{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T23:24:10Z","timestamp":1775085850227,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T00:00:00Z","timestamp":1716163200000},"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":[[2024,5,20]]},"DOI":"10.1145\/3658271.3658282","type":"proceedings-article","created":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T10:26:23Z","timestamp":1716459983000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Impact of combinatorial optimization on reinforcement learning for stock trading in financial markets"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4559-9878","authenticated-orcid":false,"given":"Guilherme Dourado","family":"Santos","sequence":"first","affiliation":[{"name":"School of Arts, Sciences and Humanities, University of Sao Paulo, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5483-5466","authenticated-orcid":false,"given":"Karla Roberta","family":"Lima","sequence":"additional","affiliation":[{"name":"School of Arts, Sciences and Humanities, University of Sao Paulo, Brazil"}]}],"member":"320","published-online":{"date-parts":[[2024,5,23]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Dynamic Programming","author":"Bellman E.","unstructured":"Richard\u00a0E. Bellman. 1957. Dynamic Programming. Princeton University Press. https:\/\/press.princeton.edu\/books\/paperback\/9780691146683\/dynamic-programming"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206938"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"Quang-Vinh Dang. 2019. Reinforcement Learning in Stock Trading. (2019). https:\/\/doi.org\/10.1007\/978-3-030-38364-0_28","DOI":"10.1007\/978-3-030-38364-0_28"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.12988\/ams.2016.58541"},{"key":"e_1_3_2_1_6_1","volume-title":"2019 International Joint Conference on Neural Networks (IJCNN). IEEE, 1\u20138.","author":"Jia WU","year":"2019","unstructured":"WU Jia, WANG Chen, Lidong Xiong, and SUN Hongyong. 2019. Quantitative trading on stock market based on deep reinforcement learning. In 2019 International Joint Conference on Neural Networks (IJCNN). IEEE, 1\u20138."},{"key":"e_1_3_2_1_7_1","volume-title":"On the complexity of policy iteration. arXiv preprint arXiv:1301.6718","author":"Mansour Yishay","year":"2013","unstructured":"Yishay Mansour and Satinder Singh. 2013. On the complexity of policy iteration. arXiv preprint arXiv:1301.6718 (2013)."},{"key":"e_1_3_2_1_8_1","volume-title":"International conference on machine learning. PMLR","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih, Adria\u00a0Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous methods for deep reinforcement learning. In International conference on machine learning. PMLR, 1928\u20131937."},{"key":"e_1_3_2_1_9_1","volume-title":"Technical analysis of the financial markets: A comprehensive guide to trading methods and applications","author":"Murphy J","unstructured":"John\u00a0J Murphy. 1999. Technical analysis of the financial markets: A comprehensive guide to trading methods and applications. Penguin."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887.fmatter"},{"key":"e_1_3_2_1_11_1","volume-title":"Reinforcement Learning for Quantitative Trading. ArXiv abs\/2109.13851","author":"Sun Shuo","year":"2021","unstructured":"Shuo Sun, R. Wang, and Bo An. 2021. Reinforcement Learning for Quantitative Trading. ArXiv abs\/2109.13851 (2021). https:\/\/www.semanticscholar.org\/paper\/f18c3f40f62596337ce79d3d103160d3236498f2"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3625234"},{"key":"e_1_3_2_1_13_1","volume-title":"Machine learning 8, 3-4","author":"Watkins JCH","year":"1992","unstructured":"Christopher\u00a0JCH Watkins and Peter Dayan. 1992. Q-learning. Machine learning 8, 3-4 (1992), 279\u2013292."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422540"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Zihao Zhang S. Zohren and Stephen\u00a0J. Roberts. 2019. Deep Reinforcement Learning for Trading. (2019). https:\/\/doi.org\/10.3905\/jfds.2020.1.030","DOI":"10.3905\/jfds.2020.1.030"}],"event":{"name":"SBSI '24: XX Brazilian Symposium on Information Systems","location":"Juiz de Fora Brazil","acronym":"SBSI '24"},"container-title":["Proceedings of the 20th Brazilian Symposium on Information Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658271.3658282","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658271.3658282","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:04:00Z","timestamp":1755867840000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658271.3658282"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,20]]},"references-count":15,"alternative-id":["10.1145\/3658271.3658282","10.1145\/3658271"],"URL":"https:\/\/doi.org\/10.1145\/3658271.3658282","relation":{},"subject":[],"published":{"date-parts":[[2024,5,20]]},"assertion":[{"value":"2024-05-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}