{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:33:55Z","timestamp":1730205235937,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010712","name":"Vietnam National University HoChiMinh City (VNU-HCM)","doi-asserted-by":"publisher","award":["C2024-26-05"],"award-info":[{"award-number":["C2024-26-05"]}],"id":[{"id":"10.13039\/501100010712","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/cec60901.2024.10611765","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:55:15Z","timestamp":1723139715000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Evolutionary Deep Reinforcement Learning via Hybridizing Estimation-of-Distribution Algorithms with Policy Gradients"],"prefix":"10.1109","author":[{"given":"Thai Bao","family":"Tran","sequence":"first","affiliation":[{"name":"University of Information Technology, Ho Chi Minh City, Vietnam Vietnam National University,Ho Chi Minh City,Vietnam"}]},{"given":"Ngoc Hoang","family":"Luong","sequence":"additional","affiliation":[{"name":"University of Information Technology, Ho Chi Minh City, Vietnam Vietnam National University,Ho Chi Minh City,Vietnam"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.011"},{"volume-title":"Reinforcement Learning: An Introduction, ser. Adaptive computation and machine learning","year":"1998","author":"Sutton","key":"ref2"},{"key":"ref3","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"ICML, ser. JMLR Workshop and Conference Proceedings","volume":"32","author":"Silver"},{"key":"ref4","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2016","journal-title":"ICLR"},{"key":"ref5","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"ICML, ser. Proceedings of Machine Learning Research","volume":"80","author":"Fujimoto"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20732"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3569096"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CEC55065.2022.9870209"},{"key":"ref9","article-title":"CEM-RL: combining evolutionary and gradient-based methods for policy search","author":"Pourchot","year":"2019","journal-title":"ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/NICS54270.2021.9701549"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45356-3_75"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1276958.1277066"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87700-4_14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/EVCO_a_00094"},{"key":"ref16","article-title":"The Nature of Statistical Learning Theory, Second Edition, ser","volume-title":"Statistics for Engineering and Information Science","author":"Vapnik","year":"2000"},{"key":"ref17","article-title":"Playing Atari with deep reinforcement learning","volume":"abs\/1312.5602","author":"Mnih","year":"2013","journal-title":"CoRR"},{"key":"ref18","first-page":"2613","article-title":"Double Q-learning","author":"van Hasselt","year":"2010","journal-title":"NIPS"},{"key":"ref19","article-title":"OpenAI Gym","volume":"abs\/1606.01540","author":"Brockman","year":"2016","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref21","first-page":"267:1","article-title":"Tianshou: A highly modularized deep reinforcement learning library","volume":"23","author":"Weng","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/evco_a_00260"}],"event":{"name":"2024 IEEE Congress on Evolutionary Computation (CEC)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 IEEE Congress on Evolutionary Computation (CEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609966\/10611750\/10611765.pdf?arnumber=10611765","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:21:04Z","timestamp":1723350064000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611765\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/cec60901.2024.10611765","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}