{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T04:27:17Z","timestamp":1743049637960,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030801250"},{"type":"electronic","value":"9783030801267"}],"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\/978-3-030-80126-7_64","type":"book-chapter","created":{"date-parts":[[2021,7,6]],"date-time":"2021-07-06T11:11:23Z","timestamp":1625569883000},"page":"912-926","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Investigating the Robustness and Generalizability of Deep Reinforcement Learning Based Optimal Trade Execution Systems"],"prefix":"10.1007","author":[{"given":"Siyu","family":"Lin","sequence":"first","affiliation":[]},{"given":"Peter A.","family":"Beling","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,7,7]]},"reference":[{"key":"64_CR1","doi-asserted-by":"publisher","first-page":"5","DOI":"10.21314\/JOR.2001.041","volume":"3","author":"R Almgren","year":"2000","unstructured":"Almgren, R., Chriss, N.: Optimal execution of portfolio transactions. J. Risk 3, 5\u201340 (2000)","journal-title":"J. Risk"},{"key":"64_CR2","unstructured":"Fortunato, M., Azar, M.G., Piot, B., Menick, J., Osband, I., Graves, A., Mnih, V., Munos, R., Hassabis, D., Pietquin, O., Blundell, C.: Noisy networks for exploration. In: ICLR (2018)"},{"key":"64_CR3","doi-asserted-by":"crossref","unstructured":"Hendricks, D., Wilcox, D.: A reinforcement learning extension to the Almgren-Chriss framework for optimal trade execution. In: Proceedings from IEEE Conference on Computational Intelligence for Financial Economics and Engineering, pp. 57\u2013464, London, UK. IEEE, March 2014","DOI":"10.1109\/CIFEr.2014.6924109"},{"issue":"8","key":"64_CR4","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"64_CR5","doi-asserted-by":"crossref","unstructured":"Kakade, S.M., Kearns, M., Mansour, Y., Ortiz, L.E.: Competitive algorithms for vwap and limit order trading. In: Proceedings of the ACM Conference on Electronic Commerce, New York, NY (2004)","DOI":"10.1145\/988772.988801"},{"key":"64_CR6","unstructured":"Siyu, L., Beling, P.A.: Optimal liquidation with deep reinforcement learning. In: 33rd Conference on Neural Information Processing Systems (NeurIPS): Deep Reinforcement Learning Workshop, p. 2019. Vancouver, Canada (2019)"},{"key":"64_CR7","doi-asserted-by":"crossref","unstructured":"Lin, S., Beling, P.A.: An end-to-end optimal trade execution framework based on proximal policy optimization. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20, pp. 4548\u20134554. International Joint Conferences on Artificial Intelligence Organization, July 2020","DOI":"10.24963\/ijcai.2020\/627"},{"key":"64_CR8","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. arXiv preprintarXiv:1312.5602 (2013)"},{"key":"64_CR9","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"64_CR10","doi-asserted-by":"crossref","unstructured":"Nevmyvaka, Y., Feng, Y., Kearns, M.: Reinforcement learning for optimal trade execution. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 673\u201368, Pittsburgh, PA, June 2006. Association for Computing Machinery (2006)","DOI":"10.1145\/1143844.1143929"},{"key":"64_CR11","unstructured":"Ning, B., Lin, F.H.T., Jaimungal, S.: Double deep q-learning for optimal execution. arXiv:1812.06600 (2018)"},{"key":"64_CR12","unstructured":"Schulman, J,. Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv:1811.08540v2 (2017)"},{"key":"64_CR13","volume-title":"Reinforcement Learning: An Introduction","author":"R Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"64_CR14","unstructured":"van Hasselt, H.: Double q-learning. In: Advances in Neural Information Processing Systems, pp. 2613\u20132621. Vancouver, British Columbia, Canada, December 2010"},{"key":"64_CR15","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: AAAI Conference on Artificial Intelligence (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"64_CR16","unstructured":"Wang, Z., Schaul, T., Hessel, M., Hasselt, H., Lanctot, M., Freitas, N.: Dueling network architectures for deep reinforcement learning. In: Proceedings of the 33rd International Conference on Machine Learning, pp. 1995\u20132003, New York, NY. JMLR, June 2016"}],"container-title":["Lecture Notes in Networks and Systems","Intelligent Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-80126-7_64","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,3]],"date-time":"2023-01-03T00:31:00Z","timestamp":1672705860000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-80126-7_64"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030801250","9783030801267"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-80126-7_64","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"7 July 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}