{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T01:07:13Z","timestamp":1779325633370,"version":"3.51.4"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032214768","type":"print"},{"value":"9783032214775","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-21477-5_5","type":"book-chapter","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:29:01Z","timestamp":1779323341000},"page":"66-79","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hedging American Put Options with Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1671-0355","authenticated-orcid":false,"given":"Reilly","family":"Pickard","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3439-7881","authenticated-orcid":false,"given":"Gordon Finn","family":"Wredenhagen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1420-4323","authenticated-orcid":false,"given":"Julio","family":"DeJesus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8898-5821","authenticated-orcid":false,"given":"Yuri","family":"Lawryshyn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"5_CR1","volume-title":"Options, Futures, and Other Derivatives","author":"JC Hull","year":"2017","unstructured":"Hull, J.C.: Options, Futures, and Other Derivatives, 9th edn. Pearson, Boston (2017)","edition":"9"},{"issue":"3","key":"5_CR2","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1086\/260062","volume":"81","author":"F Black","year":"1973","unstructured":"Black, F., Scholes, M.: The pricing of options and corporate liabilities. J. Polit. Econ. 81(3), 637\u2013654 (1973). https:\/\/doi.org\/10.1086\/260062","journal-title":"J. Polit. Econ."},{"key":"5_CR3","doi-asserted-by":"publisher","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing Atari with Deep Reinforcement Learning. arXiv preprint arXiv:1312.5602 (2013). https:\/\/doi.org\/10.48550\/arXiv.1312.5602","DOI":"10.48550\/arXiv.1312.5602"},{"issue":"7587","key":"5_CR4","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016). https:\/\/doi.org\/10.1038\/nature16961","journal-title":"Nature"},{"key":"5_CR5","doi-asserted-by":"publisher","unstructured":"Lillicrap, T.P., et al.: Continuous Control with Deep Reinforcement Learning. arXiv preprint arXiv:1509.02971 (2015). https:\/\/doi.org\/10.48550\/arXiv.1509.02971","DOI":"10.48550\/arXiv.1509.02971"},{"key":"5_CR6","doi-asserted-by":"publisher","unstructured":"Pickard, R., Lawryshyn, Y.: Deep reinforcement learning for dynamic stock option hedging: a review. Mathematics 11(24) (2023). https:\/\/doi.org\/10.3390\/math11244943","DOI":"10.3390\/math11244943"},{"key":"5_CR7","doi-asserted-by":"publisher","unstructured":"Glau, K., Mahlstedt, M., Potz, C.: A New Approach for American Option Pricing: The Dynamic Chebyshev Method. arXiv preprint arXiv:1806.05579 (2018). https:\/\/doi.org\/10.48550\/arXiv.1806.05579","DOI":"10.48550\/arXiv.1806.05579"},{"key":"5_CR8","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. MIT Press, Cambridge, A Bradford Book (2018)","edition":"2"},{"key":"5_CR9","unstructured":"Watkins, C.J.C.H.: Learning from Delayed Rewards. PhD thesis, King\u2019s College, Cambridge (1989). https:\/\/www.cs.rhul.ac.uk\/~chrisw\/new_thesis.pdf"},{"issue":"1","key":"5_CR10","doi-asserted-by":"publisher","first-page":"99","DOI":"10.3905\/jod.2020.1.108","volume":"28","author":"I Halperin","year":"2020","unstructured":"Halperin, I.: QLBS: Q-learner in the black-scholes(-merton) worlds. J. Deriv. 28(1), 99\u2013122 (2020). https:\/\/doi.org\/10.3905\/jod.2020.1.108","journal-title":"J. Deriv."