{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:30:15Z","timestamp":1757622615208,"version":"3.44.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030865139"},{"type":"electronic","value":"9783030865146"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86514-6_15","type":"book-chapter","created":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T12:05:38Z","timestamp":1631189138000},"page":"237-252","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Continuous-Action Reinforcement Learning for Portfolio Allocation of a Life Insurance Company"],"prefix":"10.1007","author":[{"given":"Carlo","family":"Abrate","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessio","family":"Angius","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gianmarco","family":"De Francisci Morales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefano","family":"Cozzini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesca","family":"Iadanza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laura Li","family":"Puma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simone","family":"Pavanelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alan","family":"Perotti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefano","family":"Pignataro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Silvia","family":"Ronchiadin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,10]]},"reference":[{"issue":"5","key":"15_CR1","doi-asserted-by":"publisher","first-page":"28","DOI":"10.2469\/faj.v48.n5.28","volume":"48","author":"F Black","year":"1992","unstructured":"Black, F., Litterman, R.: Global portfolio optimization. Financ. Anal. J. 48(5), 28\u201343 (1992)","journal-title":"Financ. Anal. J."},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Buhler, H., Gonon, L., Teichmann, J., Wood, B.: Deep hedging (2018)","DOI":"10.2139\/ssrn.3120710"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Cox, J.C., Ingersoll, J.E., Ross, S.A.: A theory of the term structure of interest rates. Econometrica 53(2), 385\u2013407 (1985). ISSN 00129682, 14680262","DOI":"10.2307\/1911242"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"De Asis, K., Chan, A., Pitis, S., Sutton, R.S., Graves, D.: Fixed-horizon temporal difference methods for stable reinforcement learning. arXiv preprint arXiv:1909.03906 (2019)","DOI":"10.1609\/aaai.v34i04.5784"},{"issue":"5","key":"15_CR5","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1287\/mnsc.16.5.281","volume":"16","author":"EV Denardo","year":"1970","unstructured":"Denardo, E.V.: On linear programming in a Markov decision problem. Manag. Sci. 16(5), 281\u2013288 (1970)","journal-title":"Manag. Sci."},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Doob, J.L.: The Brownian movement and stochastic equations. Ann. Math. 351\u2013369 (1942)","DOI":"10.2307\/1968873"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Fontoura, A., Haddad, D., Bezerra, E.: A deep reinforcement learning approach to asset-liability management. In: 2019 8th Brazilian Conference on Intelligent Systems (BRACIS), pp. 216\u2013221. IEEE (2019)","DOI":"10.1109\/BRACIS.2019.00046"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Halperin, I.: QLBS: Q-learner in the Black-Scholes(-Merton) worlds. arXiv preprint arXiv:1712.04609 (2017)","DOI":"10.2139\/ssrn.3087076"},{"issue":"15","key":"15_CR9","doi-asserted-by":"publisher","first-page":"2121","DOI":"10.1016\/j.ins.2005.10.009","volume":"176","author":"O Jangmin","year":"2006","unstructured":"Jangmin, O., Lee, J., Lee, J.W., Zhang, B.T.: Adaptive stock trading with dynamic asset allocation using reinforcement learning. Inf. Sci. 176(15), 2121\u20132147 (2006)","journal-title":"Inf. Sci."},{"key":"15_CR10","unstructured":"Jiang, N., Kulesza, A., Singh, S., Lewis, R.: The dependence of effective planning horizon on model accuracy. In: Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2015, Richland, SC, pp. 1181\u20131189. International Foundation for Autonomous Agents and Multiagent Systems (2015). ISBN 9781450334136"},{"key":"15_CR11","unstructured":"Krabichler, T., Teichmann, J.: Deep replication of a runoff portfolio (2020)"},{"key":"15_CR12","unstructured":"Leibowitz, M., Fabozzi, F.J., Sharpe, W.: Investing: The Collected Works of Martin L. Leibowitz. Probus Professional Pub (1992)"},{"issue":"39","key":"15_CR13","first-page":"1","volume":"17","author":"S