":"ref14"},{"key":"ref15","article-title":"Optimal hedging with continuous action reinforcement learning","author":"Mikkil\u00e4","year":"2020","journal-title":"semanticscholar"},{"key":"ref16","first-page":"1582","article-title":"Addressing Function Approximation Error in Actor-Critic Methods","volume-title":"International Conference on Machine Learning 80","author":"Fujimoto"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3847272"},{"article-title":"Option Dynamic Hedging Using Reinforcement Learning","year":"2023","author":"Zheng","key":"ref18"},{"key":"ref19","article-title":"Deep Hedging with Market Impact","author":"Neagu","year":"2024","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2022.2136037"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfds.2023.100101"},{"article-title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","year":"2014","author":"Chung","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2307\/2975974.JSTOR2975974"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0304-405X(79)90015-1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1093\/rfs\/6.2.327"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228590.pdf?arnumber=11228590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:21:54Z","timestamp":1763191314000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228590\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228590","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}