},{"issue":"1","key":"5_CR11","doi-asserted-by":"publisher","first-page":"159","DOI":"10.3905\/jfds.2019.1.1.159","volume":"1","author":"PN Kolm","year":"2019","unstructured":"Kolm, P.N., Ritter, G.: Dynamic replication and hedging: a reinforcement learning approach. J. Financ. Data Sci. 1(1), 159\u2013171 (2019). https:\/\/doi.org\/10.3905\/jfds.2019.1.1.159","journal-title":"J. Financ. Data Sci."},{"issue":"4","key":"5_CR12","doi-asserted-by":"publisher","first-page":"44","DOI":"10.3905\/jfds.2020.1.045","volume":"2","author":"J Du","year":"2020","unstructured":"Du, J., Jin, M., Kolm, P.N., Ritter, G., Wang, Y., Zhang, B.: Deep reinforcement learning for option replication and hedging. J. Financ. Data Sci. 2(4), 44\u201357 (2020). https:\/\/doi.org\/10.3905\/jfds.2020.1.045","journal-title":"J. Financ. Data Sci."},{"key":"5_CR13","doi-asserted-by":"publisher","unstructured":"Giurca, A., Borovkova, S.: Delta Hedging of Derivatives Using Deep Reinforcement Learning. SSRN preprint SSRN:3847272 (2021). https:\/\/doi.org\/10.2139\/ssrn.3847272","DOI":"10.2139\/ssrn.3847272"},{"issue":"1","key":"5_CR14","doi-asserted-by":"publisher","first-page":"10","DOI":"10.3905\/jfds.2020.1.052","volume":"3","author":"J Cao","year":"2021","unstructured":"Cao, J., Chen, J., Hull, J., Poulos, Z.: Deep hedging of derivatives using reinforcement learning. J. Financ. Data Sci. 3(1), 10\u201327 (2021). https:\/\/doi.org\/10.3905\/jfds.2020.1.052","journal-title":"J. Financ. Data Sci."},{"key":"5_CR15","doi-asserted-by":"publisher","unstructured":"Cao, J., et al.: Gamma and vega hedging using deep distributional reinforcement learning. Front. Artif. Intell. 6, Article 1129370 (2023). https:\/\/doi.org\/10.3389\/frai.2023.1129370","DOI":"10.3389\/frai.2023.1129370"},{"key":"5_CR16","doi-asserted-by":"publisher","unstructured":"Assa, H., Kenyon, C., Zhang, H.: Assessing Reinforcement Delta Hedging. SSRN preprint SSRN:3918375 (2021). https:\/\/doi.org\/10.2139\/ssrn.3918375","DOI":"10.2139\/ssrn.3918375"},{"issue":"5","key":"5_CR17","doi-asserted-by":"publisher","first-page":"60","DOI":"10.3905\/jod.2022.1.156","volume":"29","author":"W Xu","year":"2022","unstructured":"Xu, W., Dai, B.: Delta-Gamma\u2013like hedging with transaction cost under reinforcement learning technique. J. Deriv. 29(5), 60\u201382 (2022). https:\/\/doi.org\/10.3905\/jod.2022.1.156","journal-title":"J. Deriv."},{"key":"5_CR18","doi-asserted-by":"publisher","unstructured":"Fathi, A., Hientzsch, B.: A comparison of reinforcement learning and deep trajectory based stochastic control agents for stepwise mean-variance hedging. arXiv preprint arXiv:2302.07996 (2023). https:\/\/doi.org\/10.48550\/arXiv.2302.07996","DOI":"10.48550\/arXiv.2302.07996"},{"key":"5_CR19","doi-asserted-by":"publisher","unstructured":"Vittori, E., Trapletti, M., Restelli, M.: Option hedging with risk averse reinforcement learning. In: Proceedings of the ACM International Conference on AI in Finance (ICAIF \u201920), New York, NY, USA, 8 pages (2020). https:\/\/doi.org\/10.1145\/3383455.3422532","DOI":"10.1145\/3383455.3422532"},{"key":"5_CR20","doi-asserted-by":"publisher","unstructured":"Zheng, C., He, J., Yang, C.: Option Dynamic Hedging Using Reinforcement Learning. arXiv preprint arXiv:2306.10743 (2023). https:\/\/doi.org\/10.48550\/arXiv.2306.10743","DOI":"10.48550\/arXiv.2306.10743"},{"issue":"January","key":"5_CR21","first-page":"84","volume":"1","author":"P Hagan","year":"2002","unstructured":"Hagan, P., Kumar, D., Lesniewski, A., Woodward, D.: Managing smile risk. Wilmott Magazine 1(January), 84\u2013108 (2002)","journal-title":"Wilmott Magazine"},{"issue":"2","key":"5_CR22","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1093\/rfs\/6.2.327","volume":"6","author":"SL Heston","year":"1993","unstructured":"Heston, S.L.: A closed-form solution for options with stochastic volatility with applications to bond and currency options. Rev. Financ. Stud. 6(2), 327\u2013343 (1993). https:\/\/doi.org\/10.1093\/rfs\/6.2.327","journal-title":"Rev. Financ. Stud."