{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T12:10:00Z","timestamp":1771503000407,"version":"3.50.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61602149"],"award-info":[{"award-number":["61602149"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018594","name":"Central University Basic Research Fund of China","doi-asserted-by":"publisher","award":["B210202078"],"award-info":[{"award-number":["B210202078"]}],"id":[{"id":"10.13039\/501100018594","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postgraduate Research & Practice Innovation Program of Jiangsu Province","award":["KYCX21_0483"],"award-info":[{"award-number":["KYCX21_0483"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Big Data"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tbdata.2023.3338011","type":"journal-article","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T19:22:39Z","timestamp":1701372159000},"page":"288-300","source":"Crossref","is-referenced-by-count":3,"title":["Hierarchical Deep Reinforcement Learning for VWAP Strategy Optimization"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6690-836X","authenticated-orcid":false,"given":"Xiaodong","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer and Information, Hohai University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0290-4594","authenticated-orcid":false,"given":"Pangjing","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer and Information, Hohai University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0263-7748","authenticated-orcid":false,"given":"Chenxin","family":"Zou","sequence":"additional","affiliation":[{"name":"College of Computer and Information, Hohai University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-471X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computing, Hong Kong Polytechnic University, Hong Kong, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.1988.tb02591.x"},{"key":"ref2","author":"Johnson","year":"2010","journal-title":"Algorithmic Trading & DMA: An Introduction to Direct Access Trading Strategies"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/130924676"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/627"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3374766"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S1386-4181(01)00023-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbankfin.2007.09.023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/988772.988801"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3905\/jot.2006.654300"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/16M1058406"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143929"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/1350486X.2022.2077783"},{"key":"ref13","first-page":"1","article-title":"Reinforced deep Markov models with applications in automatic trading","author":"Ferreira","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2022.2062431"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/21M144640X"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/22M1527209"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1111\/mafi.12388"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1966.10482183"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/0022-1082.00183"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref21","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kulkarni"},{"key":"ref22","first-page":"23609","article-title":"A hierarchical reinforcement learning based optimization framework for large-scale dynamic pickup and delivery problems","volume":"34","author":"Ma","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S1386-4181(97)00012-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2001.041"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10679-005-7591-5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CIFEr.2014.6924109"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59410-7_42"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892166"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CIFEr.2014.6924100"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16083"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16142"},{"key":"ref34","first-page":"271","article-title":"Feudal reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dayan"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref36","first-page":"31","article-title":"Linear options","volume-title":"Proc. 9th Int. Conf. Auton. Agents Multiagent Syst.","author":"Sorg"},{"key":"ref37","first-page":"990","article-title":"Universal option models","volume":"27","author":"Szepesvari","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref39","first-page":"2125","article-title":"Variational information maximisation for intrinsically motivated reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mohamed"},{"key":"ref40","first-page":"1","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Eysenbach"},{"key":"ref41","first-page":"1","article-title":"Reinforcement learning with competitive ensembles of information-constrained primitives","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goyal"},{"key":"ref42","first-page":"1312","article-title":"Universal value function approximators","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schaul"},{"key":"ref43","first-page":"3307","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Nachum"},{"key":"ref44","first-page":"1","article-title":"Hindsight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref45","first-page":"1","article-title":"Learning multi-level hierarchies with hindsight","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Levy"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1080\/1350486X.2018.1506257"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.79.8.2554.PMC346238.PMID6953413"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref50","article-title":"Openai baselines: ACKTR & A2C","author":"Wu","year":"2017"},{"key":"ref51","article-title":"A machine learning approach to regime modeling","author":"Botte","year":"2021","journal-title":"Two Sigma"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-021-09820-1"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICSESS54813.2022.9930158"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102212"}],"container-title":["IEEE Transactions on Big Data"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6687317\/10530495\/10336391.pdf?arnumber=10336391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T17:41:41Z","timestamp":1715794901000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10336391\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":54,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tbdata.2023.3338011","relation":{},"ISSN":["2332-7790","2372-2096"],"issn-type":[{"value":"2332-7790","type":"electronic"},{"value":"2372-2096","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}