{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T02:17:45Z","timestamp":1783649865313,"version":"3.55.0"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1109\/tnnls.2020.2997523","type":"journal-article","created":{"date-parts":[[2020,6,9]],"date-time":"2020-06-09T20:53:11Z","timestamp":1591735991000},"page":"2837-2846","source":"Crossref","is-referenced-by-count":58,"title":["Price Trailing for Financial Trading Using Deep Reinforcement Learning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9528-9702","authenticated-orcid":false,"given":"Avraam","family":"Tsantekidis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1177-9139","authenticated-orcid":false,"given":"Nikolaos","family":"Passalis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3383-4381","authenticated-orcid":false,"given":"Anastasia-Sotiria","family":"Toufa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1402-4017","authenticated-orcid":false,"given":"Konstantinos","family":"Saitas-Zarkias","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1702-9152","authenticated-orcid":false,"given":"Stergios","family":"Chairistanidis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1288-3667","authenticated-orcid":false,"given":"Anastasios","family":"Tefas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref11","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2017","journal-title":"arXiv 1710 02298"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7965896"},{"key":"ref13","first-page":"565","article-title":"Reward shaping in episodic reinforcement learning","author":"grze?","year":"2017","journal-title":"Adaptive Agents and Multi-Agent Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.040"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.02.006"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CBI.2017.23"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3213389"},{"key":"ref28","first-page":"2892","article-title":"Distributional reinforcement learning with quantile regression","author":"dabney","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref27","author":"sutton","year":"2011","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081663"},{"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":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv 1506 02438 [cs]"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2005.10.012"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref7","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2015.05.013"},{"key":"ref9","first-page":"5","article-title":"Deep reinforcement learning with double q-learning","volume":"2","author":"van hasselt","year":"2016","journal-title":"Proc AAAI"},{"key":"ref1","author":"haynes","year":"2015","journal-title":"Automated trading in futures markets"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2869225"},{"key":"ref22","first-page":"917","article-title":"Reinforcement learning for trading","author":"moody","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/72.935097"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1086\/209650"},{"key":"ref23","author":"nison","year":"2001","journal-title":"Japanese Candlestick Charting Techniques A Contemporary Guide to the Ancient Investment Techniques of the Far East"},{"key":"ref26","article-title":"Financial trading as a game: A deep reinforcement learning approach","author":"yi huang","year":"2018","journal-title":"arXiv 1807 02787"},{"key":"ref25","author":"murphy","year":"1999","journal-title":"Technical Analysis of the Financial Markets A Comprehensive Guide to Trading Methods and Applications"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9475542\/09112694.pdf?arnumber=9112694","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:02Z","timestamp":1652194382000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9112694\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":29,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2997523","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7]]}}}