{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:48:52Z","timestamp":1771955332162,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2021M693002"],"award-info":[{"award-number":["2021M693002"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3351696","type":"journal-article","created":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T20:37:56Z","timestamp":1704832676000},"page":"12295-12307","source":"Crossref","is-referenced-by-count":5,"title":["An Improved Reinforcement Learning Method Based on Unsupervised Learning"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4505-522X","authenticated-orcid":false,"given":"Xin","family":"Chang","sequence":"first","affiliation":[{"name":"The 54th Research Institute of China Electronics Technology Group Corporation (CETC54), Shijiazhuang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbin","family":"Li","sequence":"additional","affiliation":[{"name":"The 54th Research Institute of China Electronics Technology Group Corporation (CETC54), Shijiazhuang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6149-6490","authenticated-orcid":false,"given":"Guanjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"The 54th Research Institute of China Electronics Technology Group Corporation (CETC54), Shijiazhuang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghui","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Management, Shijiazhuang Tiedao University, Shijiazhuang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changjun","family":"Fu","sequence":"additional","affiliation":[{"name":"The 54th Research Institute of China Electronics Technology Group Corporation (CETC54), Shijiazhuang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref2","volume-title":"Hands-On Reinforcement Learning With Python: Master Reinforcement and Deep Reinforcement Learning Using OpenAI Gym and TensorFlow","author":"Ravivhandiran","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3248796"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05732-2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3187030"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2954531"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2017.1700363"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879433"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2815018"},{"key":"ref12","article-title":"Revisiting distributed synchronous SGD","author":"Chen","year":"2016","journal-title":"arXiv:1604.00981"},{"key":"ref13","article-title":"Large scale distributed neural network training through online distillation","author":"Anil","year":"2018","journal-title":"arXiv:1804.03235"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.915114"},{"key":"ref15","article-title":"Hyper-parameter optimization: A review of algorithms and applications","author":"Yu","year":"2020","journal-title":"arXiv:2003.05689"},{"key":"ref16","article-title":"A tutorial on Bayesian optimization","author":"Frazier","year":"2018","journal-title":"arXiv:1807.02811"},{"key":"ref17","first-page":"1","article-title":"Algorithms for hyper-parameter optimization","volume-title":"Proc. 25th Annu. Conf. Neural Inf. Process. Syst.","author":"Bergstra"},{"key":"ref18","article-title":"Population based training of neural networks","author":"Jaderberg","year":"2017","journal-title":"arXiv:1711.09846"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/Radar53847.2021.10028041"},{"key":"ref20","volume-title":"Computational Intelligence: An Introduction","author":"Engelbrecht","year":"2004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3118899"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2871518"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1049\/iet-rsn.2015.0180"},{"key":"ref24","article-title":"Study on distributed cooperative jamming techniques against multichannel SAR","author":"Zhang","year":"2016"},{"key":"ref25","volume-title":"Interpretable Machine Learning. A Guide for Making Black Box Models Explainable","author":"Molnar","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3260977"},{"key":"ref27","volume-title":"Hands-on Machine Learning With Scikit-Learn, Keras, and TensorFlow","author":"Geron","year":"2019"},{"key":"ref28","volume-title":"Deep Hands-On Unsupervised Learning Using Python","author":"Patel","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557245"},{"issue":"1","key":"ref30","first-page":"188","article-title":"Detection of genes patterns with an enhanced partitioning-based DBSCAN algorithm","volume":"4","author":"Mohammed","year":"2018","journal-title":"J. Inf. Commun. Eng."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-018-1238-7"},{"key":"ref32","volume-title":"Deep Reinforcement Learning Hands-On: Apply Modern RL methods, With Deep Q-Networks, Value Iteration, Policy Gradients, TRPO, AlphaGo Zero and More","author":"Lapan","year":"2018"},{"key":"ref33","article-title":"Dueling network architectures for deep reinforcement learning","author":"Wang","year":"2015","journal-title":"arXiv:1511.06581"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24292-7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2605799"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1504\/IJAHUC.2014.066419"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511841224"},{"key":"ref38","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref39","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018","journal-title":"arXiv:1801.01290"},{"key":"ref40","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2019","journal-title":"arXiv:1812.05905"},{"key":"ref41","article-title":"Reinforcement learning with deep energy-based policies","author":"Haarnoja","year":"2017","journal-title":"arXiv:1702.08165"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2007.02.013"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10385075.pdf?arnumber=10385075","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T08:52:34Z","timestamp":1706777554000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10385075\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3351696","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}