{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T14:02:40Z","timestamp":1781272960909,"version":"3.54.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100008538","name":"UCL Engineering University College London","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008538","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2021.3139510","type":"journal-article","created":{"date-parts":[[2021,12,30]],"date-time":"2021-12-30T15:49:45Z","timestamp":1640879385000},"page":"5024-5036","source":"Crossref","is-referenced-by-count":11,"title":["Reinforcement Learning for Systematic FX Trading"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0063-7103","authenticated-orcid":false,"given":"Gabriel","family":"Borrageiro","sequence":"first","affiliation":[{"name":"Department of Computer Science, University College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6460-0406","authenticated-orcid":false,"given":"Nick","family":"Firoozye","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4588-667X","authenticated-orcid":false,"given":"Paolo","family":"Barucca","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"dempster","year":"1977","journal-title":"J Roy Statist Soc B Statist Methodol"},{"key":"ref38","article-title":"Online learning with radial basis function networks","author":"borrageiro","year":"2021","journal-title":"arXiv 2103 08414"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.112872"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114002"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.112891"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2001.041"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1992.227335"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref34","author":"grinold","year":"2019","journal-title":"Advances in Active Portfolio Management New Developments in Quantitative Investing"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0304-405X(76)90022-2"},{"key":"ref40","article-title":"Machine learning a probabilistic perspective","author":"murphy","year":"2012","journal-title":"Adaptive Computation and Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1017\/9781139061773"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.06.003"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/BRACIS.2019.00074"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICACI49185.2020.9177746"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1201\/b18188"},{"key":"ref18","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1086\/294846"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59410-7_42"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CIFER.2003.1196283"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-8201-6_5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CIFER.1997.618952"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-131X(1998090)17:5\/6<441::AID-FOR707>3.0.CO;2-#"},{"key":"ref29","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.2469\/faj.v63.n5.4837"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1017\/9781139061773","author":"yang","year":"2020","journal-title":"Transfer of Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/34.990138"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065797000422"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/0471221546"},{"key":"ref1","author":"tsay","year":"2019","journal-title":"Nonlinear Time Series Analysis"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2644871"},{"key":"ref22","article-title":"Deep reinforcement learning for trading","author":"zhang","year":"2019","journal-title":"arXiv 1911 10107"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2019.09.013"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.07.005"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/42.4.270"},{"key":"ref23","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref25","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"arXiv 1602 01783"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09665743.pdf?arnumber=9665743","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T07:28:13Z","timestamp":1726385293000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9665743\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3139510","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.16778932","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.16778932.v2","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.16778932.v3","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.16778932.v4","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.16778932.v1","asserted-by":"object"}]},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}