{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T15:44:10Z","timestamp":1778255050434,"version":"3.51.4"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100014219","name":"National Natural Science Foundation for Distinguished Young Scholars of China","doi-asserted-by":"publisher","award":["T2325018"],"award-info":[{"award-number":["T2325018"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171274"],"award-info":[{"award-number":["62171274"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2241228"],"award-info":[{"award-number":["U2241228"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"Shanghai Municipal Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tcyb.2024.3401014","type":"journal-article","created":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T17:57:27Z","timestamp":1718733447000},"page":"6048-6057","source":"Crossref","is-referenced-by-count":6,"title":["Efficient Reinforcement Learning With the Novel N-Step Method and V-Network"],"prefix":"10.1109","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9921-6511","authenticated-orcid":false,"given":"Miaomiao","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9589-5657","authenticated-orcid":false,"given":"Shuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Knowledge Based Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6039-160X","authenticated-orcid":false,"given":"Xinying","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyi","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyang","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Electronic Information Engineering, Naval Aeronautical University, Yantai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1301-9870","authenticated-orcid":false,"given":"Edmond Q.","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3238-745X","authenticated-orcid":false,"given":"Xin","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Intelligent Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3116063"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3283771"},{"key":"ref3","first-page":"12078","article-title":"Scalable deep reinforcement learning algorithms for mean field games","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lauriere"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/app13042443"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3241015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2022.03.013"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3061094"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3108034"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.03.037"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3111082"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3053414"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3041265"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3089941"},{"key":"ref15","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref16","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref17","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref20","first-page":"1587","article-title":"Addressing function approximation error in actor\u2013critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref21","article-title":"Reinforcement learning with dynamic boltzmann softmax updates","author":"Pan","year":"2019","journal-title":"arXiv:1903.05926"},{"key":"ref22","first-page":"11767","article-title":"Softmax deep double deterministic policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Pan"},{"key":"ref23","first-page":"176","article-title":"Averaged-DQN: Variance reduction and Stabilization for deep reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Oron"},{"key":"ref24","volume-title":"Maxmin Q-learning: Controlling the estimation bias of Q-learning","author":"Lan","year":"2020"},{"key":"ref25","first-page":"1","article-title":"Actor\u2013critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda"},{"key":"ref26","first-page":"7927","article-title":"GMAC: A distributional perspective on actor\u2013critic framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nam"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2618926"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20732"},{"key":"ref29","first-page":"1861","article-title":"Soft actor\u2013critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI50040.2020.00068"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3203024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2959129"},{"key":"ref35","article-title":"Efficient deep reinforcement learning requires regulating overfitting","author":"Li","year":"2023","journal-title":"arXiv:2304.10466"},{"key":"ref36","article-title":"Taming the noise in reinforcement learning via soft updates","author":"Fox","year":"2015","journal-title":"arXiv:1512.08562"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6614994"},{"key":"ref38","first-page":"1","article-title":"Regulating action value estimation in deep reinforcement learning","volume-title":"Proc. Adapt. Learning Agents Workshop","author":"Xue"},{"key":"ref39","article-title":"A review of safe reinforcement learning: Methods, theory and applications","author":"Gu","year":"2022","journal-title":"arXiv:2205.10330"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3263430"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2022.05.017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3121078"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3324601"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3059912"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3165074"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.03.018"},{"key":"ref48","first-page":"12733","article-title":"A long N-step surrogate stage reward for deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhong"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.4324\/9781315380636"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221036\/10711993\/10561592.pdf?arnumber=10561592","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T11:35:33Z","timestamp":1728560133000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10561592\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":50,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2024.3401014","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}