{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:54:49Z","timestamp":1784645689262,"version":"3.55.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0119903"],"award-info":[{"award-number":["2022ZD0119903"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019014","name":"Shanghai Science and Technology Program","doi-asserted-by":"publisher","award":["22015810300"],"award-info":[{"award-number":["22015810300"]}],"id":[{"id":"10.13039\/501100019014","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hainan Province Science and Technology Special Fund","award":["ZDYF2021GXJS041"],"award-info":[{"award-number":["ZDYF2021GXJS041"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2141234"],"award-info":[{"award-number":["U2141234"]}],"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":["U24A20260"],"award-info":[{"award-number":["U24A20260"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tsmc.2025.3525473","type":"journal-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T18:56:47Z","timestamp":1737572207000},"page":"2707-2720","source":"Crossref","is-referenced-by-count":4,"title":["Visionary Policy Iteration for Continuous Control"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2026-6856","authenticated-orcid":false,"given":"Botao","family":"Dong","sequence":"first","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5123-5043","authenticated-orcid":false,"given":"Longyang","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9212-3523","authenticated-orcid":false,"given":"Xiwen","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Oceanography, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8600-9668","authenticated-orcid":false,"given":"Hongtian","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4700-1276","authenticated-orcid":false,"given":"Weidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3364844"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3405568"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3276218"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3292253"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3051335"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3228901"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3336444"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3296769"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2962103"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3183991"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3214681"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3098451"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20684"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25865"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref17","first-page":"1","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2024.3398712"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3388007"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3065995"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3324215"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3202192"},{"key":"ref23","first-page":"7017","article-title":"Finite-time analysis of single-timescale actor-critic","volume-title":"Proc. 37th Adv. Neural Inf. Process. Syst.","volume":"36","author":"Chen"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2651104"},{"key":"ref25","first-page":"31811","article-title":"Accelerating reinforcement learning with value-conditional state entropy exploration","volume-title":"Proc. 37th Adv. Neural Inf. Process. Syst.","volume":"36","author":"Kim"},{"key":"ref26","first-page":"11767","article-title":"Softmax deep double deterministic policy gradients","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst.","volume":"33","author":"Pan"},{"key":"ref27","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Fujimoto"},{"key":"ref28","first-page":"317","article-title":"Foresight distribution adjustment for off-policy reinforcement learning","volume-title":"Proc. 23rd Int. Conf. Auton. Agents Multiagent Syst.","author":"Chen"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20732"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/422"},{"key":"ref31","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3329513"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2024.124281"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3385910"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref36","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref37","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref38","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref39","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref40","first-page":"9443","article-title":"State entropy maximization with random encoders for efficient exploration","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Seo"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3313312"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3009214"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00573-6"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322426"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3271642"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/10933809\/10849991.pdf?arnumber=10849991","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T23:30:11Z","timestamp":1743463811000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849991\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":47,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2025.3525473","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}