{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:14:47Z","timestamp":1766067287966,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,6,5]]},"DOI":"10.1109\/cist49399.2021.9357266","type":"proceedings-article","created":{"date-parts":[[2021,3,29]],"date-time":"2021-03-29T21:32:53Z","timestamp":1617053573000},"page":"424-429","source":"Crossref","is-referenced-by-count":3,"title":["Deep Deterministic Policy Gradient for Portfolio Management"],"prefix":"10.1109","author":[{"given":"Firdaous","family":"Khemlichi","sequence":"first","affiliation":[]},{"given":"Hiba","family":"Chougrad","sequence":"additional","affiliation":[]},{"given":"Youness Idrissi","family":"Khamlichi","sequence":"additional","affiliation":[]},{"given":"Abdessamad","family":"el Boushaki","sequence":"additional","affiliation":[]},{"given":"Safae Elhaj","family":"Ben Ali","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932842"},{"key":"ref11","first-page":"799","article-title":"Autonomous helicopter flight via reinforcement learning","author":"kim","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"137","article-title":"BOXES: An experiment in adaptive control","volume":"2","author":"michie","year":"1968","journal-title":"Machine Intelligence"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3618-5_3"},{"key":"ref14","first-page":"173","article-title":"Learning hand-eye coordination for robotic grasping with large-scale data collection","author":"levine","year":"2016","journal-title":"International Symposium on Experimental Robotics"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989379"},{"journal-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref16"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-131X(1998090)17:5\/6<441::AID-FOR707>3.0.CO;2-#"},{"key":"ref19","volume":"33","author":"bertoluzzo","year":"2012","journal-title":"Reinforcement Learning for automatic financial trading Introduction and some applications"},{"journal-title":"Keras Reinforcement Learning Projects 9 Projects Exploring Popular Reinforcement Learning Techniques to Build Self-Learning Agents","year":"2018","author":"ciaburro","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/data4030110"},{"journal-title":"Keras Reinforcement Learning Projects 9 Projects Exploring Popular Reinforcement Learning Techniques to Build Self-Learning Agents","year":"2018","author":"ciaburro","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref6"},{"journal-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITAIC.2019.8785463"},{"key":"ref8","first-page":"1","article-title":"An application of reinforcement learning to aerobatic helicopter flight","author":"abbeel","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.7b00492"},{"key":"ref1","volume":"49","author":"li","year":"0","journal-title":"OLPS A Toolbox for On-Line Portfolio Selection"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S1386-4181(97)00012-8"},{"journal-title":"An investigation into the use of reinforcement learning techniques within the algorithmic trading domain","year":"2015","author":"cumming","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/72.935097"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553453"},{"journal-title":"Deep Reinforcement Learning-based Portfolio Management [m]","year":"2019","author":"kanwar","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8285188"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"}],"event":{"name":"2020 6th IEEE Congress on Information Science and Technology (CiSt)","start":{"date-parts":[[2021,6,5]]},"location":"Agadir - Essaouira, Morocco","end":{"date-parts":[[2021,6,12]]}},"container-title":["2020 6th IEEE Congress on Information Science and Technology (CiSt)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9357063\/9357166\/09357266.pdf?arnumber=9357266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,8]],"date-time":"2021-06-08T17:50:31Z","timestamp":1623174631000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9357266\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/cist49399.2021.9357266","relation":{},"subject":[],"published":{"date-parts":[[2020,6,5]]}}}