{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T16:44:50Z","timestamp":1765039490836,"version":"3.44.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683161","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"3067-3071","source":"Crossref","is-referenced-by-count":29,"title":["Deep Reinforcement Learning for Financial Trading Using Price Trailing"],"prefix":"10.1109","author":[{"given":"Konstantinos Saitas","family":"Zarkias","sequence":"first","affiliation":[{"name":"School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolaos","family":"Passalis","sequence":"additional","affiliation":[{"name":"School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Avraam","family":"Tsantekidis","sequence":"additional","affiliation":[{"name":"School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anastasios","family":"Tefas","sequence":"additional","affiliation":[{"name":"School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/72.935097"},{"key":"ref11","first-page":"5","article-title":"Deep reinforcement learning with double q-learning","volume":"2","author":"hasselt","year":"2016","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3213389"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2872598"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(03)00372-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2011.07.001"},{"key":"ref16","article-title":"Temporal attention-augmented bilinear network for financial time-series data analysis","author":"tran","year":"2018","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"ref17","first-page":"917","article-title":"Reinforcement learning for trading","author":"moody","year":"1999","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459203"},{"key":"ref19","first-page":"846","article-title":"Max-margin multiple-instance dictionary learning","author":"wang","year":"2013","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref4","first-page":"1","article-title":"Classification-based financial markets prediction using deep neural networks","author":"dixon","year":"2016","journal-title":"Algorithmic Finance"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.02.006"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0180944"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CBI.2017.23"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-131X(1998090)17:5\/6<441::AID-FOR707>3.0.CO;2-#"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.040"},{"journal-title":"Paul Wilmott on Quantitative Finance","year":"2013","author":"wilmott","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081663"},{"key":"ref20","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, UK","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683161.pdf?arnumber=8683161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T18:19:25Z","timestamp":1757009965000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683161\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683161","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}