},{"issue":"1","key":"5_CR23","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1080\/14697688.2022.2136037","volume":"23","author":"O Mikkil\u00e4","year":"2023","unstructured":"Mikkil\u00e4, O., Kanniainen, J.: Empirical deep hedging. Quant. Finance 23(1), 111\u2013122 (2023). https:\/\/doi.org\/10.1080\/14697688.2022.2136037","journal-title":"Quant. Finance"},{"key":"5_CR24","doi-asserted-by":"publisher","unstructured":"Murray, P., Wood, B., Buehler, H., Wiese, M., Pakkanen, M.S.: Deep hedging: continuous reinforcement learning for hedging of general portfolios across multiple risk aversions. In: Proceedings of the 3rd ACM International Conference on AI in Finance (ICAIF \u201922), pp. 361\u2013368. ACM, New York (2022). https:\/\/doi.org\/10.1145\/3533271.3561731","DOI":"10.1145\/3533271.3561731"},{"key":"5_CR25","doi-asserted-by":"publisher","unstructured":"Xiao, B., Yao, W., Zhou, X.: Optimal option hedging with policy gradient. In: Proceedings of the 2021 IEEE International Conference on Data Mining Workshops (ICDMW), pp. 1112\u20131119. IEEE, Auckland (2021). https:\/\/doi.org\/10.1109\/ICDMW53433.2021.00145","DOI":"10.1109\/ICDMW53433.2021.00145"},{"issue":"12","key":"5_CR26","doi-asserted-by":"publisher","first-page":"7877","DOI":"10.1007\/s00500-021-05801-6","volume":"25","author":"U Pham","year":"2021","unstructured":"Pham, U., Luu, Q., Tran, H.: Multi-agent reinforcement learning approach for hedging portfolio problem. Soft. Comput. 25(12), 7877\u20137885 (2021). https:\/\/doi.org\/10.1007\/s00500-021-05801-6","journal-title":"Soft. Comput."},{"key":"5_CR27","doi-asserted-by":"publisher","DOI":"10.3905\/jfds.2023.1.124","author":"P Liu","year":"2023","unstructured":"Liu, P.: A review on derivative hedging using reinforcement learning. J. Financial Data Sci. (2023). https:\/\/doi.org\/10.3905\/jfds.2023.1.124","journal-title":"J. Financial Data Sci."},{"key":"5_CR28","doi-asserted-by":"publisher","unstructured":"Smith, L.N.: A Disciplined Approach to Neural Network Hyper-Parameters: Part 1 -- Learning Rate, Batch Size, Momentum, and Weight Decay (2018). https:\/\/doi.org\/10.48550\/arXiv.1803.09820","DOI":"10.48550\/arXiv.1803.09820"},{"issue":"4","key":"5_CR29","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1016\/j.physa.2008.10.012","volume":"388","author":"I Florescu","year":"2009","unstructured":"Florescu, I., P\u00e3s\u00e3ric\u00e3, C.G.: A study about the existence of the leverage effect in stochastic volatility models. Physica A 388(4), 419\u2013432 (2009). https:\/\/doi.org\/10.1016\/j.physa.2008.10.012","journal-title":"Physica A"}],"container-title":["Lecture Notes in Computer Science","Machine Learning, Optimization, and Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-21477-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:29:04Z","timestamp":1779323344000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21477-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032214768","9783032214775"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21477-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LOD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Artificial Intelligence Symposium","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Castiglione della Pescaia","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mod2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lod2025.icas.events","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}