Levine","year":"2016","unstructured":"Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17(39), 1\u201340 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"15_CR14","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Mansley, C., Weinstein, A., Littman, M.: Sample-based planning for continuous action Markov decision processes. In: Twenty-First International Conference on Automated Planning and Scheduling (2011)","DOI":"10.1609\/icaps.v21i1.13484"},{"key":"15_CR16","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1007\/978-1-4612-4120-1_14","volume-title":"Systems and Control in the Twenty-First Century","author":"SI Marcus","year":"1997","unstructured":"Marcus, S.I., Fern\u00e1ndez-Gaucherand, E., Hern\u00e1ndez-Hernandez, D., Coraluppi, S., Fard, P.: Risk sensitive Markov decision processes. In: Byrnes, C.I., Datta, B.N., Martin, C.F., Gilliam, D.S. (eds.) Systems and Control in the Twenty-First Century. PSCT, vol. 22, pp. 263\u2013279. Springer, Heidelberg (1997). https:\/\/doi.org\/10.1007\/978-1-4612-4120-1_14"},{"issue":"1","key":"15_CR17","first-page":"77","volume":"7","author":"H Markowitz","year":"1952","unstructured":"Markowitz, H.: Portfolio selection. J. Financ. 7(1), 77\u201391 (1952)","journal-title":"J. Financ."},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015). ISSN 00280836","DOI":"10.1038\/nature14236"},{"issue":"4","key":"15_CR19","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1109\/72.935097","volume":"12","author":"J Moody","year":"2001","unstructured":"Moody, J., Saffell, M.: Learning to trade via direct reinforcement. IEEE Trans. Neural Netw. 12(4), 875\u201389 (2001)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"5\u20136","key":"15_CR20","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1002\/(SICI)1099-131X(1998090)17:5\/6<441::AID-FOR707>3.0.CO;2-#","volume":"17","author":"J Moody","year":"1998","unstructured":"Moody, J., Wu, L., Liao, Y., Saffell, M.: Performance functions and reinforcement learning for trading systems and portfolios. J. Forecast. 17(5\u20136), 441\u2013470 (1998)","journal-title":"J. Forecast."},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Nevmyvaka, Y., Feng, Y., Kearns, M.: Reinforcement learning for optimized trade execution. In: Proceedings of the 23rd International Conference on Machine Learning, ICML 2006, pp. 673\u2013680. Association for Computing Machinery, New York (2006)","DOI":"10.1145\/1143844.1143929"},{"key":"15_CR22","unstructured":"Peters, J., Vijayakumar, S., Schaal, S.: Reinforcement learning for humanoid robotics. In: IEEE-RAS International Conference on Humanoid Robots (Humanoids2003), Karlsruhe, Germany, 29\u201330 September (2003). CLMC"},{"key":"15_CR23","unstructured":"Plappert, M., et al.: Parameter space noise for exploration. arXiv preprint arXiv:1706.01905 (2017)"},{"key":"15_CR24","volume-title":"Advances in Financial Machine Learning","author":"ML de Prado","year":"2018","unstructured":"de Prado, M.L.: Advances in Financial Machine Learning, 1st edn. Wiley, Hoboken (2018)","edition":"1"},{"key":"15_CR25","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Hassabis, D.: Mastering the game of go with deep neural networks and tree search. Nature 529, 484\u2013503 (2016)","journal-title":"Nature"},{"key":"15_CR26","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"issue":"4","key":"15_CR27","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1111\/mafi.12281","volume":"30","author":"H Wang","year":"2020","unstructured":"Wang, H., Zhou, X.Y.: Continuous-time mean-variance portfolio selection: a reinforcement learning framework. Math. Financ. 30(4), 1273\u20131308 (2020)","journal-title":"Math. Financ."}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86514-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T22:02:17Z","timestamp":1757368937000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86514-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030865139","9783030865146"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86514-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"10 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bilbao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2021.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"869","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"210","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-9","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}