{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T17:57:32Z","timestamp":1770746252619,"version":"3.49.0"},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T00:00:00Z","timestamp":1745193600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T00:00:00Z","timestamp":1745193600000},"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":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-025-03854-0","type":"journal-article","created":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T11:19:46Z","timestamp":1745234386000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep Reinforcement Learning in Continuous Action Spaces for Pair Trading: A Comparative Study of A2 C and PPO"],"prefix":"10.1007","volume":"6","author":[{"given":"Cristian","family":"Quintero","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1434-7569","authenticated-orcid":false,"given":"Diego","family":"Leon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javier","family":"Sandoval","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"German","family":"Hernandez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,21]]},"reference":[{"key":"3854_CR1","volume-title":"Quantitative portfolio management. The art and science of statistical arbitrage. Wiley finance series","author":"M Isichenko","year":"2021","unstructured":"Isichenko M. Quantitative portfolio management. The art and science of statistical arbitrage. Wiley finance series. Hoboken: Wiley; 2021."},{"key":"3854_CR2","first-page":"7","volume":"24","author":"L Diego","year":"2023","unstructured":"Diego L. Reinforcement learning for finance: A review. ODEON. 2023;24:7\u201324.","journal-title":"ODEON"},{"issue":"2","key":"3854_CR3","doi-asserted-by":"publisher","first-page":"25","DOI":"10.3905\/jfds.2020.1.030","volume":"2","author":"Z Zhang","year":"2020","unstructured":"Zhang Z, Zohren SRS. Deep reinforcement learning for trading. J Financ Data Sci. 2020;2(2):25\u201340.","journal-title":"J Financ Data Sci"},{"key":"3854_CR4","series-title":"Wiley finance","volume-title":"Pairs trading: quantitative methods and analysis","author":"V Ganapathy","year":"2004","unstructured":"Ganapathy V. Pairs trading: quantitative methods and analysis. Wiley finance. Hoboken: Wiley; 2004."},{"issue":"5","key":"3854_CR5","doi-asserted-by":"publisher","first-page":"631","DOI":"10.1007\/s42979-024-02930-1","volume":"5","author":"D Leon","year":"2024","unstructured":"Leon D, Sandoval J, Cruz A, Hernandez G, Sierra O. Deep heterogeneous automl trend prediction model for algorithmic trading in the USD\/COP Colombian fx market through limit order book (lob). SN Comput Sci. 2024;5(5):631.","journal-title":"SN Comput Sci"},{"key":"3854_CR6","doi-asserted-by":"publisher","unstructured":"Gatev E, Goetzmann WN, Rouwenhorst KG. Pairs trading: Performance of a relative value arbitrage rule 8(3) (2006) https:\/\/doi.org\/10.2139\/ssrn.141615","DOI":"10.2139\/ssrn.141615"},{"key":"3854_CR7","doi-asserted-by":"publisher","DOI":"10.1002\/9781119815068","volume-title":"Reinforcement learning and stochastic optimization: an unified framework for sequential decisions","author":"W Powell","year":"2022","unstructured":"Powell W. Reinforcement learning and stochastic optimization: an unified framework for sequential decisions. Hoboken: Wiley; 2022."},{"key":"3854_CR8","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"2020","unstructured":"Sutton RS, Barto AG. Reinforcement learning: an introduction. London: The MIT Press; 2020."},{"key":"3854_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-4095-0","volume-title":"Deep reinforcement learning: fundamentals, research and applications","author":"H Dong","year":"2020","unstructured":"Dong H, Ding Z, Zhang S. Deep reinforcement learning: fundamentals, research and applications. Singapore: Springer; 2020."},{"key":"3854_CR10","volume-title":"Advances in intelligent signal processing and data mining","year":"2013","unstructured":"Georgieva P, Mihaylova L, Kain LC, editors. Advances in intelligent signal processing and data mining. New York: Springer; 2013."},{"key":"3854_CR11","volume-title":"Foundations of deep reinforcement learning: theory and practice in Python","author":"L Graesser","year":"2020","unstructured":"Graesser L, Keng WL. Foundations of deep reinforcement learning: theory and practice in Python. Boston: Addison-Wesley; 2020."},{"key":"3854_CR12","unstructured":"Sun\u00a0S, Wang\u00a0R, An B. Reinforcement learning for quantitative trading. arXiv:2109.13851 (2021)"},{"key":"3854_CR13","unstructured":"Fischer TG. Reinforcement learning in financial markets - a survey (2018)"},{"key":"3854_CR14","unstructured":"Schulman\u00a0J, Wolski\u00a0F, Dhariwal P, Radford A, Klimov O. Proximal policy optimization algorithms. CoRR arXiv:1707.06347 (2017)"},{"key":"3854_CR15","doi-asserted-by":"crossref","unstructured":"Quintero C, Leon D, Sandoval J, Hernandez G. Reinforcement learning model applied in a pair trading strategy. In: Workshop on Engineering Applications, pp. 31\u201342 (2024). Springer","DOI":"10.1007\/978-3-031-74595-9_3"},{"key":"3854_CR16","doi-asserted-by":"publisher","unstructured":"Huang\u00a0S, Kanervisto\u00a0A, Raffin A, Wang W, Onta\u00f1\u00f3n S, Dossa RFJ. A2c is a special case of ppo (2022) https:\/\/doi.org\/10.48550\/ARXIV.2205.09123","DOI":"10.48550\/ARXIV.2205.09123"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-03854-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-025-03854-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-03854-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T11:19:51Z","timestamp":1745234391000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-025-03854-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,21]]},"references-count":16,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["3854"],"URL":"https:\/\/doi.org\/10.1007\/s42979-025-03854-0","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,21]]},"assertion":[{"value":"23 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human or animal participants.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human and Animal Rights"}},{"value":"There are no human participants in this article and informed consent is not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}}],"article-number":"407"}}